Search

This note presents a novel Bayesian attitude estimator with the matrix Fisher distribution on the special orthogonal group, which can smoothly accommodate both unit and non-unit vector measurements. The posterior attitude distribution is proven to be a matrix Fisher distribution with the assumption that non-unit vector measurement errors follow the isotropic Gaussian distributions and unit vector measurements follow the von-Mises Fisher distributions. Next, a global unscented transformation is proposed to approximate the full likelihood distribution with a matrix Fisher distribution for more generic cases of vector measurement errors following the non-isotropic Gaussian distributions. Following these, a Bayesian attitude estimator with the matrix Fisher distribution is constructed. Numerical examples are then presented. The proposed estimator exhibits advantageous performance compared with the previous attitude estimator with matrix Fisher distributions and the classic multiplicative extended Kalman filter in the case of non-unit vector measurements., Comment: 10 pages, 4 figures

We present the Qwen2-VL Series, an advanced upgrade of the previous Qwen-VL models that redefines the conventional predetermined-resolution approach in visual processing. Qwen2-VL introduces the Naive Dynamic Resolution mechanism, which enables the model to dynamically process images of varying resolutions into different numbers of visual tokens. This approach allows the model to generate more efficient and accurate visual representations, closely aligning with human perceptual processes. The model also integrates Multimodal Rotary Position Embedding (M-RoPE), facilitating the effective fusion of positional information across text, images, and videos. We employ a unified paradigm for processing both images and videos, enhancing the model's visual perception capabilities. To explore the potential of large multimodal models, Qwen2-VL investigates the scaling laws for large vision-language models (LVLMs). By scaling both the model size-with versions at 2B, 8B, and 72B parameters-and the amount of training data, the Qwen2-VL Series achieves highly competitive performance. Notably, the Qwen2-VL-72B model achieves results comparable to leading models such as GPT-4o and Claude3.5-Sonnet across various multimodal benchmarks, outperforming other generalist models. Code is available at https://github.com/QwenLM/Qwen2-VL ., Comment: Code is available at https://github.com/QwenLM/Qwen2-VL. arXiv admin note: text overlap with arXiv:2408.15262 by other authors

For a vision-language model (VLM) to understand the physical world, such as cause and effect, a first step is to capture the temporal dynamics of the visual world, for example how the physical states of objects evolve over time (e.g. a whole apple into a sliced apple). Our paper aims to investigate if VLMs pre-trained on web-scale data learn to encode object states, which can be extracted with zero-shot text prompts. We curate an object state recognition dataset ChangeIt-Frames, and evaluate nine open-source VLMs, including models trained with contrastive and generative objectives. We observe that while these state-of-the-art vision-language models can reliably perform object recognition, they consistently fail to accurately distinguish the objects' physical states. Through extensive experiments, we identify three areas for improvements for VLMs to better encode object states, namely the quality of object localization, the architecture to bind concepts to objects, and the objective to learn discriminative visual and language encoders on object states. Data and code are released.

The core objective of this study is to address the perception challenges faced by autonomous driving in adverse environments like basements. Initially, this paper commences with data collection in an underground garage. A simulated underground garage model is established within the CARLA simulation environment, and SemanticKITTI format occupancy ground truth data is collected in this simulated setting. Subsequently, the study integrates a Transformer-based Occupancy Network model to complete the occupancy grid prediction task within this scenario. A comprehensive BEV perception framework is designed to enhance the accuracy of neural network models in dimly lit, challenging autonomous driving environments. Finally, experiments validate the accuracy of the proposed solution's perception performance in basement scenarios. The proposed solution is tested on our self-constructed underground garage dataset, SUSTech-COE-ParkingLot, yielding satisfactory results.

Tailoring XAI methods to individual needs is crucial for intuitive Human-AI interactions. While context and task goals are vital, factors like user personality traits could also influence method selection. Our study investigates using personality traits to predict user preferences among decision trees, texts, and factor graphs. We trained a Machine Learning model on responses to the Big Five personality test to predict preferences. Deploying these predicted preferences in a navigation game (n=6), we found users more receptive to personalized XAI recommendations, enhancing trust in the system. This underscores the significance of customization in XAI interfaces, impacting user engagement and confidence.

Phase engineering strategies in two-dimensional transition metal dichalcogenides (2D-TMDs) have garnered significant attention due to their potential applications in electronics, optoelectronics, and energy storage. Various methods, including direct synthesis, pressure control, and chemical doping, have been employed to manipulate structural transitions in 2D-TMDs. Metal intercalation emerges as an effective technique to modulate phase transition dynamics by inserting external atoms or ions between the layers of 2D-TMDs, altering their electronic structure and physical properties. Here, we investigate the significant structural phase transitions in Pb(Ta1+xSe2)2 single crystals induced by Ta intercalation using a combination of Raman spectroscopy and first-principles calculations. The results highlight the pivotal role of Ta atoms in driving these transitions and elucidate the interplay between intercalation, phase transitions, and resulting electronic and vibrational properties in 2D-TMDs. By focusing on Pb(Ta1+xSe2)2 as an ideal case study and investigating like metal intercalation, this study advances understanding in the field and paves the way for the development of novel applications for 2D-TMDs, offering insights into the potential of these materials for future technological advancements.

Visual grounding tasks aim to localize image regions based on natural language references. In this work, we explore whether generative VLMs predominantly trained on image-text data could be leveraged to scale up the text annotation of visual grounding data. We find that grounding knowledge already exists in generative VLM and can be elicited by proper prompting. We thus prompt a VLM to generate object-level descriptions by feeding it object regions from existing object detection datasets. We further propose attribute modeling to explicitly capture the important object attributes, and spatial relation modeling to capture inter-object relationship, both of which are common linguistic pattern in referring expression. Our constructed dataset (500K images, 1M objects, 16M referring expressions) is one of the largest grounding datasets to date, and the first grounding dataset with purely model-generated queries and human-annotated objects. To verify the quality of this data, we conduct zero-shot transfer experiments to the popular RefCOCO benchmarks for both referring expression comprehension (REC) and segmentation (RES) tasks. On both tasks, our model significantly outperform the state-of-the-art approaches without using human annotated visual grounding data. Our results demonstrate the promise of generative VLM to scale up visual grounding in the real world. Code and models will be released.

This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models. We release a comprehensive suite of foundational and instruction-tuned language models, encompassing a parameter range from 0.5 to 72 billion, featuring dense models and a Mixture-of-Experts model. Qwen2 surpasses most prior open-weight models, including its predecessor Qwen1.5, and exhibits competitive performance relative to proprietary models across diverse benchmarks on language understanding, generation, multilingual proficiency, coding, mathematics, and reasoning. The flagship model, Qwen2-72B, showcases remarkable performance: 84.2 on MMLU, 37.9 on GPQA, 64.6 on HumanEval, 89.5 on GSM8K, and 82.4 on BBH as a base language model. The instruction-tuned variant, Qwen2-72B-Instruct, attains 9.1 on MT-Bench, 48.1 on Arena-Hard, and 35.7 on LiveCodeBench. Moreover, Qwen2 demonstrates robust multilingual capabilities, proficient in approximately 30 languages, spanning English, Chinese, Spanish, French, German, Arabic, Russian, Korean, Japanese, Thai, Vietnamese, and more, underscoring its versatility and global reach. To foster community innovation and accessibility, we have made the Qwen2 model weights openly available on Hugging Face and ModelScope, and the supplementary materials including example code on GitHub. These platforms also include resources for quantization, fine-tuning, and deployment, facilitating a wide range of applications and research endeavors., Comment: 26 pages, 1 figure

Mixing (or prior) density estimation is an important problem in machine learning and statistics, especially in empirical Bayes $g$-modeling where accurately estimating the prior is necessary for making good posterior inferences. In this paper, we propose neural-$g$, a new neural network-based estimator for $g$-modeling. Neural-$g$ uses a softmax output layer to ensure that the estimated prior is a valid probability density. Under default hyperparameters, we show that neural-$g$ is very flexible and capable of capturing many unknown densities, including those with flat regions, heavy tails, and/or discontinuities. In contrast, existing methods struggle to capture all of these prior shapes. We provide justification for neural-$g$ by establishing a new universal approximation theorem regarding the capability of neural networks to learn arbitrary probability mass functions. To accelerate convergence of our numerical implementation, we utilize a weighted average gradient descent approach to update the network parameters. Finally, we extend neural-$g$ to multivariate prior density estimation. We illustrate the efficacy of our approach through simulations and analyses of real datasets. A software package to implement neural-$g$ is publicly available at https://github.com/shijiew97/neuralG., Comment: 40 pages, 8 figures, 5 tables

As one of the most advanced techniques in AI, Retrieval-Augmented Generation (RAG) can offer reliable and up-to-date external knowledge, providing huge convenience for numerous tasks. Particularly in the era of AI-Generated Content (AIGC), the powerful capacity of retrieval in providing additional knowledge enables RAG to assist existing generative AI in producing high-quality outputs. Recently, Large Language Models (LLMs) have demonstrated revolutionary abilities in language understanding and generation, while still facing inherent limitations, such as hallucinations and out-of-date internal knowledge. Given the powerful abilities of RAG in providing the latest and helpful auxiliary information, Retrieval-Augmented Large Language Models (RA-LLMs) have emerged to harness external and authoritative knowledge bases, rather than solely relying on the model's internal knowledge, to augment the generation quality of LLMs. In this survey, we comprehensively review existing research studies in RA-LLMs, covering three primary technical perspectives: architectures, training strategies, and applications. As the preliminary knowledge, we briefly introduce the foundations and recent advances of LLMs. Then, to illustrate the practical significance of RAG for LLMs, we systematically review mainstream relevant work by their architectures, training strategies, and application areas, detailing specifically the challenges of each and the corresponding capabilities of RA-LLMs. Finally, to deliver deeper insights, we discuss current limitations and several promising directions for future research. Updated information about this survey can be found at https://advanced-recommender-systems.github.io/RAG-Meets-LLMs/, Comment: This is the long version of the corresponding survey paper accepted by KDD2024

Graphs play an important role in representing complex relationships in various domains like social networks, knowledge graphs, and molecular discovery. With the advent of deep learning, Graph Neural Networks (GNNs) have emerged as a cornerstone in Graph Machine Learning (Graph ML), facilitating the representation and processing of graph structures. Recently, LLMs have demonstrated unprecedented capabilities in language tasks and are widely adopted in a variety of applications such as computer vision and recommender systems. This remarkable success has also attracted interest in applying LLMs to the graph domain. Increasing efforts have been made to explore the potential of LLMs in advancing Graph ML's generalization, transferability, and few-shot learning ability. Meanwhile, graphs, especially knowledge graphs, are rich in reliable factual knowledge, which can be utilized to enhance the reasoning capabilities of LLMs and potentially alleviate their limitations such as hallucinations and the lack of explainability. Given the rapid progress of this research direction, a systematic review summarizing the latest advancements for Graph ML in the era of LLMs is necessary to provide an in-depth understanding to researchers and practitioners. Therefore, in this survey, we first review the recent developments in Graph ML. We then explore how LLMs can be utilized to enhance the quality of graph features, alleviate the reliance on labeled data, and address challenges such as graph heterogeneity and out-of-distribution (OOD) generalization. Afterward, we delve into how graphs can enhance LLMs, highlighting their abilities to enhance LLM pre-training and inference. Furthermore, we investigate various applications and discuss the potential future directions in this promising field.

Human-like Agents with diverse and dynamic personalities could serve as an essential design probe in the process of user-centered design, thereby enabling designers to enhance the user experience of interactive applications. In this article, we introduce Evolving Agents, a novel agent architecture that consists of two systems: Personality and Behavior. The Personality system includes Cognition, Emotion, and Character Growth modules. The Behavior system comprises two modules: Planning and Action. We also build a simulation platform that enables agents to interact with the environment and other agents. Evolving Agents can simulate the human personality evolution process. Compared to its initial state, agents' personality and behavior patterns undergo believable development after several days of simulation. Agents reflect on their behavior to reason and develop new personality traits. These traits, in turn, generate new behavior patterns, forming a feedback loop-like personality evolution. Our experiment utilized a simulation platform with ten agents for evaluation. During the assessment, these agents experienced believable and inspirational personality evolution. Through ablation and control experiments, we demonstrated the effectiveness of agent personality evolution, and all of our agent architecture modules contribute to creating believable human-like agents with diverse and dynamic personalities. We also demonstrated through workshops how Evolving Agents could inspire designers.

Graph Neural Networks (GNNs) have achieved remarkable success in various real-world applications. However, GNNs may be trained on undesirable graph data, which can degrade their performance and reliability. To enable trained GNNs to efficiently unlearn unwanted data, a desirable solution is retraining-based graph unlearning, which partitions the training graph into subgraphs and trains sub-models on them, allowing fast unlearning through partial retraining. However, the graph partition process causes information loss in the training graph, resulting in the low model utility of sub-GNN models. In this paper, we propose GraphRevoker, a novel graph unlearning framework that better maintains the model utility of unlearnable GNNs. Specifically, we preserve the graph property with graph property-aware sharding and effectively aggregate the sub-GNN models for prediction with graph contrastive sub-model aggregation. We conduct extensive experiments to demonstrate the superiority of our proposed approach., Comment: 8 pages, 3 figures, accepted by The Web Conference 2024 (PhD Symposium Track)

Multi-view depth estimation has achieved impressive performance over various benchmarks. However, almost all current multi-view systems rely on given ideal camera poses, which are unavailable in many real-world scenarios, such as autonomous driving. In this work, we propose a new robustness benchmark to evaluate the depth estimation system under various noisy pose settings. Surprisingly, we find current multi-view depth estimation methods or single-view and multi-view fusion methods will fail when given noisy pose settings. To address this challenge, we propose a single-view and multi-view fused depth estimation system, which adaptively integrates high-confident multi-view and single-view results for both robust and accurate depth estimations. The adaptive fusion module performs fusion by dynamically selecting high-confidence regions between two branches based on a wrapping confidence map. Thus, the system tends to choose the more reliable branch when facing textureless scenes, inaccurate calibration, dynamic objects, and other degradation or challenging conditions. Our method outperforms state-of-the-art multi-view and fusion methods under robustness testing. Furthermore, we achieve state-of-the-art performance on challenging benchmarks (KITTI and DDAD) when given accurate pose estimations. Project website: https://github.com/Junda24/AFNet/., Comment: Accepted to CVPR 2024

Estimating the mixing density of a latent mixture model is an important task in signal processing. Nonparametric maximum likelihood estimation is one popular approach to this problem. If the latent variable distribution is assumed to be continuous, then bootstrapping can be used to approximate it. However, traditional bootstrapping requires repeated evaluations on resampled data and is not scalable. In this letter, we construct a generative process to rapidly produce nonparametric maximum likelihood bootstrap estimates. Our method requires only a single evaluation of a novel two-stage optimization algorithm. Simulations and real data analyses demonstrate that our procedure accurately estimates the mixing density with little computational cost even when there are a hundred thousand observations., Comment: 6 pages (main article is 4 pages, one page of references, and one page Appendix). 5 figures and 4 tables. This paper supersedes a previously circulated technical report by S. Wang and M. Shin (arXiv:2006.00767v2.pdf)

In this paper, we investigate the problem of verifying the finite-time safety of continuous-time perturbed deterministic systems represented by ordinary differential equations in the presence of measurable disturbances. Given a finite time horizon, if the system is safe, it, starting from a compact initial set, will remain within an open and bounded safe region throughout the specified time horizon, regardless of the disturbances. The main contribution of this work is to uncover that there exists a time-dependent barrier certificate if and only if the system is safe. This barrier certificate satisfies the following conditions: negativity over the initial set at the initial time instant, non-negativity over the boundary of the safe set, and non-increasing behavior along the system dynamics over the specified finite time horizon. The existence problem is explored using a Hamilton-Jacobi differential equation, which has a unique Lipschitz viscosity solution.

In this era, the success of large language models and text-to-image models can be attributed to the driving force of large-scale datasets. However, in the realm of 3D vision, while remarkable progress has been made with models trained on large-scale synthetic and real-captured object data like Objaverse and MVImgNet, a similar level of progress has not been observed in the domain of human-centric tasks partially due to the lack of a large-scale human dataset. Existing datasets of high-fidelity 3D human capture continue to be mid-sized due to the significant challenges in acquiring large-scale high-quality 3D human data. To bridge this gap, we present MVHumanNet, a dataset that comprises multi-view human action sequences of 4,500 human identities. The primary focus of our work is on collecting human data that features a large number of diverse identities and everyday clothing using a multi-view human capture system, which facilitates easily scalable data collection. Our dataset contains 9,000 daily outfits, 60,000 motion sequences and 645 million frames with extensive annotations, including human masks, camera parameters, 2D and 3D keypoints, SMPL/SMPLX parameters, and corresponding textual descriptions. To explore the potential of MVHumanNet in various 2D and 3D visual tasks, we conducted pilot studies on view-consistent action recognition, human NeRF reconstruction, text-driven view-unconstrained human image generation, as well as 2D view-unconstrained human image and 3D avatar generation. Extensive experiments demonstrate the performance improvements and effective applications enabled by the scale provided by MVHumanNet. As the current largest-scale 3D human dataset, we hope that the release of MVHumanNet data with annotations will foster further innovations in the domain of 3D human-centric tasks at scale., Comment: Project page: https://x-zhangyang.github.io/MVHumanNet/

What makes good representations for video understanding, such as anticipating future activities, or answering video-conditioned questions? While earlier approaches focus on end-to-end learning directly from video pixels, we propose to revisit text-based representations, such as general-purpose video captions, which are interpretable and can be directly consumed by large language models (LLMs). Intuitively, different video understanding tasks may require representations that are complementary and at different granularity. To this end, we propose versatile action models (Vamos), a learning framework powered by a large language model as the ``reasoner'', and can flexibly leverage visual embedding and free-form text descriptions as its input. To interpret the important text evidence for question answering, we generalize the concept bottleneck model to work with tokens and nonlinear models, which uses hard attention to select a small subset of tokens from the free-form text as inputs to the LLM reasoner. We evaluate Vamos on five complementary benchmarks, Ego4D, NeXT-QA, IntentQA, Spacewalk-18, and EgoSchema, on its capability to model temporal dynamics, encode visual history, and perform reasoning. Surprisingly, we observe that text-based representations consistently achieve competitive performance on all benchmarks, and that visual embeddings provide marginal or no performance improvement, demonstrating the effectiveness of text-based video representation in the LLM era. We also demonstrate that our token bottleneck model is able to select relevant evidence from free-form text, support test-time intervention, and achieves nearly 5 times inference speedup while keeping a competitive question answering performance. Code and models are publicly released at https://brown-palm.github.io/Vamos/, Comment: Accepted to ECCV 2024 (European Conference on Computer Vision). Code and models are released at https://brown-palm.github.io/Vamos/

The rise of online social networks has facilitated the evolution of social recommender systems, which incorporate social relations to enhance users' decision-making process. With the great success of Graph Neural Networks (GNNs) in learning node representations, GNN-based social recommendations have been widely studied to model user-item interactions and user-user social relations simultaneously. Despite their great successes, recent studies have shown that these advanced recommender systems are highly vulnerable to adversarial attacks, in which attackers can inject well-designed fake user profiles to disrupt recommendation performances. While most existing studies mainly focus on argeted attacks to promote target items on vanilla recommender systems, untargeted attacks to degrade the overall prediction performance are less explored on social recommendations under a black-box scenario. To perform untargeted attacks on social recommender systems, attackers can construct malicious social relationships for fake users to enhance the attack performance. However, the coordination of social relations and item profiles is challenging for attacking black-box social recommendations. To address this limitation, we first conduct several preliminary studies to demonstrate the effectiveness of cross-community connections and cold-start items in degrading recommendations performance. Specifically, we propose a novel framework MultiAttack based on multi-agent reinforcement learning to coordinate the generation of cold-start item profiles and cross-community social relations for conducting untargeted attacks on black-box social recommendations. Comprehensive experiments on various real-world datasets demonstrate the effectiveness of our proposed attacking framework under the black-box setting., Comment: Accepted by ACM TOIS

This paper focuses on building object-centric representations for long-term action anticipation in videos. Our key motivation is that objects provide important cues to recognize and predict human-object interactions, especially when the predictions are longer term, as an observed "background" object could be used by the human actor in the future. We observe that existing object-based video recognition frameworks either assume the existence of in-domain supervised object detectors or follow a fully weakly-supervised pipeline to infer object locations from action labels. We propose to build object-centric video representations by leveraging visual-language pretrained models. This is achieved by "object prompts", an approach to extract task-specific object-centric representations from general-purpose pretrained models without finetuning. To recognize and predict human-object interactions, we use a Transformer-based neural architecture which allows the "retrieval" of relevant objects for action anticipation at various time scales. We conduct extensive evaluations on the Ego4D, 50Salads, and EGTEA Gaze+ benchmarks. Both quantitative and qualitative results confirm the effectiveness of our proposed method., Comment: This is an accepted WACV 2024 paper. Our code is available at https://github.com/brown-palm/ObjectPrompt

Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans. In this work, we introduce Qwen, the first installment of our large language model series. Qwen is a comprehensive language model series that encompasses distinct models with varying parameter counts. It includes Qwen, the base pretrained language models, and Qwen-Chat, the chat models finetuned with human alignment techniques. The base language models consistently demonstrate superior performance across a multitude of downstream tasks, and the chat models, particularly those trained using Reinforcement Learning from Human Feedback (RLHF), are highly competitive. The chat models possess advanced tool-use and planning capabilities for creating agent applications, showcasing impressive performance even when compared to bigger models on complex tasks like utilizing a code interpreter. Furthermore, we have developed coding-specialized models, Code-Qwen and Code-Qwen-Chat, as well as mathematics-focused models, Math-Qwen-Chat, which are built upon base language models. These models demonstrate significantly improved performance in comparison with open-source models, and slightly fall behind the proprietary models., Comment: 59 pages, 5 figures

In this work, we introduce the Qwen-VL series, a set of large-scale vision-language models (LVLMs) designed to perceive and understand both texts and images. Starting from the Qwen-LM as a foundation, we endow it with visual capacity by the meticulously designed (i) visual receptor, (ii) input-output interface, (iii) 3-stage training pipeline, and (iv) multilingual multimodal cleaned corpus. Beyond the conventional image description and question-answering, we implement the grounding and text-reading ability of Qwen-VLs by aligning image-caption-box tuples. The resulting models, including Qwen-VL and Qwen-VL-Chat, set new records for generalist models under similar model scales on a broad range of visual-centric benchmarks (e.g., image captioning, question answering, visual grounding) and different settings (e.g., zero-shot, few-shot). Moreover, on real-world dialog benchmarks, our instruction-tuned Qwen-VL-Chat also demonstrates superiority compared to existing vision-language chatbots. Code, demo and models are available at https://github.com/QwenLM/Qwen-VL., Comment: Code, demo and models are available at https://github.com/QwenLM/Qwen-VL

Can we better anticipate an actor's future actions (e.g. mix eggs) by knowing what commonly happens after his/her current action (e.g. crack eggs)? What if we also know the longer-term goal of the actor (e.g. making egg fried rice)? The long-term action anticipation (LTA) task aims to predict an actor's future behavior from video observations in the form of verb and noun sequences, and it is crucial for human-machine interaction. We propose to formulate the LTA task from two perspectives: a bottom-up approach that predicts the next actions autoregressively by modeling temporal dynamics; and a top-down approach that infers the goal of the actor and plans the needed procedure to accomplish the goal. We hypothesize that large language models (LLMs), which have been pretrained on procedure text data (e.g. recipes, how-tos), have the potential to help LTA from both perspectives. It can help provide the prior knowledge on the possible next actions, and infer the goal given the observed part of a procedure, respectively. To leverage the LLMs, we propose a two-stage framework, AntGPT. It first recognizes the actions already performed in the observed videos and then asks an LLM to predict the future actions via conditioned generation, or to infer the goal and plan the whole procedure by chain-of-thought prompting. Empirical results on the Ego4D LTA v1 and v2 benchmarks, EPIC-Kitchens-55, as well as EGTEA GAZE+ demonstrate the effectiveness of our proposed approach. AntGPT achieves state-of-the-art performance on all above benchmarks, and can successfully infer the goal and thus perform goal-conditioned "counterfactual" prediction via qualitative analysis. Code and model will be released at https://brown-palm.github.io/AntGPT, Comment: ICLR 2024 Camera Ready