Search

As urban residents demand higher travel quality, vehicle dispatch has become a critical component of online ride-hailing services. However, current vehicle dispatch systems struggle to navigate the complexities of urban traffic dynamics, including unpredictable traffic conditions, diverse driver behaviors, and fluctuating supply and demand patterns. These challenges have resulted in travel difficulties for passengers in certain areas, while many drivers in other areas are unable to secure orders, leading to a decline in the overall quality of urban transportation services. To address these issues, this paper introduces GARLIC: a framework of GPT-Augmented Reinforcement Learning with Intelligent Control for vehicle dispatching. GARLIC utilizes multiview graphs to capture hierarchical traffic states, and learns a dynamic reward function that accounts for individual driving behaviors. The framework further integrates a GPT model trained with a custom loss function to enable high-precision predictions and optimize dispatching policies in real-world scenarios. Experiments conducted on two real-world datasets demonstrate that GARLIC effectively aligns with driver behaviors while reducing the empty load rate of vehicles.

Multi-modal Large Language Models (MLLMs) have advanced significantly, offering powerful vision-language understanding capabilities. However, these models often inherit severe social biases from their training datasets, leading to unfair predictions based on attributes like race and gender. This paper addresses the issue of social biases in MLLMs by i) Introducing a comprehensive Counterfactual dataset with Multiple Social Concepts (CMSC), which provides a more diverse and extensive training set compared to existing datasets. ii) Proposing an Anti-Stereotype Debiasing strategy (ASD). Our method works by revisiting the MLLM training process, rescaling the autoregressive loss function, and improving data sampling methods to counteract biases. Through extensive experiments on various MLLMs, our CMSC dataset and ASD method demonstrate a significant reduction in social biases while maintaining the models' original performance.

Building a general-purpose agent is a long-standing vision in the field of artificial intelligence. Existing agents have made remarkable progress in many domains, yet they still struggle to complete long-horizon tasks in an open world. We attribute this to the lack of necessary world knowledge and multimodal experience that can guide agents through a variety of long-horizon tasks. In this paper, we propose a Hybrid Multimodal Memory module to address the above challenges. It 1) transforms knowledge into Hierarchical Directed Knowledge Graph that allows agents to explicitly represent and learn world knowledge, and 2) summarises historical information into Abstracted Multimodal Experience Pool that provide agents with rich references for in-context learning. On top of the Hybrid Multimodal Memory module, a multimodal agent, Optimus-1, is constructed with dedicated Knowledge-guided Planner and Experience-Driven Reflector, contributing to a better planning and reflection in the face of long-horizon tasks in Minecraft. Extensive experimental results show that Optimus-1 significantly outperforms all existing agents on challenging long-horizon task benchmarks, and exhibits near human-level performance on many tasks. In addition, we introduce various Multimodal Large Language Models (MLLMs) as the backbone of Optimus-1. Experimental results show that Optimus-1 exhibits strong generalization with the help of the Hybrid Multimodal Memory module, outperforming the GPT-4V baseline on many tasks., Comment: 30 pages, 13 figures

In this technical report, we present our solution for the EgoPlan Challenge in ICML 2024. To address the real-world egocentric task planning problem, we introduce a novel planning framework which comprises three stages: long-term memory Extraction, context-awared Planning, and multi-iteration Decision, named EPD. Given the task goal, task progress, and current observation, the extraction model first extracts task-relevant memory information from the progress video, transforming the complex long video into summarized memory information. The planning model then combines the context of the memory information with fine-grained visual information from the current observation to predict the next action. Finally, through multi-iteration decision-making, the decision model comprehensively understands the task situation and current state to make the most realistic planning decision. On the EgoPlan-Test set, EPD achieves a planning accuracy of 53.85% over 1,584 egocentric task planning questions. We have made all codes available at https://github.com/Kkskkkskr/EPD .

Text-to-image retrieval is a fundamental task in multimedia processing, aiming to retrieve semantically relevant cross-modal content. Traditional studies have typically approached this task as a discriminative problem, matching the text and image via the cross-attention mechanism (one-tower framework) or in a common embedding space (two-tower framework). Recently, generative cross-modal retrieval has emerged as a new research line, which assigns images with unique string identifiers and generates the target identifier as the retrieval target. Despite its great potential, existing generative approaches are limited due to the following issues: insufficient visual information in identifiers, misalignment with high-level semantics, and learning gap towards the retrieval target. To address the above issues, we propose an autoregressive voken generation method, named AVG. AVG tokenizes images into vokens, i.e., visual tokens, and innovatively formulates the text-to-image retrieval task as a token-to-voken generation problem. AVG discretizes an image into a sequence of vokens as the identifier of the image, while maintaining the alignment with both the visual information and high-level semantics of the image. Additionally, to bridge the learning gap between generative training and the retrieval target, we incorporate discriminative training to modify the learning direction during token-to-voken training. Extensive experiments demonstrate that AVG achieves superior results in both effectiveness and efficiency., Comment: Work in progress

Cropping high-resolution document images into multiple sub-images is the most widely used approach for current Multimodal Large Language Models (MLLMs) to do document understanding. Most of current document understanding methods preserve all tokens within sub-images and treat them equally. This neglects their different informativeness and leads to a significant increase in the number of image tokens. To perform a more adaptive and efficient document understanding, we propose Token-level Correlation-guided Compression, a parameter-free and plug-and-play methodology to optimize token processing. Firstly, we propose an innovative approach for assessing the pattern repetitiveness based on the correlation between each patch tokens. This method identifies redundant tokens, allowing for the determination of the sub-image's information density. Secondly, we present a token-level sampling method that efficiently captures the most informative tokens by delving into the correlation between the [CLS] token and patch tokens. By integrating these strategies, we develop a plug-and-play adaptive compressor module that can be seamlessly incorporated into MLLMs utilizing cropping techniques. This module not only enhances the processing speed during training and inference but also maintains comparable performance. We conduct experiments with the SOTA document understanding model mPLUG-DocOwl1.5 and the effectiveness is demonstrated through extensive comparisons with other compression methods.

Multimodal large language models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, a generalist MLLM typically underperforms compared with a specialist MLLM on most VL tasks, which can be attributed to task interference. In this paper, we propose a mixture of multimodal experts (MoME) to mitigate task interference and obtain a generalist MLLM. Our MoME is composed of two key components, a mixture of vision experts (MoVE) and a mixture of language experts (MoLE). MoVE can adaptively modulate the features transformed from various vision encoders, and has a strong compatibility in transformation architecture. MoLE incorporates sparsely gated experts into LLMs to achieve painless improvements with roughly unchanged inference costs. In response to task interference, our MoME specializes in both vision and language modality to adapt to task discrepancies. Extensive experiments show that MoME significantly improves the performance of generalist MLLMs across various VL tasks. The source code is released at https://github.com/JiuTian-VL/MoME, Comment: Github: https://github.com/JiuTian-VL/MoME

Few-shot class-incremental learning (FSCIL) confronts the challenge of integrating new classes into a model with minimal training samples while preserving the knowledge of previously learned classes. Traditional methods widely adopt static adaptation relying on a fixed parameter space to learn from data that arrive sequentially, prone to overfitting to the current session. Existing dynamic strategies require the expansion of the parameter space continually, leading to increased complexity. In this study, we explore the potential of Selective State Space Models (SSMs) for FSCIL, leveraging its dynamic weights and strong ability in sequence modeling to address these challenges. Concretely, we propose a dual selective SSM projector that dynamically adjusts the projection parameters based on the intermediate features for dynamic adaptation. The dual design enables the model to maintain the robust features of base classes, while adaptively learning distinctive feature shifts for novel classes. Additionally, we develop a class-sensitive selective scan mechanism to guide dynamic adaptation. It minimizes the disruption to base-class representations caused by training on novel data, and meanwhile, forces the selective scan to perform in distinct patterns between base and novel classes. Experiments on miniImageNet, CUB-200, and CIFAR-100 demonstrate that our framework outperforms the existing state-of-the-art methods. The code is available at \url{https://github.com/xiaojieli0903/Mamba-FSCIL}., Comment: Code: https://github.com/xiaojieli0903/Mamba-FSCIL

The rapid evolution of deep learning and large language models has led to an exponential growth in the demand for training data, prompting the development of Dataset Distillation methods to address the challenges of managing large datasets. Among these, Matching Training Trajectories (MTT) has been a prominent approach, which replicates the training trajectory of an expert network on real data with a synthetic dataset. However, our investigation found that this method suffers from three significant limitations: 1. Instability of expert trajectory generated by Stochastic Gradient Descent (SGD); 2. Low convergence speed of the distillation process; 3. High storage consumption of the expert trajectory. To address these issues, we offer a new perspective on understanding the essence of Dataset Distillation and MTT through a simple transformation of the objective function, and introduce a novel method called Matching Convexified Trajectory (MCT), which aims to provide better guidance for the student trajectory. MCT leverages insights from the linearized dynamics of Neural Tangent Kernel methods to create a convex combination of expert trajectories, guiding the student network to converge rapidly and stably. This trajectory is not only easier to store, but also enables a continuous sampling strategy during distillation, ensuring thorough learning and fitting of the entire expert trajectory. Comprehensive experiments across three public datasets validate the superiority of MCT over traditional MTT methods., Comment: 11 pages

In this report, we present our approach for the Natural Language Query track and Goal Step track of the Ego4D Episodic Memory Benchmark at CVPR 2024. Both challenges require the localization of actions within long video sequences using textual queries. To enhance localization accuracy, our method not only processes the temporal information of videos but also identifies fine-grained objects spatially within the frames. To this end, we introduce a novel approach, termed ObjectNLQ, which incorporates an object branch to augment the video representation with detailed object information, thereby improving grounding efficiency. ObjectNLQ achieves a mean R@1 of 23.15, ranking 2nd in the Natural Language Queries Challenge, and gains 33.00 in terms of the metric R@1, IoU=0.3, ranking 3rd in the Goal Step Challenge. Our code will be released at https://github.com/Yisen-Feng/ObjectNLQ., Comment: The solution for the Natural Language Query track and Goal Step track at CVPR EgoVis Workshop 2024

In this report, we present our champion solution for Ego4D EgoSchema Challenge in CVPR 2024. To deeply integrate the powerful egocentric captioning model and question reasoning model, we propose a novel Hierarchical Comprehension scheme for egocentric video Question Answering, named HCQA. It consists of three stages: Fine-grained Caption Generation, Context-driven Summarization, and Inference-guided Answering. Given a long-form video, HCQA captures local detailed visual information and global summarised visual information via Fine-grained Caption Generation and Context-driven Summarization, respectively. Then in Inference-guided Answering, HCQA utilizes this hierarchical information to reason and answer given question. On the EgoSchema blind test set, HCQA achieves 75% accuracy in answering over 5,000 human curated multiple-choice questions. Our code will be released at https://github.com/Hyu-Zhang/HCQA., Comment: The champion solution for Ego4D EgoSchema Challenge in CVPR EgoVis Workshop 2024

The recent surge of versatile large language models (LLMs) largely depends on aligning increasingly capable foundation models with human intentions by preference learning, enhancing LLMs with excellent applicability and effectiveness in a wide range of contexts. Despite the numerous related studies conducted, a perspective on how human preferences are introduced into LLMs remains limited, which may prevent a deeper comprehension of the relationships between human preferences and LLMs as well as the realization of their limitations. In this survey, we review the progress in exploring human preference learning for LLMs from a preference-centered perspective, covering the sources and formats of preference feedback, the modeling and usage of preference signals, as well as the evaluation of the aligned LLMs. We first categorize the human feedback according to data sources and formats. We then summarize techniques for human preferences modeling and compare the advantages and disadvantages of different schools of models. Moreover, we present various preference usage methods sorted by the objectives to utilize human preference signals. Finally, we summarize some prevailing approaches to evaluate LLMs in terms of alignment with human intentions and discuss our outlooks on the human intention alignment for LLMs., Comment: IEEE copyright statement added (also applied to the former version)

How humans can efficiently and effectively acquire images has always been a perennial question. A typical solution is text-to-image retrieval from an existing database given the text query; however, the limited database typically lacks creativity. By contrast, recent breakthroughs in text-to-image generation have made it possible to produce fancy and diverse visual content, but it faces challenges in synthesizing knowledge-intensive images. In this work, we rethink the relationship between text-to-image generation and retrieval and propose a unified framework in the context of Multimodal Large Language Models (MLLMs). Specifically, we first explore the intrinsic discriminative abilities of MLLMs and introduce a generative retrieval method to perform retrieval in a training-free manner. Subsequently, we unify generation and retrieval in an autoregressive generation way and propose an autonomous decision module to choose the best-matched one between generated and retrieved images as the response to the text query. Additionally, we construct a benchmark called TIGeR-Bench, including creative and knowledge-intensive domains, to standardize the evaluation of unified text-to-image generation and retrieval. Extensive experimental results on TIGeR-Bench and two retrieval benchmarks, i.e., Flickr30K and MS-COCO, demonstrate the superiority and effectiveness of our proposed method.

While the conditional sequence modeling with the transformer architecture has demonstrated its effectiveness in dealing with offline reinforcement learning (RL) tasks, it is struggle to handle out-of-distribution states and actions. Existing work attempts to address this issue by data augmentation with the learned policy or adding extra constraints with the value-based RL algorithm. However, these studies still fail to overcome the following challenges: (1) insufficiently utilizing the historical temporal information among inter-steps, (2) overlooking the local intrastep relationships among states, actions and return-to-gos (RTGs), (3) overfitting suboptimal trajectories with noisy labels. To address these challenges, we propose Decision Mamba (DM), a novel multi-grained state space model (SSM) with a self-evolving policy learning strategy. DM explicitly models the historical hidden state to extract the temporal information by using the mamba architecture. To capture the relationship among state-action-RTG triplets, a fine-grained SSM module is designed and integrated into the original coarse-grained SSM in mamba, resulting in a novel mamba architecture tailored for offline RL. Finally, to mitigate the overfitting issue on noisy trajectories, a self-evolving policy is proposed by using progressive regularization. The policy evolves by using its own past knowledge to refine the suboptimal actions, thus enhancing its robustness on noisy demonstrations. Extensive experiments on various tasks show that DM outperforms other baselines substantially.

Current parameter-efficient fine-tuning (PEFT) methods build adapters without considering the context of downstream task to learn, or the context of important knowledge to maintain. As a result, there is often a performance gap compared to full-parameter finetuning, and meanwhile the finetuned model suffers from catastrophic forgetting of the pre-trained world knowledge. In this paper, we propose CorDA, a Context-oriented Decomposition Adaptation method that builds learnable adapters from weight decomposition oriented by the context of downstream task or world knowledge. Concretely, we collect a few data samples, and perform singular value decomposition for each linear layer of a pre-trained LLM multiplied by the covariance matrix of the input activation using these samples. By doing so, the context of the representative samples is captured through deciding the factorizing orientation. Our method enables two options, the knowledge-preserved adaptation and the instruction-previewed adaptation. For the former, we use question-answering samples to obtain the covariance matrices, and use the decomposed components with the smallest $r$ singular values to initialize a learnable adapter, with the others frozen such that the world knowledge is better preserved. For the latter, we use the instruction data from the finetuning task, such as math or coding, to orientate the decomposition and train the largest $r$ components that capture the main characteristics of the task to learn. We conduct extensive experiments on Math, Code, and Instruction Following tasks. Our knowledge-preserved adaptation not only achieves better performance than LoRA on finetuning tasks, but also mitigates the forgetting of world knowledge. Our instruction-previewed adaptation is able to further enhance the finetuning performance, surpassing full-parameter finetuning and the state-of-the-art PEFT methods.

Visual Commonsense Reasoning (VCR) calls for explanatory reasoning behind question answering over visual scenes. To achieve this goal, a model is required to provide an acceptable rationale as the reason for the predicted answers. Progress on the benchmark dataset stems largely from the recent advancement of Vision-Language Transformers (VL Transformers). These models are first pre-trained on some generic large-scale vision-text datasets, and then the learned representations are transferred to the downstream VCR task. Despite their attractive performance, this paper posits that the VL Transformers do not exhibit visual commonsense, which is the key to VCR. In particular, our empirical results pinpoint several shortcomings of existing VL Transformers: small gains from pre-training, unexpected language bias, limited model architecture for the two inseparable sub-tasks, and neglect of the important object-tag correlation. With these findings, we tentatively suggest some future directions from the aspect of dataset, evaluation metric, and training tricks. We believe this work could make researchers revisit the intuition and goals of VCR, and thus help tackle the remaining challenges in visual reasoning.

Loss functions and sample mining strategies are essential components in deep metric learning algorithms. However, the existing loss function or mining strategy often necessitate the incorporation of additional hyperparameters, notably the threshold, which defines whether the sample pair is informative. The threshold provides a stable numerical standard for determining whether to retain the pairs. It is a vital parameter to reduce the redundant sample pairs participating in training. Nonetheless, finding the optimal threshold can be a time-consuming endeavor, often requiring extensive grid searches. Because the threshold cannot be dynamically adjusted in the training stage, we should conduct plenty of repeated experiments to determine the threshold. Therefore, we introduce a novel approach for adjusting the thresholds associated with both the loss function and the sample mining strategy. We design a static Asymmetric Sample Mining Strategy (ASMS) and its dynamic version Adaptive Tolerance ASMS (AT-ASMS), tailored for sample mining methods. ASMS utilizes differentiated thresholds to address the problems (too few positive pairs and too many redundant negative pairs) caused by only applying a single threshold to filter samples. AT-ASMS can adaptively regulate the ratio of positive and negative pairs during training according to the ratio of the currently mined positive and negative pairs. This meta-learning-based threshold generation algorithm utilizes a single-step gradient descent to obtain new thresholds. We combine these two threshold adjustment algorithms to form the Dual Dynamic Threshold Adjustment Strategy (DDTAS). Experimental results show that our algorithm achieves competitive performance on CUB200, Cars196, and SOP datasets., Comment: accepted by ACM Transactions on Multimedia Computing, Communications, and Applications

With the information explosion on the Web, search and recommendation are foundational infrastructures to satisfying users' information needs. As the two sides of the same coin, both revolve around the same core research problem, matching queries with documents or users with items. In the recent few decades, search and recommendation have experienced synchronous technological paradigm shifts, including machine learning-based and deep learning-based paradigms. Recently, the superintelligent generative large language models have sparked a new paradigm in search and recommendation, i.e., generative search (retrieval) and recommendation, which aims to address the matching problem in a generative manner. In this paper, we provide a comprehensive survey of the emerging paradigm in information systems and summarize the developments in generative search and recommendation from a unified perspective. Rather than simply categorizing existing works, we abstract a unified framework for the generative paradigm and break down the existing works into different stages within this framework to highlight the strengths and weaknesses. And then, we distinguish generative search and recommendation with their unique challenges, identify open problems and future directions, and envision the next information-seeking paradigm.

Multimodal recommendation aims to recommend user-preferred candidates based on her/his historically interacted items and associated multimodal information. Previous studies commonly employ an embed-and-retrieve paradigm: learning user and item representations in the same embedding space, then retrieving similar candidate items for a user via embedding inner product. However, this paradigm suffers from inference cost, interaction modeling, and false-negative issues. Toward this end, we propose a new MMGRec model to introduce a generative paradigm into multimodal recommendation. Specifically, we first devise a hierarchical quantization method Graph RQ-VAE to assign Rec-ID for each item from its multimodal and CF information. Consisting of a tuple of semantically meaningful tokens, Rec-ID serves as the unique identifier of each item. Afterward, we train a Transformer-based recommender to generate the Rec-IDs of user-preferred items based on historical interaction sequences. The generative paradigm is qualified since this model systematically predicts the tuple of tokens identifying the recommended item in an autoregressive manner. Moreover, a relation-aware self-attention mechanism is devised for the Transformer to handle non-sequential interaction sequences, which explores the element pairwise relation to replace absolute positional encoding. Extensive experiments evaluate MMGRec's effectiveness compared with state-of-the-art methods.

Composed image retrieval (CIR) aims to retrieve the target image based on a multimodal query, i.e., a reference image paired with corresponding modification text. Recent CIR studies leverage vision-language pre-trained (VLP) methods as the feature extraction backbone, and perform nonlinear feature-level multimodal query fusion to retrieve the target image. Despite the promising performance, we argue that their nonlinear feature-level multimodal fusion may lead to the fused feature deviating from the original embedding space, potentially hurting the retrieval performance. To address this issue, in this work, we propose shifting the multimodal fusion from the feature level to the raw-data level to fully exploit the VLP model's multimodal encoding and cross-modal alignment abilities. In particular, we introduce a Dual Query Unification-based Composed Image Retrieval framework (DQU-CIR), whose backbone simply involves a VLP model's image encoder and a text encoder. Specifically, DQU-CIR first employs two training-free query unification components: text-oriented query unification and vision-oriented query unification, to derive a unified textual and visual query based on the raw data of the multimodal query, respectively. The unified textual query is derived by concatenating the modification text with the extracted reference image's textual description, while the unified visual query is created by writing the key modification words onto the reference image. Ultimately, to address diverse search intentions, DQU-CIR linearly combines the features of the two unified queries encoded by the VLP model to retrieve the target image. Extensive experiments on four real-world datasets validate the effectiveness of our proposed method., Comment: ACM SIGIR 2024

Conventional video object segmentation (VOS) methods usually necessitate a substantial volume of pixel-level annotated video data for fully supervised learning. In this paper, we present HVC, a \textbf{h}ybrid static-dynamic \textbf{v}isual \textbf{c}orrespondence framework for self-supervised VOS. HVC extracts pseudo-dynamic signals from static images, enabling an efficient and scalable VOS model. Our approach utilizes a minimalist fully-convolutional architecture to capture static-dynamic visual correspondence in image-cropped views. To achieve this objective, we present a unified self-supervised approach to learn visual representations of static-dynamic feature similarity. Firstly, we establish static correspondence by utilizing a priori coordinate information between cropped views to guide the formation of consistent static feature representations. Subsequently, we devise a concise convolutional layer to capture the forward / backward pseudo-dynamic signals between two views, serving as cues for dynamic representations. Finally, we propose a hybrid visual correspondence loss to learn joint static and dynamic consistency representations. Our approach, without bells and whistles, necessitates only one training session using static image data, significantly reducing memory consumption ($\sim$16GB) and training time ($\sim$\textbf{2h}). Moreover, HVC achieves state-of-the-art performance in several self-supervised VOS benchmarks and additional video label propagation tasks.

Lexicon-based retrieval has gained siginificant popularity in text retrieval due to its efficient and robust performance. To further enhance performance of lexicon-based retrieval, researchers have been diligently incorporating state-of-the-art methodologies like Neural retrieval and text-level contrastive learning approaches. Nonetheless, despite the promising outcomes, current lexicon-based retrieval methods have received limited attention in exploring the potential benefits of feature context representations and term-level knowledge guidance. In this paper, we introduce an innovative method by introducing FEature Context and TErm-level Knowledge modules(FecTek). To effectively enrich the feature context representations of term weight, the Feature Context Module (FCM) is introduced, which leverages the power of BERT's representation to determine dynamic weights for each element in the embedding. Additionally, we develop a term-level knowledge guidance module (TKGM) for effectively utilizing term-level knowledge to intelligently guide the modeling process of term weight. Evaluation of the proposed method on MS Marco benchmark demonstrates its superiority over the previous state-of-the-art approaches.

Graph Convolution Networks (GCNs) have significantly succeeded in learning user and item representations for recommendation systems. The core of their efficacy is the ability to explicitly exploit the collaborative signals from both the first- and high-order neighboring nodes. However, most existing GCN-based methods overlook the multiple interests of users while performing high-order graph convolution. Thus, the noisy information from unreliable neighbor nodes (e.g., users with dissimilar interests) negatively impacts the representation learning of the target node. Additionally, conducting graph convolution operations without differentiating high-order neighbors suffers the over-smoothing issue when stacking more layers, resulting in performance degradation. In this paper, we aim to capture more valuable information from high-order neighboring nodes while avoiding noise for better representation learning of the target node. To achieve this goal, we propose a novel GCN-based recommendation model, termed Cluster-based Graph Collaborative Filtering (ClusterGCF). This model performs high-order graph convolution on cluster-specific graphs, which are constructed by capturing the multiple interests of users and identifying the common interests among them. Specifically, we design an unsupervised and optimizable soft node clustering approach to classify user and item nodes into multiple clusters. Based on the soft node clustering results and the topology of the user-item interaction graph, we assign the nodes with probabilities for different clusters to construct the cluster-specific graphs. To evaluate the effectiveness of ClusterGCF, we conducted extensive experiments on four publicly available datasets. Experimental results demonstrate that our model can significantly improve recommendation performance., Comment: 22 pages, 8 figures

Multimodal Large Language Models (MLLMs) have shown impressive reasoning abilities and general intelligence in various domains. It inspires researchers to train end-to-end MLLMs or utilize large models to generate policies with human-selected prompts for embodied agents. However, these methods exhibit limited generalization capabilities on unseen tasks or scenarios, and overlook the multimodal environment information which is critical for robots to make decisions. In this paper, we introduce a novel Robotic Multimodal Perception-Planning (RoboMP$^2$) framework for robotic manipulation which consists of a Goal-Conditioned Multimodal Preceptor (GCMP) and a Retrieval-Augmented Multimodal Planner (RAMP). Specially, GCMP captures environment states by employing a tailored MLLMs for embodied agents with the abilities of semantic reasoning and localization. RAMP utilizes coarse-to-fine retrieval method to find the $k$ most-relevant policies as in-context demonstrations to enhance the planner. Extensive experiments demonstrate the superiority of RoboMP$^2$ on both VIMA benchmark and real-world tasks, with around 10% improvement over the baselines., Comment: Accepted by ICML 2024; Project page: https://aopolin-lv.github.io/RoboMP2.github.io/

Personality detection aims to detect one's personality traits underlying in social media posts. One challenge of this task is the scarcity of ground-truth personality traits which are collected from self-report questionnaires. Most existing methods learn post features directly by fine-tuning the pre-trained language models under the supervision of limited personality labels. This leads to inferior quality of post features and consequently affects the performance. In addition, they treat personality traits as one-hot classification labels, overlooking the semantic information within them. In this paper, we propose a large language model (LLM) based text augmentation enhanced personality detection model, which distills the LLM's knowledge to enhance the small model for personality detection, even when the LLM fails in this task. Specifically, we enable LLM to generate post analyses (augmentations) from the aspects of semantic, sentiment, and linguistic, which are critical for personality detection. By using contrastive learning to pull them together in the embedding space, the post encoder can better capture the psycho-linguistic information within the post representations, thus improving personality detection. Furthermore, we utilize the LLM to enrich the information of personality labels for enhancing the detection performance. Experimental results on the benchmark datasets demonstrate that our model outperforms the state-of-the-art methods on personality detection.

Despite advancements in text-to-image generation (T2I), prior methods often face text-image misalignment problems such as relation confusion in generated images. Existing solutions involve cross-attention manipulation for better compositional understanding or integrating large language models for improved layout planning. However, the inherent alignment capabilities of T2I models are still inadequate. By reviewing the link between generative and discriminative modeling, we posit that T2I models' discriminative abilities may reflect their text-image alignment proficiency during generation. In this light, we advocate bolstering the discriminative abilities of T2I models to achieve more precise text-to-image alignment for generation. We present a discriminative adapter built on T2I models to probe their discriminative abilities on two representative tasks and leverage discriminative fine-tuning to improve their text-image alignment. As a bonus of the discriminative adapter, a self-correction mechanism can leverage discriminative gradients to better align generated images to text prompts during inference. Comprehensive evaluations across three benchmark datasets, including both in-distribution and out-of-distribution scenarios, demonstrate our method's superior generation performance. Meanwhile, it achieves state-of-the-art discriminative performance on the two discriminative tasks compared to other generative models., Comment: CVPR 2024; project page: https://dpt-t2i.github.io/

Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process. This paper addresses these challenges by focusing on the quantization of LLMs, a technique that reduces memory consumption by converting model parameters and activations into low-bit integers. We critically analyze the existing quantization approaches, identifying their limitations in balancing the accuracy and efficiency of the quantized LLMs. To advance beyond these limitations, we propose WKVQuant, a PTQ framework especially designed for quantizing weights and the key/value (KV) cache of LLMs. Specifically, we incorporates past-only quantization to improve the computation of attention. Additionally, we introduce two-dimensional quantization strategy to handle the distribution of KV cache, along with a cross-block reconstruction regularization for parameter optimization. Experiments show that WKVQuant achieves almost comparable memory savings to weight-activation quantization, while also approaching the performance of weight-only quantization., Comment: Frist work to exclusively quantize weight and Key/Value cache for large language models

Recommending fashion items often leverages rich user profiles and makes targeted suggestions based on past history and previous purchases. In this paper, we work under the assumption that no prior knowledge is given about a user. We propose to build a user profile on the fly by integrating user reactions as we recommend complementary items to compose an outfit. We present a reinforcement learning agent capable of suggesting appropriate garments and ingesting user feedback so to improve its recommendations and maximize user satisfaction. To train such a model, we resort to a proxy model to be able to simulate having user feedback in the training loop. We experiment on the IQON3000 fashion dataset and we find that a reinforcement learning-based agent becomes capable of improving its recommendations by taking into account personal preferences. Furthermore, such task demonstrated to be hard for non-reinforcement models, that cannot exploit exploration during training.

The recent advancements in generative language models have demonstrated their ability to memorize knowledge from documents and recall knowledge to respond to user queries effectively. Building upon this capability, we propose to enable multimodal large language models (MLLMs) to memorize and recall images within their parameters. Given a user query for visual content, the MLLM is anticipated to "recall" the relevant image from its parameters as the response. Achieving this target presents notable challenges, including inbuilt visual memory and visual recall schemes within MLLMs. To address these challenges, we introduce a generative cross-modal retrieval framework, which assigns unique identifier strings to represent images and involves two training steps: learning to memorize and learning to retrieve. The first step focuses on training the MLLM to memorize the association between images and their respective identifiers. The latter step teaches the MLLM to generate the corresponding identifier of the target image, given the textual query input. By memorizing images in MLLMs, we introduce a new paradigm to cross-modal retrieval, distinct from previous discriminative approaches. The experiments demonstrate that the generative paradigm performs effectively and efficiently even with large-scale image candidate sets.

Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target. This paradigm leverages powerful generative language models, distinct from traditional sparse or dense retrieval methods. In this work, we identify a viable direction to further enhance generative retrieval via distillation and propose a feasible framework, named DGR. DGR utilizes sophisticated ranking models, such as the cross-encoder, in a teacher role to supply a passage rank list, which captures the varying relevance degrees of passages instead of binary hard labels; subsequently, DGR employs a specially designed distilled RankNet loss to optimize the generative retrieval model, considering the passage rank order provided by the teacher model as labels. This framework only requires an additional distillation step to enhance current generative retrieval systems and does not add any burden to the inference stage. We conduct experiments on four public datasets, and the results indicate that DGR achieves state-of-the-art performance among the generative retrieval methods. Additionally, DGR demonstrates exceptional robustness and generalizability with various teacher models and distillation losses.

Sarcasm Explanation in Dialogue (SED) is a new yet challenging task, which aims to generate a natural language explanation for the given sarcastic dialogue that involves multiple modalities (i.e., utterance, video, and audio). Although existing studies have achieved great success based on the generative pretrained language model BART, they overlook exploiting the sentiments residing in the utterance, video and audio, which are vital clues for sarcasm explanation. In fact, it is non-trivial to incorporate sentiments for boosting SED performance, due to three main challenges: 1) diverse effects of utterance tokens on sentiments; 2) gap between video-audio sentiment signals and the embedding space of BART; and 3) various relations among utterances, utterance sentiments, and video-audio sentiments. To tackle these challenges, we propose a novel sEntiment-enhanceD Graph-based multimodal sarcasm Explanation framework, named EDGE. In particular, we first propose a lexicon-guided utterance sentiment inference module, where a heuristic utterance sentiment refinement strategy is devised. We then develop a module named Joint Cross Attention-based Sentiment Inference (JCA-SI) by extending the multimodal sentiment analysis model JCA to derive the joint sentiment label for each video-audio clip. Thereafter, we devise a context-sentiment graph to comprehensively model the semantic relations among the utterances, utterance sentiments, and video-audio sentiments, to facilitate sarcasm explanation generation. Extensive experiments on the publicly released dataset WITS verify the superiority of our model over cutting-edge methods.

Speculative decoding is a relatively new decoding framework that leverages small and efficient draft models to reduce the latency of LLMs. In this study, we introduce GliDe and CaPE, two low-hassle modifications to vanilla speculative decoding to further improve the decoding speed of a frozen LLM. Specifically, GliDe is a modified draft model architecture that reuses the cached keys and values from the target LLM, while CaPE is a proposal expansion method that uses the draft model's confidence scores to help select additional candidate tokens for verification. Extensive experiments on different benchmarks demonstrate that our proposed GliDe draft model significantly reduces the expected decoding latency. Additional evaluation using walltime reveals that GliDe can accelerate Vicuna models up to 2.17x and further extend the improvement to 2.61x with CaPE. We will release our code, data, and the trained draft models.

Detecting diffusion-generated images has recently grown into an emerging research area. Existing diffusion-based datasets predominantly focus on general image generation. However, facial forgeries, which pose a more severe social risk, have remained less explored thus far. To address this gap, this paper introduces DiFF, a comprehensive dataset dedicated to face-focused diffusion-generated images. DiFF comprises over 500,000 images that are synthesized using thirteen distinct generation methods under four conditions. In particular, this dataset leverages 30,000 carefully collected textual and visual prompts, ensuring the synthesis of images with both high fidelity and semantic consistency. We conduct extensive experiments on the DiFF dataset via a human test and several representative forgery detection methods. The results demonstrate that the binary detection accuracy of both human observers and automated detectors often falls below 30%, shedding light on the challenges in detecting diffusion-generated facial forgeries. Furthermore, we propose an edge graph regularization approach to effectively enhance the generalization capability of existing detectors., Comment: The dataset will be released at \url{https://github.com/xaCheng1996/DiFF}

The image-level label has prevailed in weakly supervised semantic segmentation tasks due to its easy availability. Since image-level labels can only indicate the existence or absence of specific categories of objects, visualization-based techniques have been widely adopted to provide object location clues. Considering class activation maps (CAMs) can only locate the most discriminative part of objects, recent approaches usually adopt an expansion strategy to enlarge the activation area for more integral object localization. However, without proper constraints, the expanded activation will easily intrude into the background region. In this paper, we propose spatial structure constraints (SSC) for weakly supervised semantic segmentation to alleviate the unwanted object over-activation of attention expansion. Specifically, we propose a CAM-driven reconstruction module to directly reconstruct the input image from deep CAM features, which constrains the diffusion of last-layer object attention by preserving the coarse spatial structure of the image content. Moreover, we propose an activation self-modulation module to refine CAMs with finer spatial structure details by enhancing regional consistency. Without external saliency models to provide background clues, our approach achieves 72.7\% and 47.0\% mIoU on the PASCAL VOC 2012 and COCO datasets, respectively, demonstrating the superiority of our proposed approach., Comment: accepted by IEEE Transactions on Image Processing

Large Language Models (LLMs) have shown remarkable performance in various emotion recognition tasks, thereby piquing the research community's curiosity for exploring their potential in emotional intelligence. However, several issues in the field of emotional generation tasks remain unresolved, including human preference alignment and emotional generation assessment. In this paper, we propose the Emotional Chain-of-Thought (ECoT), a plug-and-play prompting method that enhances the performance of LLMs on various emotional generation tasks by aligning with human emotional intelligence guidelines. To assess the reliability of ECoT, we propose an automated model-based evaluation method called Emotional Generation Score (EGS). EGS incorporates Goleman's Emotional Intelligence Theory as a consensus of human experts, providing a new perspective on the evaluation of emotional generation tasks. Extensive experimental results demonstrate the effectiveness of ECoT and EGS. Further, we discuss the promise of LLMs in the field of emotional intelligence and present key insights into the LLMs with the ECoT in emotional generation tasks.

Recommendation systems harness user-item interactions like clicks and reviews to learn their representations. Previous studies improve recommendation accuracy and interpretability by modeling user preferences across various aspects and intents. However, the aspects and intents are inferred directly from user reviews or behavior patterns, suffering from the data noise and the data sparsity problem. Furthermore, it is difficult to understand the reasons behind recommendations due to the challenges of interpreting implicit aspects and intents. Inspired by the deep semantic understanding offered by large language models (LLMs), we introduce a chain-based prompting approach to uncover semantic aspect-aware interactions, which provide clearer insights into user behaviors at a fine-grained semantic level. To incorporate the abundant interactions of various aspects, we propose the simple yet effective Semantic Aspect-based Graph Convolution Network (short for SAGCN). By performing graph convolutions on multiple semantic aspect graphs, SAGCN efficiently combines embeddings across multiple semantic aspects for final user and item representations. The effectiveness of the SAGCN was evaluated on three publicly available datasets through extensive experiments, which revealed that it outperforms all other competitors. Furthermore, interpretability analysis experiments were conducted to demonstrate the interpretability of incorporating semantic aspects into the model., Comment: 10 pages, 7 figures

Recommendation algorithms forecast user preferences by correlating user and item representations derived from historical interaction patterns. In pursuit of enhanced performance, many methods focus on learning robust and independent representations by disentangling the intricate factors within interaction data across various modalities in an unsupervised manner. However, such an approach obfuscates the discernment of how specific factors (e.g., category or brand) influence the outcomes, making it challenging to regulate their effects. In response to this challenge, we introduce a novel method called Attribute-Driven Disentangled Representation Learning (short for AD-DRL), which explicitly incorporates attributes from different modalities into the disentangled representation learning process. By assigning a specific attribute to each factor in multimodal features, AD-DRL can disentangle the factors at both attribute and attribute-value levels. To obtain robust and independent representations for each factor associated with a specific attribute, we first disentangle the representations of features both within and across different modalities. Moreover, we further enhance the robustness of the representations by fusing the multimodal features of the same factor. Empirical evaluations conducted on three public real-world datasets substantiate the effectiveness of AD-DRL, as well as its interpretability and controllability., Comment: ACM Multimedia 2024 Accepted

Existing sign language translation methods follow a two-stage pipeline: first converting the sign language video to a gloss sequence (i.e. Sign2Gloss) and then translating the generated gloss sequence into a spoken language sentence (i.e. Gloss2Text). While previous studies have focused on boosting the performance of the Sign2Gloss stage, we emphasize the optimization of the Gloss2Text stage. However, this task is non-trivial due to two distinct features of Gloss2Text: (1) isolated gloss input and (2) low-capacity gloss vocabulary. To address these issues, we propose a vision and context knowledge enhanced Gloss2Text model, named VK-G2T, which leverages the visual content of the sign language video to learn the properties of the target sentence and exploit the context knowledge to facilitate the adaptive translation of gloss words. Extensive experiments conducted on a Chinese benchmark validate the superiority of our model., Comment: Accepted by ICASSP 2024

Recently, temporal action localization (TAL) has garnered significant interest in information retrieval community. However, existing supervised/weakly supervised methods are heavily dependent on extensive labeled temporal boundaries and action categories, which is labor-intensive and time-consuming. Although some unsupervised methods have utilized the ``iteratively clustering and localization'' paradigm for TAL, they still suffer from two pivotal impediments: 1) unsatisfactory video clustering confidence, and 2) unreliable video pseudolabels for model training. To address these limitations, we present a novel self-paced incremental learning model to enhance clustering and localization training simultaneously, thereby facilitating more effective unsupervised TAL. Concretely, we improve the clustering confidence through exploring the contextual feature-robust visual information. Thereafter, we design two (constant- and variable- speed) incremental instance learning strategies for easy-to-hard model training, thus ensuring the reliability of these video pseudolabels and further improving overall localization performance. Extensive experiments on two public datasets have substantiated the superiority of our model over several state-of-the-art competitors.

We present a new approach, termed GPS-Gaussian, for synthesizing novel views of a character in a real-time manner. The proposed method enables 2K-resolution rendering under a sparse-view camera setting. Unlike the original Gaussian Splatting or neural implicit rendering methods that necessitate per-subject optimizations, we introduce Gaussian parameter maps defined on the source views and regress directly Gaussian Splatting properties for instant novel view synthesis without any fine-tuning or optimization. To this end, we train our Gaussian parameter regression module on a large amount of human scan data, jointly with a depth estimation module to lift 2D parameter maps to 3D space. The proposed framework is fully differentiable and experiments on several datasets demonstrate that our method outperforms state-of-the-art methods while achieving an exceeding rendering speed., Comment: Accepted by CVPR 2024 (Highlight). Project page: https://shunyuanzheng.github.io/GPS-Gaussian

We present GaussianAvatar, an efficient approach to creating realistic human avatars with dynamic 3D appearances from a single video. We start by introducing animatable 3D Gaussians to explicitly represent humans in various poses and clothing styles. Such an explicit and animatable representation can fuse 3D appearances more efficiently and consistently from 2D observations. Our representation is further augmented with dynamic properties to support pose-dependent appearance modeling, where a dynamic appearance network along with an optimizable feature tensor is designed to learn the motion-to-appearance mapping. Moreover, by leveraging the differentiable motion condition, our method enables a joint optimization of motions and appearances during avatar modeling, which helps to tackle the long-standing issue of inaccurate motion estimation in monocular settings. The efficacy of GaussianAvatar is validated on both the public dataset and our collected dataset, demonstrating its superior performances in terms of appearance quality and rendering efficiency., Comment: Project Page: https://huliangxiao.github.io/GaussianAvatar

Recent advancements in video-language understanding have been established on the foundation of image-text models, resulting in promising outcomes due to the shared knowledge between images and videos. However, video-language understanding presents unique challenges due to the inclusion of highly complex semantic details, which result in information redundancy, temporal dependency, and scene complexity. Current techniques have only partially tackled these issues, and our quantitative analysis indicates that some of these methods are complementary. In light of this, we propose a novel framework called RTQ (Refine, Temporal model, and Query), which addresses these challenges simultaneously. The approach involves refining redundant information within frames, modeling temporal relations among frames, and querying task-specific information from the videos. Remarkably, our model demonstrates outstanding performance even in the absence of video-language pre-training, and the results are comparable with or superior to those achieved by state-of-the-art pre-training methods. Code is available at https://github.com/SCZwangxiao/RTQ-MM2023., Comment: Accepted by ACM MM 2023 as Oral representation

Multimodal Large Language Models (MLLMs) have endowed LLMs with the ability to perceive and understand multi-modal signals. However, most of the existing MLLMs mainly adopt vision encoders pretrained on coarsely aligned image-text pairs, leading to insufficient extraction and reasoning of visual knowledge. To address this issue, we devise a dual-Level vIsual knOwledge eNhanced Multimodal Large Language Model (LION), which empowers the MLLM by injecting visual knowledge in two levels. 1) Progressive incorporation of fine-grained spatial-aware visual knowledge. We design a vision aggregator cooperated with region-level vision-language (VL) tasks to incorporate fine-grained spatial-aware visual knowledge into the MLLM. To alleviate the conflict between image-level and region-level VL tasks during incorporation, we devise a dedicated stage-wise instruction-tuning strategy with mixture-of-adapters. This progressive incorporation scheme contributes to the mutual promotion between these two kinds of VL tasks. 2) Soft prompting of high-level semantic visual evidence. We facilitate the MLLM with high-level semantic visual evidence by leveraging diverse image tags. To mitigate the potential influence caused by imperfect predicted tags, we propose a soft prompting method by embedding a learnable token into the tailored text instruction. Comprehensive experiments on several multi-modal benchmarks demonstrate the superiority of our model (e.g., improvement of 5% accuracy on VSR and 3% CIDEr on TextCaps over InstructBLIP, 5% accuracy on RefCOCOg over Kosmos-2)., Comment: Technical Report. Project page: https://rshaojimmy.github.io/Projects/JiuTian-LION Code: https://github.com/rshaojimmy/JiuTian

Text-to-video retrieval (TVR) aims to find the most relevant video in a large video gallery given a query text. The intricate and abundant context of the video challenges the performance and efficiency of TVR. To handle the serialized video contexts, existing methods typically select a subset of frames within a video to represent the video content for TVR. How to select the most representative frames is a crucial issue, whereby the selected frames are required to not only retain the semantic information of the video but also promote retrieval efficiency by excluding temporally redundant frames. In this paper, we make the first empirical study of frame selection for TVR. We systemically classify existing frame selection methods into text-free and text-guided ones, under which we detailedly analyze six different frame selections in terms of effectiveness and efficiency. Among them, two frame selections are first developed in this paper. According to the comprehensive analysis on multiple TVR benchmarks, we empirically conclude that the TVR with proper frame selections can significantly improve the retrieval efficiency without sacrificing the retrieval performance., Comment: Accepted by 2023 EMNLP findings

Teaching Visual Question Answering (VQA) models to refrain from answering unanswerable questions is necessary for building a trustworthy AI system. Existing studies, though have explored various aspects of VQA but somewhat ignored this particular attribute. This paper aims to bridge the research gap by contributing a comprehensive dataset, called UNK-VQA. The dataset is specifically designed to address the challenge of questions that models do not know. To this end, we first augment the existing data via deliberate perturbations on either the image or question. In specific, we carefully ensure that the question-image semantics remain close to the original unperturbed distribution. By this means, the identification of unanswerable questions becomes challenging, setting our dataset apart from others that involve mere image replacement. We then extensively evaluate the zero- and few-shot performance of several emerging multi-modal large models and discover their significant limitations when applied to our dataset. Additionally, we also propose a straightforward method to tackle these unanswerable questions. This dataset, we believe, will serve as a valuable benchmark for enhancing the abstention capability of VQA models, thereby leading to increased trustworthiness of AI systems. We have made the dataset (https://github.com/guoyang9/UNK-VQA) available to facilitate further exploration in this area., Comment: Accepted by TPAMI

In contrast to conventional visual question answering, video-grounded dialog necessitates a profound understanding of both dialog history and video content for accurate response generation. Despite commendable progress made by existing approaches, they still face the challenges of incrementally understanding complex dialog history and assimilating video information. In response to these challenges, we present an iterative search and reasoning framework, which consists of a textual encoder, a visual encoder, and a generator. Specifically, we devise a path search and aggregation strategy in the textual encoder, mining core cues from dialog history that are pivotal to understanding the posed questions. Concurrently, our visual encoder harnesses an iterative reasoning network to extract and emphasize critical visual markers from videos, enhancing the depth of visual comprehension. Finally, we utilize the pre-trained GPT-2 model as our answer generator to decode the mined hidden clues into coherent and contextualized answers. Extensive experiments on three public datasets demonstrate the effectiveness and generalizability of our proposed framework.

Learning a versatile language-image model is computationally prohibitive under a limited computing budget. This paper delves into the \emph{efficient language-image pre-training}, an area that has received relatively little attention despite its importance in reducing computational cost and footprint. To that end, we propose a vision token pruning and merging method ELIP, to remove less influential tokens based on the supervision of language outputs. Our method is designed with several strengths, such as being computation-efficient, memory-efficient, and trainable-parameter-free, and is distinguished from previous vision-only token pruning approaches by its alignment with task objectives. We implement this method in a progressively pruning manner using several sequential blocks. To evaluate its generalization performance, we apply ELIP to three commonly used language-image pre-training models and utilize public image-caption pairs with 4M images for pre-training. Our experiments demonstrate that with the removal of ~30$\%$ vision tokens across 12 ViT layers, ELIP maintains significantly comparable performance with baselines ($\sim$0.32 accuracy drop on average) over various downstream tasks including cross-modal retrieval, VQA, image captioning, \emph{etc}. In addition, the spared GPU resources by our ELIP allow us to scale up with larger batch sizes, thereby accelerating model pre-training and even sometimes enhancing downstream model performance.

Misinformation has become a pressing issue. Fake media, in both visual and textual forms, is widespread on the web. While various deepfake detection and text fake news detection methods have been proposed, they are only designed for single-modality forgery based on binary classification, let alone analyzing and reasoning subtle forgery traces across different modalities. In this paper, we highlight a new research problem for multi-modal fake media, namely Detecting and Grounding Multi-Modal Media Manipulation (DGM^4). DGM^4 aims to not only detect the authenticity of multi-modal media, but also ground the manipulated content, which requires deeper reasoning of multi-modal media manipulation. To support a large-scale investigation, we construct the first DGM^4 dataset, where image-text pairs are manipulated by various approaches, with rich annotation of diverse manipulations. Moreover, we propose a novel HierArchical Multi-modal Manipulation rEasoning tRansformer (HAMMER) to fully capture the fine-grained interaction between different modalities. HAMMER performs 1) manipulation-aware contrastive learning between two uni-modal encoders as shallow manipulation reasoning, and 2) modality-aware cross-attention by multi-modal aggregator as deep manipulation reasoning. Dedicated manipulation detection and grounding heads are integrated from shallow to deep levels based on the interacted multi-modal information. To exploit more fine-grained contrastive learning for cross-modal semantic alignment, we further integrate Manipulation-Aware Contrastive Loss with Local View and construct a more advanced model HAMMER++. Finally, we build an extensive benchmark and set up rigorous evaluation metrics for this new research problem. Comprehensive experiments demonstrate the superiority of HAMMER and HAMMER++., Comment: Extension of our CVPR 2023 paper: arXiv:2304.02556 Code: https://github.com/rshaojimmy/MultiModal-DeepFake

Composed image retrieval (CIR) is a new and flexible image retrieval paradigm, which can retrieve the target image for a multimodal query, including a reference image and its corresponding modification text. Although existing efforts have achieved compelling success, they overlook the conflict relationship modeling between the reference image and the modification text for improving the multimodal query composition and the adaptive matching degree modeling for promoting the ranking of the candidate images that could present different levels of matching degrees with the given query. To address these two limitations, in this work, we propose a Target-Guided Composed Image Retrieval network (TG-CIR). In particular, TG-CIR first extracts the unified global and local attribute features for the reference/target image and the modification text with the contrastive language-image pre-training model (CLIP) as the backbone, where an orthogonal regularization is introduced to promote the independence among the attribute features. Then TG-CIR designs a target-query relationship-guided multimodal query composition module, comprising a target-free student composition branch and a target-based teacher composition branch, where the target-query relationship is injected into the teacher branch for guiding the conflict relationship modeling of the student branch. Last, apart from the conventional batch-based classification loss, TG-CIR additionally introduces a batch-based target similarity-guided matching degree regularization to promote the metric learning process. Extensive experiments on three benchmark datasets demonstrate the superiority of our proposed method.

The integration of emotional support into various conversational scenarios presents profound societal benefits, such as social interactions, mental health counseling, and customer service. However, there are unsolved challenges that hinder real-world applications in this field, including limited data availability and the absence of well-accepted model training paradigms. This work endeavors to navigate these challenges by harnessing the capabilities of Large Language Models (LLMs). We introduce an innovative methodology that synthesizes human insights with the computational prowess of LLMs to curate an extensive emotional support dialogue dataset. Our approach is initiated with a meticulously designed set of dialogues spanning diverse scenarios as generative seeds. By utilizing the in-context learning potential of ChatGPT, we recursively generate an ExTensible Emotional Support dialogue dataset, named ExTES. Following this, we deploy advanced tuning techniques on the LLaMA model, examining the impact of diverse training strategies, ultimately yielding an LLM meticulously optimized for emotional support interactions. An exhaustive assessment of the resultant model showcases its proficiency in offering emotional support, marking a pivotal step in the realm of emotional support bots and paving the way for subsequent research and implementations.