Search

Efficient communication can enhance the overall performance of collaborative multi-agent reinforcement learning. A common approach is to share observations through full communication, leading to significant communication overhead. Existing work attempts to perceive the global state by conducting teammate model based on local information. However, they ignore that the uncertainty generated by prediction may lead to difficult training. To address this problem, we propose a Demand-aware Customized Multi-Agent Communication (DCMAC) protocol, which use an upper bound training to obtain the ideal policy. By utilizing the demand parsing module, agent can interpret the gain of sending local message on teammate, and generate customized messages via compute the correlation between demands and local observation using cross-attention mechanism. Moreover, our method can adapt to the communication resources of agents and accelerate the training progress by appropriating the ideal policy which is trained with joint observation. Experimental results reveal that DCMAC significantly outperforms the baseline algorithms in both unconstrained and communication constrained scenarios.

There is a great need to accurately predict short-term precipitation, which has socioeconomic effects such as agriculture and disaster prevention. Recently, the forecasting models have employed multi-source data as the multi-modality input, thus improving the prediction accuracy. However, the prevailing methods usually suffer from the desynchronization of multi-source variables, the insufficient capability of capturing spatio-temporal dependency, and unsatisfactory performance in predicting extreme precipitation events. To fix these problems, we propose a short-term precipitation forecasting model based on spatio-temporal alignment attention, with SATA as the temporal alignment module and STAU as the spatio-temporal feature extractor to filter high-pass features from precipitation signals and capture multi-term temporal dependencies. Based on satellite and ERA5 data from the southwestern region of China, our model achieves improvements of 12.61\% in terms of RMSE, in comparison with the state-of-the-art methods.

Existing research often treats long-form videos as extended short videos, leading to several limitations: inadequate capture of long-range dependencies, inefficient processing of redundant information, and failure to extract high-level semantic concepts. To address these issues, we propose a novel approach that more accurately reflects human cognition. This paper introduces HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics, a model that simulates episodic memory accumulation to capture action sequences and reinforces them with semantic knowledge dispersed throughout the video. Our work makes two key contributions: First, we develop an Episodic COmpressor (ECO) that efficiently aggregates crucial representations from micro to semi-macro levels, overcoming the challenge of long-range dependencies. Second, we propose a Semantics ReTRiever (SeTR) that enhances these aggregated representations with semantic information by focusing on the broader context, dramatically reducing feature dimensionality while preserving relevant macro-level information. This addresses the issues of redundancy and lack of high-level concept extraction. Extensive experiments demonstrate that HERMES achieves state-of-the-art performance across multiple long-video understanding benchmarks in both zero-shot and fully-supervised settings., Comment: This is an improved and expanded version of our EVAL-FoMo Workshop at ECCV'24 (v1 of this paper). Project page: https://joslefaure.github.io/assets/html/hermes.html

Spatio-temporal action detection encompasses the tasks of localizing and classifying individual actions within a video. Recent works aim to enhance this process by incorporating interaction modeling, which captures the relationship between people and their surrounding context. However, these approaches have primarily focused on fully-supervised learning, and the current limitation lies in the lack of generalization capability to recognize unseen action categories. In this paper, we aim to adapt the pretrained image-language models to detect unseen actions. To this end, we propose a method which can effectively leverage the rich knowledge of visual-language models to perform Person-Context Interaction. Meanwhile, our Context Prompting module will utilize contextual information to prompt labels, thereby enhancing the generation of more representative text features. Moreover, to address the challenge of recognizing distinct actions by multiple people at the same timestamp, we design the Interest Token Spotting mechanism which employs pretrained visual knowledge to find each person's interest context tokens, and then these tokens will be used for prompting to generate text features tailored to each individual. To evaluate the ability to detect unseen actions, we propose a comprehensive benchmark on J-HMDB, UCF101-24, and AVA datasets. The experiments show that our method achieves superior results compared to previous approaches and can be further extended to multi-action videos, bringing it closer to real-world applications. The code and data can be found in https://webber2933.github.io/ST-CLIP-project-page., Comment: Project page: https://webber2933.github.io/ST-CLIP-project-page

Enabling Large Language Models (LLMs) to comprehend the 3D physical world remains a significant challenge. Due to the lack of large-scale 3D-text pair datasets, the success of LLMs has yet to be replicated in 3D understanding. In this paper, we rethink this issue and propose a new task: 3D Data-Efficient Point-Language Understanding. The goal is to enable LLMs to achieve robust 3D object understanding with minimal 3D point cloud and text data pairs. To address this task, we introduce GreenPLM, which leverages more text data to compensate for the lack of 3D data. First, inspired by using CLIP to align images and text, we utilize a pre-trained point cloud-text encoder to map the 3D point cloud space to the text space. This mapping leaves us to seamlessly connect the text space with LLMs. Once the point-text-LLM connection is established, we further enhance text-LLM alignment by expanding the intermediate text space, thereby reducing the reliance on 3D point cloud data. Specifically, we generate 6M free-text descriptions of 3D objects, and design a three-stage training strategy to help LLMs better explore the intrinsic connections between different modalities. To achieve efficient modality alignment, we design a zero-parameter cross-attention module for token pooling. Extensive experimental results show that GreenPLM requires only 12% of the 3D training data used by existing state-of-the-art models to achieve superior 3D understanding. Remarkably, GreenPLM also achieves competitive performance using text-only data. The code and weights are available at: https://github.com/TangYuan96/GreenPLM.

Large-scale vision-language models, such as CLIP, are known to contain harmful societal bias regarding protected attributes (e.g., gender and age). In this paper, we aim to address the problems of societal bias in CLIP. Although previous studies have proposed to debias societal bias through adversarial learning or test-time projecting, our comprehensive study of these works identifies two critical limitations: 1) loss of attribute information when it is explicitly disclosed in the input and 2) use of the attribute annotations during debiasing process. To mitigate societal bias in CLIP and overcome these limitations simultaneously, we introduce a simple-yet-effective debiasing method called SANER (societal attribute neutralizer) that eliminates attribute information from CLIP text features only of attribute-neutral descriptions. Experimental results show that SANER, which does not require attribute annotations and preserves original information for attribute-specific descriptions, demonstrates superior debiasing ability than the existing methods.

Traditional deep Gaussian processes model the data evolution using a discrete hierarchy, whereas differential Gaussian processes (DIFFGPs) represent the evolution as an infinitely deep Gaussian process. However, prior DIFFGP methods often overlook the uncertainty of kernel hyperparameters and assume them to be fixed and time-invariant, failing to leverage the unique synergy between continuous-time models and approximate inference. In this work, we propose a fully Bayesian approach that treats the kernel hyperparameters as random variables and constructs coupled stochastic differential equations (SDEs) to learn their posterior distribution and that of inducing points. By incorporating estimation uncertainty on hyperparameters, our method enhances the model's flexibility and adaptability to complex dynamics. Additionally, our approach provides a time-varying, comprehensive, and realistic posterior approximation through coupling variables using SDE methods. Experimental results demonstrate the advantages of our method over traditional approaches, showcasing its superior performance in terms of flexibility, accuracy, and other metrics. Our work opens up exciting research avenues for advancing Bayesian inference and offers a powerful modeling tool for continuous-time Gaussian processes.

Relativistic polarized electron beams can find applications in broad areas of fundamental physics. Here, we propose for the first time that electron spin polarization can be realized efficiently via collective beam-target interactions. When a relativistic unpolarized electron beam is incident onto the surface of a solid target with a grazing angle, strong magnetic fields are induced at the target surface due to the formation of a high reflux of target electrons. This results in violent beam self-focusing and corresponding beam density increase via magnetic pinching. The pinched dense beam in turn further enhances the magnetic fields to the level of a few Giga-Gauss, which is high enough to trigger strong synchrotron radiation of ultrarelativistic electrons. During the interaction, electron spin polarization develops along the magnetic field direction, which is achieved via radiative spin flips in the quantum radiation-dominated regime. As a consequence, the incident electron beam can be effectively polarized via the spin-dependent radiation reaction, for example, the mean polarization of electrons with energy less than 2 GeV can reach above 50% for an initial 5GeV beam. This provides a robust way for the development of polarized electron sources.

Bayesian Last Layer (BLL) models focus solely on uncertainty in the output layer of neural networks, demonstrating comparable performance to more complex Bayesian models. However, the use of Gaussian priors for last layer weights in Bayesian Last Layer (BLL) models limits their expressive capacity when faced with non-Gaussian, outlier-rich, or high-dimensional datasets. To address this shortfall, we introduce a novel approach that combines diffusion techniques and implicit priors for variational learning of Bayesian last layer weights. This method leverages implicit distributions for modeling weight priors in BLL, coupled with diffusion samplers for approximating true posterior predictions, thereby establishing a comprehensive Bayesian prior and posterior estimation strategy. By delivering an explicit and computationally efficient variational lower bound, our method aims to augment the expressive abilities of BLL models, enhancing model accuracy, calibration, and out-of-distribution detection proficiency. Through detailed exploration and experimental validation, We showcase the method's potential for improving predictive accuracy and uncertainty quantification while ensuring computational efficiency.

The workshop focused on the application of ANAs to particle physics keeping in mind the ultimate goal of a collider at the energy frontier (10\,TeV, e$^+$/e$^-$, e$^-$/e$^-$, or $\gamma\gamma$). The development of ANAs is conducted at universities and national laboratories worldwide. The community is thematically broad and diverse, in particular since lasers suitable for ANA research (multi-hundred-terawatt peak power, a few tens of femtosecond-long pulses) and acceleration of electrons to hundreds of mega electron volts to multi giga electron volts became commercially available. The community spans several continents (Europe, America, Asia), including more than 62 laboratories in more than 20 countries. It is among the missions of the ICFA-ANA panel to feature the amazing progress made with ANAs, to provide international coordination and to foster international collaborations towards a future HEP collider. The scope of this edition of the workshop was to discuss the recent progress and necessary steps towards realizing a linear collider for particle physics based on novel-accelerator technologies (laser or beam driven in plasma or structures). Updates on the relevant aspects of the European Strategy for Particle Physics (ESPP) Roadmap Process as well as of the P5 (in the US) were presented, and ample time was dedicated to discussions. The major outcome of the workshop is the decision for ALEGRO to coordinate efforts in Europe, in the US, and in Asia towards a pre-CDR for an ANA-based, 10\,TeV CM collider. This goal of this coordination is to lead to a funding proposal to be submitted to both EU and EU/US funding agencies. This document presents a summary of the workshop, as seen by the co-chairs, as well as short 'one-pagers' written by the presenters at the workshop., Comment: 72 pages

This paper introduces the three-branch Dual Attention-Guided Compact Bilinear CNN (DACB-Net) by focusing on learning from disease-specific regions to enhance accuracy and alignment. A global branch compensates for lost discriminative features, generating Attention Heat Maps (AHM) for relevant cropped regions. Finally, the last pooling layers of global and local branches are concatenated for fine-tuning, which offers a comprehensive solution to the challenges posed by skin disease diagnosis. Although current CNNs employ Stochastic Gradient Descent (SGD) for discriminative feature learning, using distinct pairs of local image patches to compute gradients and incorporating a modulation factor in the loss for focusing on complex data during training. However, this approach can lead to dataset imbalance, weight adjustments, and vulnerability to overfitting. The proposed solution combines two supervision branches and a novel loss function to address these issues, enhancing performance and interpretability. The framework integrates data augmentation, transfer learning, and fine-tuning to tackle data imbalance to improve classification performance, and reduce computational costs. Simulations on the HAM10000 and ISIC2019 datasets demonstrate the effectiveness of this approach, showcasing a 2.59% increase in accuracy compared to the state-of-the-art., Comment: 23 pages, 18 figures, 6 tables

Axions have aroused widespread research interest because they can solve the strong CP problem and serve as a possible candidate for dark matter. Currently, people have explored a lot of axion detection experiments, including passively detecting the existing axions in the universe, and actively generating axions in the laboratory. Recently, axion-coupled laser-plasma interactions have been discussed as a novel method to detect axions. Petawatt (PW) lasers are considered as a powerful tool to study not only the vacuum polarization but also the axion coupling, due to their extreme fields. However, particle-in-cell (PIC) simulation is still missed in current studies, which limits the understanding of axion-coupled laser-plasma interactions. In this paper, we proposed the method to include the axion field and the coupling with electromagnetic (EM) fields in PIC codes. The axion wave equation and modified Maxwell's equations are numerically solved, while the EM field modulation from axions is considered as a first-order perturbation. Meanwhile, different axion field boundary conditions are considered to satisfy different simulation scenarios. The processes of conversions between axions and photons, and weak laser pulse propagation with axion effects are checked as benchmarks of the code. Such an extended PIC code may help researchers develop novel axion detection schemes based on laser-plasma interactions and provide a better understanding of axion-coupled astrophysical processes., Comment: 8 pages, 5 figures

Depression recognition based on physiological signals such as functional near-infrared spectroscopy (fNIRS) and electroencephalogram (EEG) has made considerable progress. However, most existing studies ignore the complementarity and semantic consistency of multimodal physiological signals under the same stimulation task in complex spatio-temporal patterns. In this paper, we introduce a multimodal physiological signals representation learning framework using Siamese architecture via multiscale contrasting for depression recognition (MRLMC). First, fNIRS and EEG are transformed into different but correlated data based on a time-domain data augmentation strategy. Then, we design a spatio-temporal contrasting module to learn the representation of fNIRS and EEG through weight-sharing multiscale spatio-temporal convolution. Furthermore, to enhance the learning of semantic representation associated with stimulation tasks, a semantic consistency contrast module is proposed, aiming to maximize the semantic similarity of fNIRS and EEG. Extensive experiments on publicly available and self-collected multimodal physiological signals datasets indicate that MRLMC outperforms the state-of-the-art models. Moreover, our proposed framework is capable of transferring to multimodal time series downstream tasks.

Reconstructing textured meshes from colored point clouds is an important but challenging task in 3D graphics and vision. Most existing methods predict colors as implicit functions in 3D or UV space, suffering from blurry textures or the lack of generalization capability. Addressing this, we propose PointDreamer, a novel framework for textured mesh reconstruction from colored point cloud. It produces meshes with enhanced fidelity and clarity by 2D image inpainting, taking advantage of the mature techniques and massive data of 2D vision. Specifically, we first project the input point cloud into 2D space to generate sparse multi-view images, and then inpaint empty pixels utilizing a pre-trained 2D diffusion model. Next, we design a novel Non-Border-First strategy to unproject the colors of the inpainted dense images back to 3D space, thus obtaining the final textured mesh. In this way, our PointDreamer works in a zero-shot manner, requiring no extra training. Extensive qualitative and quantitative experiments on various synthetic and real-scanned datasets show the SoTA performance of PointDreamer, by significantly outperforming baseline methods with 30\% improvement in LPIPS score (from 0.118 to 0.068). Code at: https://github.com/YuQiao0303/PointDreamer.

Referring Video Object Segmentation (RVOS) aims to segment the object referred to by the query sentence throughout the entire video. Most existing methods require end-to-end training with dense mask annotations, which could be computation-consuming and less scalable. In this work, we aim to efficiently adapt foundation segmentation models for addressing RVOS from weak supervision with the proposed Grounded Prompting (GroPrompt) framework. More specifically, we propose Text-Aware Prompt Contrastive Learning (TAP-CL) to enhance the association between the position prompts and the referring sentences with only box supervisions, including Text-Contrastive Prompt Learning (TextCon) and Modality-Contrastive Prompt Learning (ModalCon) at frame level and video level, respectively. With the proposed TAP-CL, our GroPrompt framework can generate temporal-consistent yet text-aware position prompts describing locations and movements for the referred object from the video. The experimental results in the standard RVOS benchmarks (Ref-YouTube-VOS, Ref-DAVIS17, A2D-Sentences, and JHMDB-Sentences) demonstrate the competitive performance of our proposed GroPrompt framework given only bounding box weak supervisions., Comment: CVPR Workshop (CVinW) 2024. Project page: https://jack24658735.github.io/groprompt/

The Transformer architecture has recently gained considerable attention in the field of graph representation learning, as it naturally overcomes several limitations of Graph Neural Networks (GNNs) with customized attention mechanisms or positional and structural encodings. Despite making some progress, existing works tend to overlook external information of graphs, specifically the correlation between graphs. Intuitively, graphs with similar structures should have similar representations. Therefore, we propose Graph External Attention (GEA) -- a novel attention mechanism that leverages multiple external node/edge key-value units to capture inter-graph correlations implicitly. On this basis, we design an effective architecture called Graph External Attention Enhanced Transformer (GEAET), which integrates local structure and global interaction information for more comprehensive graph representations. Extensive experiments on benchmark datasets demonstrate that GEAET achieves state-of-the-art empirical performance. The source code is available for reproducibility at: https://github.com/icm1018/GEAET., Comment: In Proceedings of ICML 2024

Imitation learning aims to learn a policy from observing expert demonstrations without access to reward signals from environments. Generative adversarial imitation learning (GAIL) formulates imitation learning as adversarial learning, employing a generator policy learning to imitate expert behaviors and discriminator learning to distinguish the expert demonstrations from agent trajectories. Despite its encouraging results, GAIL training is often brittle and unstable. Inspired by the recent dominance of diffusion models in generative modeling, this work proposes Diffusion-Reward Adversarial Imitation Learning (DRAIL), which integrates a diffusion model into GAIL, aiming to yield more precise and smoother rewards for policy learning. Specifically, we propose a diffusion discriminative classifier to construct an enhanced discriminator; then, we design diffusion rewards based on the classifier's output for policy learning. We conduct extensive experiments in navigation, manipulation, and locomotion, verifying DRAIL's effectiveness compared to prior imitation learning methods. Moreover, additional experimental results demonstrate the generalizability and data efficiency of DRAIL. Visualized learned reward functions of GAIL and DRAIL suggest that DRAIL can produce more precise and smoother rewards.

In this study, we address the limitations inherent in most existing vehicle trajectory prediction methodologies that indiscriminately incorporate all agents within a predetermined proximity when accounting for inter-agent interactions. These approaches commonly employ attention-based architecture or graph neural networks for encoding interactions, which introduces three challenges: (i) The indiscriminate selection of all nearby agents substantially escalates the computational demands of the model, particularly in those interaction-rich scenarios. (ii) Moreover, the simplistic feature extraction of current time agents falls short of adequately capturing the nuanced dynamics of interactions. (iii) Compounded by the inherently low interpretability of attention mechanism and graph neural networks, there is a propensity for the model to allocate unreliable correlation coefficients to certain agents, adversely impacting the accuracy of trajectory predictions. To mitigate these issues, we introduce ASPILin, a novel approach that enhances the selection of interacting agents by considering their current and future lanes, extending this consideration across all historical frames. Utilizing the states of the agents, we estimate the nearest future distance between agents and the time needed to reach this distance. Then, combine these with their current distances to derive a physical correlation coefficient to encode interactions. Experiments conducted on popular trajectory prediction datasets demonstrate that our method is efficient and straightforward, outperforming other state-of-the-art methods., Comment: code:https://github.com/kkk00714/ASPILin

Finite-temperature orbital-free density functional theory (FT-OFDFT) holds significant promise for simulating warm dense matter due to its favorable scaling with both system size and temperature. However, the lack of the numerically accurate and transferable noninteracting free energy functionals results in a limit on the application of FT-OFDFT for warm dense matter simulations. Here, a nonlocal free energy functional, named XWMF, was derived by line integrals for FT-OFDFT simulations. Particularly, a designed integral path, wherein the electronic density varies from uniform to inhomogeneous, was employed to accurately describe deviations in response behavior from the uniform electron gas. The XWMF has been benchmarked by a range of warm dense matter systems including the Si, Al, H, He, and H-He mixture. The simulated results demonstrate that FT-OFDFT within XWMF achieves remarkable performance for accuracy and numerical stability. It is worth noting that XWMF exhibits a low computational cost for large-scale ab~initio simulations, offering exciting opportunities for the realistic simulations of warm dense matter systems covering a broad range of temperatures and pressures., Comment: 8 pages, 4 figures

Federated learning (FL) has attracted widespread attention because it supports the joint training of models by multiple participants without moving private dataset. However, there are still many security issues in FL that deserve discussion. In this paper, we consider three major issues: 1) how to ensure that the training process can be publicly audited by any third party; 2) how to avoid the influence of malicious participants on training; 3) how to ensure that private gradients and models are not leaked to third parties. Many solutions have been proposed to address these issues, while solving the above three problems simultaneously is seldom considered. In this paper, we propose a publicly auditable and privacy-preserving federated learning scheme that is resistant to malicious participants uploading gradients with wrong directions and enables anyone to audit and verify the correctness of the training process. In particular, we design a robust aggregation algorithm capable of detecting gradients with wrong directions from malicious participants. Then, we design a random vector generation algorithm and combine it with zero sharing and blockchain technologies to make the joint training process publicly auditable, meaning anyone can verify the correctness of the training. Finally, we conduct a series of experiments, and the experimental results show that the model generated by the protocol is comparable in accuracy to the original FL approach while keeping security advantages., Comment: ICC 2024 - 2024 IEEE International Conference on Communications Conference Program

Large 2D vision-language models (2D-LLMs) have gained significant attention by bridging Large Language Models (LLMs) with images using a simple projector. Inspired by their success, large 3D point cloud-language models (3D-LLMs) also integrate point clouds into LLMs. However, directly aligning point clouds with LLM requires expensive training costs, typically in hundreds of GPU-hours on A100, which hinders the development of 3D-LLMs. In this paper, we introduce MiniGPT-3D, an efficient and powerful 3D-LLM that achieves multiple SOTA results while training for only 27 hours on one RTX 3090. Specifically, we propose to align 3D point clouds with LLMs using 2D priors from 2D-LLMs, which can leverage the similarity between 2D and 3D visual information. We introduce a novel four-stage training strategy for modality alignment in a cascaded way, and a mixture of query experts module to adaptively aggregate features with high efficiency. Moreover, we utilize parameter-efficient fine-tuning methods LoRA and Norm fine-tuning, resulting in only 47.8M learnable parameters, which is up to 260x fewer than existing methods. Extensive experiments show that MiniGPT-3D achieves SOTA on 3D object classification and captioning tasks, with significantly cheaper training costs. Notably, MiniGPT-3D gains an 8.12 increase on GPT-4 evaluation score for the challenging object captioning task compared to ShapeLLM-13B, while the latter costs 160 total GPU-hours on 8 A800. We are the first to explore the efficient 3D-LLM, offering new insights to the community. Code and weights are available at https://github.com/TangYuan96/MiniGPT-3D., Comment: 17 pages, 9 figures

A dual-beam platform for all-optical electron-photon scattering, or Thomson/Compton scattering, with adjustable collision-angle and parameter tuning ability has been developed, which, in principle, can be used for the verification of strong-field quantum electrodynamics effects. Combining this platform with a 200 TW Ti:Sapphire laser system, we demonstrated the generation of inverse Compton scattering X/gamma-rays with tunable energies from tens of keV to MeV. The polarization of X/gamma radiation was manipulated by controlling the polarization of scattering laser. In the near future, by combining this experimental platform with multi-PW laser facilities, it is proposed to experimentally generate X/gamma radiation with orbital angular momentum for the nuclear isomer excitation, and more importantly, to explore the regime transition from nonlinear Thomson scattering to nonlinear Compton scattering, eventually to demonstrate the verification of theories on extremely strong field quantum electrodynamics effects.

Multi-task reinforcement learning (MTRL) demonstrate potential for enhancing the generalization of a robot, enabling it to perform multiple tasks concurrently. However, the performance of MTRL may still be susceptible to conflicts between tasks and negative interference. To facilitate efficient MTRL, we propose Task-Specific Action Correction (TSAC), a general and complementary approach designed for simultaneous learning of multiple tasks. TSAC decomposes policy learning into two separate policies: a shared policy (SP) and an action correction policy (ACP). To alleviate conflicts resulting from excessive focus on specific tasks' details in SP, ACP incorporates goal-oriented sparse rewards, enabling an agent to adopt a long-term perspective and achieve generalization across tasks. Additional rewards transform the original problem into a multi-objective MTRL problem. Furthermore, to convert the multi-objective MTRL into a single-objective formulation, TSAC assigns a virtual expected budget to the sparse rewards and employs Lagrangian method to transform a constrained single-objective optimization into an unconstrained one. Experimental evaluations conducted on Meta-World's MT10 and MT50 benchmarks demonstrate that TSAC outperforms existing state-of-the-art methods, achieving significant improvements in both sample efficiency and effective action execution.

This paper addresses text-supervised semantic segmentation, aiming to learn a model capable of segmenting arbitrary visual concepts within images by using only image-text pairs without dense annotations. Existing methods have demonstrated that contrastive learning on image-text pairs effectively aligns visual segments with the meanings of texts. We notice that there is a discrepancy between text alignment and semantic segmentation: A text often consists of multiple semantic concepts, whereas semantic segmentation strives to create semantically homogeneous segments. To address this issue, we propose a novel framework, Image-Text Co-Decomposition (CoDe), where the paired image and text are jointly decomposed into a set of image regions and a set of word segments, respectively, and contrastive learning is developed to enforce region-word alignment. To work with a vision-language model, we present a prompt learning mechanism that derives an extra representation to highlight an image segment or a word segment of interest, with which more effective features can be extracted from that segment. Comprehensive experimental results demonstrate that our method performs favorably against existing text-supervised semantic segmentation methods on six benchmark datasets., Comment: CVPR 2024

Existing point cloud semantic segmentation networks cannot identify unknown classes and update their knowledge, due to a closed-set and static perspective of the real world, which would induce the intelligent agent to make bad decisions. To address this problem, we propose a Probability-Driven Framework (PDF) for open world semantic segmentation that includes (i) a lightweight U-decoder branch to identify unknown classes by estimating the uncertainties, (ii) a flexible pseudo-labeling scheme to supply geometry features along with probability distribution features of unknown classes by generating pseudo labels, and (iii) an incremental knowledge distillation strategy to incorporate novel classes into the existing knowledge base gradually. Our framework enables the model to behave like human beings, which could recognize unknown objects and incrementally learn them with the corresponding knowledge. Experimental results on the S3DIS and ScanNetv2 datasets demonstrate that the proposed PDF outperforms other methods by a large margin in both important tasks of open world semantic segmentation.

Large-scale heterogeneous multiagent systems feature various realistic factors in the real world, such as agents with diverse abilities and overall system cost. In comparison to homogeneous systems, heterogeneous systems offer significant practical advantages. Nonetheless, they also present challenges for multiagent reinforcement learning, including addressing the non-stationary problem and managing an imbalanced number of agents with different types. We propose a Prioritized Heterogeneous League Reinforcement Learning (PHLRL) method to address large-scale heterogeneous cooperation problems. PHLRL maintains a record of various policies that agents have explored during their training and establishes a heterogeneous league consisting of diverse policies to aid in future policy optimization. Furthermore, we design a prioritized policy gradient approach to compensate for the gap caused by differences in the number of different types of agents. Next, we use Unreal Engine to design a large-scale heterogeneous cooperation benchmark named Large-Scale Multiagent Operation (LSMO), which is a complex two-team competition scenario that requires collaboration from both ground and airborne agents. We use experiments to show that PHLRL outperforms state-of-the-art methods, including QTRAN and QPLEX in LSMO.

Among the widely used parameter-efficient fine-tuning (PEFT) methods, LoRA and its variants have gained considerable popularity because of avoiding additional inference costs. However, there still often exists an accuracy gap between these methods and full fine-tuning (FT). In this work, we first introduce a novel weight decomposition analysis to investigate the inherent differences between FT and LoRA. Aiming to resemble the learning capacity of FT from the findings, we propose Weight-Decomposed Low-Rank Adaptation (DoRA). DoRA decomposes the pre-trained weight into two components, magnitude and direction, for fine-tuning, specifically employing LoRA for directional updates to efficiently minimize the number of trainable parameters. By employing \ours, we enhance both the learning capacity and training stability of LoRA while avoiding any additional inference overhead. \ours~consistently outperforms LoRA on fine-tuning LLaMA, LLaVA, and VL-BART on various downstream tasks, such as commonsense reasoning, visual instruction tuning, and image/video-text understanding. Code is available at https://github.com/NVlabs/DoRA., Comment: ICML2024(Oral)

We present a method to create storytelling visualization with time series data. Many personal decisions nowadays rely on access to dynamic data regularly, as we have seen during the COVID-19 pandemic. It is thus desirable to construct storytelling visualization for dynamic data that is selected by an individual for a specific context. Because of the need to tell data-dependent stories, predefined storyboards based on known data cannot accommodate dynamic data easily nor scale up to many different individuals and contexts. Motivated initially by the need to communicate time series data during the COVID-19 pandemic, we developed a novel computer-assisted method for meta-authoring of stories, which enables the design of storyboards that include feature-action patterns in anticipation of potential features that may appear in dynamically arrived or selected data. In addition to meta-storyboards involving COVID-19 data, we also present storyboards for telling stories about progress in a machine learning workflow. Our approach is complementary to traditional methods for authoring storytelling visualization, and provides an efficient means to construct data-dependent storyboards for different data-streams of similar contexts.

Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models using image data with only image-level supervision. Since precise pixel-level annotations are not accessible, existing methods typically focus on producing pseudo masks for training segmentation models by refining CAM-like heatmaps. However, the produced heatmaps may capture only the discriminative image regions of object categories or the associated co-occurring backgrounds. To address the issues, we propose a Semantic Prompt Learning for WSSS (SemPLeS) framework, which learns to effectively prompt the CLIP latent space to enhance the semantic alignment between the segmented regions and the target object categories. More specifically, we propose Contrastive Prompt Learning and Prompt-guided Semantic Refinement to learn the prompts that adequately describe and suppress the co-occurring backgrounds associated with each target object category. In this way, SemPLeS can perform better semantic alignment between object regions and the associated class labels, resulting in desired pseudo masks for training the segmentation model. The proposed SemPLeS framework achieves SOTA performance on the standard WSSS benchmarks, PASCAL VOC and MS COCO, and shows compatibility with other WSSS methods. The source codes are provided in the supplementary.

The cultural landscape of interactions with dialogue agents is a compelling yet relatively unexplored territory. It's clear that various sociocultural aspects -- from communication styles and beliefs to shared metaphors and knowledge -- profoundly impact these interactions. To delve deeper into this dynamic, we introduce cuDialog, a first-of-its-kind benchmark for dialogue generation with a cultural lens. We also develop baseline models capable of extracting cultural attributes from dialogue exchanges, with the goal of enhancing the predictive accuracy and quality of dialogue agents. To effectively co-learn cultural understanding and multi-turn dialogue predictions, we propose to incorporate cultural dimensions with dialogue encoding features. Our experimental findings highlight that incorporating cultural value surveys boosts alignment with references and cultural markers, demonstrating its considerable influence on personalization and dialogue quality. To facilitate further exploration in this exciting domain, we publish our benchmark publicly accessible at https://github.com/yongcaoplus/cuDialog., Comment: 17pages, 7 figures, EACL 2024 findings

Image similarity has been extensively studied in computer vision. In recent years, machine-learned models have shown their ability to encode more semantics than traditional multivariate metrics. However, in labelling semantic similarity, assigning a numerical score to a pair of images is impractical, making the improvement and comparisons on the task difficult. In this work, we present a more intuitive approach to build and compare image similarity models based on labelled data in the form of A:R vs B:R, i.e., determining if an image A is closer to a reference image R than another image B. We address the challenges of sparse sampling in the image space (R, A, B) and biases in the models trained with context-based data by using an ensemble model. Our testing results show that the ensemble model constructed performs ~5% better than the best individual context-sensitive models. They also performed better than the models that were directly fine-tuned using mixed imagery data as well as existing deep embeddings, e.g., CLIP and DINO. This work demonstrates that context-based labelling and model training can be effective when an appropriate ensemble approach is used to alleviate the limitation due to sparse sampling.