29 accepted papers
Multi-Agent Systems (MAS) offer a powerful paradigm for solving complex problems through distributed reasoning and collaboration. However, their effectiveness is often hindered by the challenge of optimizing interactions among agents. To address this, we introduce AgentPO, a novel framework that dir…
Current methods for content safety in Large Language Models (LLMs), such as Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), often rely on multi-stage training pipelines and lack fine-grained, post-deployment controllability. To address these limitations, we propos
Temporal context is essential for robotic manipulation because such tasks are inherently non-Markovian, yet mainstream VLA models typically overlook it and struggle with long-horizon, temporally dependent tasks. Cognitive science suggests that humans rely on working memory to buffer short-lived repr…
Contrastive Language-Image Pre-training (CLIP) exhibits strong zero-shot classification ability on image-level tasks, leading to the research to adapt CLIP for open-vocabulary semantic segmentation without training. The key is to improve spatial representation of image-level CLIP, such as replacing…
Recent advances in Large Language Models (LLMs) have highlighted the challenge of handling long-context tasks, where models need to reason over extensive input contexts to aggregate target information. While Chain-of-Thought (CoT) prompting has shown promise for multi-step reasoning, its effectivene
Distinguishing spatial relations is a basic part of human cognition which requires fine-grained perception on cross-instance. Although benchmarks like MME, MMBench and SEED comprehensively have evaluated various capabilities which already include visual spatial reasoning(VSR). There is still a la…
In this paper, we propose a “Generalization Stress Test” to assess Large Language Models’ (LLMs) generalization ability under slight and controlled perturbations, including option length, problem types, and irrelevant noun replacements. We achieve novel and significant findings that, despite high be
With the development of large language models (LLMs), there has been an increasing need for significant advancements in handling long contexts. To enhance long-context capabilities, constructing high-quality training data with **long-range dependencies** is crucial. Existing methods to select long-c…
Product Attribute Value Identification (PAVI) involves identifying attribute values from product profiles, a key task for improving product search, recommendation, and business analytics on e-commerce platforms.However, existing PAVI methods face critical challenges, such as inferring implicit value…
Functional safety is a critical aspect of automotive engineering, encompassing all phases of a vehicle’s lifecycle, including design, development, production, operation, and decommissioning. This domain involves highly knowledge-intensive tasks. This paper introduces Aegis: An Advanced LLM-Based Mul…
The acquisition of targets' complete point cloud model is crucial for tasks such as 3D reconstruction and disordered grasping. Shooting targets from multiple perspectives and registering point clouds from different perspectives can obtain a relatively complete point cloud model. However, small scene
As advances in large language models (LLMs) and multimodal techniques continue to mature, the development of general-purpose multimodal large language models (MLLMs) has surged, offering significant applications in interpreting natural images. However, the field of pathology has largely remained unt…
Multimodal information extraction (MIE) gains significant attention as the popularity of multimedia content increases. However, current MIE methods often resort to using task-specific model structures, which results in limited generalizability across tasks and underutilizes shared knowledge across M…
Conversational Causal Emotion Entailment (C<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>E<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>) is a task that aims at recognizing the causes corr…
In this paper, we model aspects of communication beyond the words that are said. Specifically, we aim to detect interruptions and active listening events, which are important elements in any dialogue. We build a dataset with fine-grained annotations for each category and train multimodal models that…
Sarcasm is important to sentiment analysis on social media. Sarcasm Target Identification (STI) deserves further study to understand sarcasm in depth. However, text lacking context or missing sarcasm target makes target identification very difficult. In this paper, we introduce multimodality to STI…
"Semi-supervised learning (SSL) has achieved new progress recently with the emerging framework of self-training deep networks, where the criteria for selection of unlabeled samples with pseudo labels play a key role in the empirical success. In this work, we propose such a new criterion based on con…
Detecting objects from LiDAR point clouds is of tremendous significance in autonomous driving. In spite of good progress, accurate and reliable 3D detection is yet to be achieved due to the sparsity and irregularity of LiDAR point clouds. Among existing strategies, multi-view methods have shown grea…
Named entity recognition (NER) is a fundamental task for information extraction (IE), and current state-of-the-art methods try to address this issue and achieve high performance on clean text (e.g., newswire genres). However, most of these algorithms do not generalize well when they transit to the n…
Recently multimodal named entity recognition (MNER) has utilized images to improve the accuracy of NER in tweets. However, most of the multimodal methods use attention mechanisms to extract visual clues regardless of whether the text and image are relevant. Practically, the irrelevant text-image pai…
Recent voxel-based 3D object detectors for autonomous vehicles learn point cloud representations either from bird eye view (BEV) or range view (RV, a.k.a. the perspective view). However, each view has its own strengths and weaknesses. In this paper, we present a novel framework to unify and leverage…
Learning robotic grasps from visual observations is a promising yet challenging task. Recent research shows its great potential by preparing and learning from large-scale synthetic datasets. For the popular, 6 degree-of-freedom (6-DOF) grasp setting of parallel-jaw gripper, most of existing methods…
Accurate 3D object detection in LiDAR based point clouds suffers from the challenges of data sparsity and irregularities. Existing methods strive to organize the points regularly, e.g. voxelize, pass them through a designed 2D/3D neural network, and then define object-level anchors that predict offs…
Trajectory prediction is crucial for autonomous vehicles. The planning system not only needs to know the current state of the surrounding objects but also their possible states in the future. As for vehicles, their trajectories are significantly influenced by the lane geometry and how to effectively…
Multimodal named entity recognition (MNER) for tweets has received increasing attention recently. Most of the multimodal methods used attention mechanisms to capture the text-related visual information. However, unrelated or weakly related text-image pairs account for a large proportion in tweets. V…
TV-L <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> is a classical diffusion-reaction model for low-level vision tasks, which can be solved by a duality based iterative algorithm. Considering the recent success of end-to-end learned representat…
urrently, the most successful learning models in computer vision are based on learning successive representations followed by a decision layer. This is usually actualized through feedforward multilayer neural networks, e.g. ConvNets, where each layer forms one of such successive representations. How…
Human actions captured in video sequences are three-dimensional signals characterizing visual appearance and motion dynamics. To learn action patterns, existing methods adopt Convolutional and/or Recurrent Neural Networks (CNNs and RNNs). CNN based methods are effective in learning spatial appearanc…
Human actions in video sequences are three-dimensional (3D) spatio-temporal signals characterizing both the visual appearance and motion dynamics of the involved humans and objects. Inspired by the success of convolutional neural networks (CNN) for image classification, recent attempts have been mad…