41 accepted papers
Large language models split into two families: reasoning-centric LLMs, which strengthen internal chain-of-thought reasoning but cannot invoke external tools, and agentic LLMs, which learn to interact with environments and leverage tools but often lag in deep reasoning. This divide arises from fundam…
In recent years, the research focus of large language models (LLMs) and agents has shifted increasingly from demonstrating novel capabilities to complex reasoning and tackling challenging tasks. However, existing evaluations focus mainly on math/code contests or general tasks, while existing multi-d…
Post-training of large language models involves a fundamental trade-off between supervised fine-tuning (SFT), which efficiently mimics demonstrations but tends to memorize, and reinforcement learning (RL), which achieves better generaliza- tion at higher computational cost. Dynamic Fine-Tuning (DFT)…
Agentic reinforcement learning (RL) for web search is prohibitively expensive due to long context lengths and costly environment interactions, and this inefficiency is further exacerbated by GRPO-based optimization, which discards learning signals from entire rollout groups with zero reward variance…
Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks when equipped with external tools. However, current frameworks predominantly rely on sequential processing, leading to inefficient execution particularly for tasks requiring extensive tool interaction.…
Self-evolving memory systems are rapidly reshaping the evolutionary paradigm of large language model (LLM)-based agents. Prior work has predominantly relied on manually engineered memory architectures to store trajectories, distill experience, and synthesize reusable tools, enabling agents to evolve…
Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks primarily evaluate short-horizon behaviors such as localized code generation, scaffolded completion, or repository repair, leaving it unclear whether agents can sustain coherent re…
Recent advances in multimodal large language models (MLLMs) have opened new opportunities for embodied intelligence, enabling multimodal understanding, reasoning, and interaction, as well as continuous spatial decision-making. Nevertheless, current MLLM-based embodied systems face two critical limit…
Automatic medical report generation from multimodal longitudinal imaging is crucial for clinical diagnosis but remains challenging due to privacy constraints and evolving disease dynamics. While federated learning (FL) enables decentralized model training without data sharing, its extension to longi
Offline reinforcement learning (RL) holds the promise of training effective policies from static datasets without the need for costly online interactions. However, offline RL faces key limitations, most notably the challenge of generalizing to unseen or infrequently encountered state-action pairs. W…
Explicit 3D representations have already become an essential medium for 3D simulation and understanding. However, the most commonly used point cloud and 3D Gaussian Splatting (3DGS) each suffer from non-photorealistic rendering and significant degradation under sparse inputs. In this paper, we intro
3D Gaussian Splatting (3DGS) has become a crucial rendering technique for many real-time applications. How- ever, the limited hardware resources on today's mobile platforms hinder these applications, as they struggle to achieve real-time performance. In this paper, we propose SEELE, a general framew
Deep Research Agents (DRAs) can autonomously conduct complex investigations and generate comprehensive reports, demonstrating strong real-world potential. However, existing evaluations mostly rely on close-ended benchmarks, while open-ended deep research benchmarks remain scarce and typically neglec…
Instruction tuning stands as a crucial advancement in leveraging large language models (LLMs) for enhanced task performance. However, the annotation of instruction datasets has traditionally been expensive and laborious, often relying on manual annotations or costly proprietary LLMs. Recent works ex…
The semantically interactive radiance field has always been an appealing task for its potential to facilitate user-friendly and automated real-world 3D scene understanding applications. However, it is a challenging task to achieve high quality, efficiency and zero-shot ability at the same time with…
Grounding 3D object affordance is a task that locates objects in 3D space where they can be manipulated, which links perception and action for embodied intelligence. For example, for an intelligent robot, it is necessary to accurately ground the affordance of an object and grasp it according to huma…
Designing reinforcement learning agents to satisfy complex temporal objectives expressed in Linear Temporal Logic (LTL), presents significant challenges, particularly in ensuring sample efficiency and task alignment over infinite horizons. Recent works have shown that by leveraging the corresponding…
Despite being pretrained on multilingual corpora, large language models (LLMs) exhibit suboptimal performance on low-resource languages. Recent approaches have leveraged multilingual encoders alongside LLMs by introducing trainable parameters connecting the two models. However, these methods typical…
Despite its promise, imitation learning often fails in long-horizon environments where perfect replication of demonstrations is unrealistic and small errors can accumulate catastrophically. We introduce Cago (Capability-Aware Goal Sampling), a novel learning-from-demonstrations method that mitigates…
Repository-level code completion has drawn great attention in software engineering, and several benchmarks have been introduced. However, existing repository-level code completion benchmarks usually focus on a limited number of languages (<5), which cannot evaluate the general code intelligence abil…
This paper aims to reconstruct the scene geometry from multi-view images with strong robustness and high quality. Previous learning-based methods incorporate neural networks into the multi-view stereo matching and have shown impressive reconstruction results. However, due to the reliance on matching…
Recently, Agentic AI has become an increasingly popular field of research. However, we argue that current practices on agent research are far from standard, rigorous scientific research, which makes it hard to conduct apples-to-apples comparisons among and against existing methods. As a result, it i
Distributional discrepancy between training and test data can lead models to make inaccurate predictions when encountering out-of-distribution (OOD) samples in real-world applications. Although existing graph OOD detection methods leverage data-centric techniques to extract effective representations…
With the emerging of huge amount of unlabeled data, unsupervised out-of-distribution (OOD) detection is vital for ensuring the reliability of graph neural networks (GNNs) by identifying OOD samples from in-distribution (ID) ones during testing, where encountering novel or unknown data is inevitable.…
High-quality instruction data is crucial for developing large language models (LLMs), yet existing approaches struggle to effectively control instruction complexity. We present Tag-Instruct, a novel framework that enhances instruction complexity through structured semantic compression and controlled…
Tool learning enhances Large Language Models’ (LLMs) dynamic interaction with external tools, improving their ability to solve complex problems. However, current empirical methods, which primarily focus on isolated tools learning, still struggle with accurate multi-tool selection due to issues like…
This letter introduces an innovative vehicle motion planning method that leverages the integration of rule-based insights to significantly improve closed-loop performance within a learning-based framework. We first employ rule-based methods to heuristically search and generate a diverse set of traje
Exploring unknown environments efficiently is a fundamental challenge in unsupervised goal-conditioned reinforcement learning. While selecting exploratory goals at the frontier of previously explored states is an effective strategy, the policy during training may still have limited capability of rea…
In many intelligent transportation systems, predicting the future motion of heterogeneous traffic participants is a fundamental but challenging task due to various factors encompassing the agents’ dynamic states, interactions with neighboring agents and surrounding traffic infrastructures, and their…
Existing self-supervised methods in natural language processing (NLP), especially hierarchical text classification (HTC), mainly focus on self-supervised contrastive learning, extremely relying on human-designed augmentation rules to generate contrastive samples, which can potentially corrupt or dis…
Learning world models offers a promising avenue for goal-conditioned reinforcement learning with sparse rewards. By allowing agents to plan actions or exploratory goals without direct interaction with the environment, world models enhance exploration efficiency. The quality of a world model hinges o…
Vehicle-to-infrastructure cooperative 3D object detection (VIC3D) is a task that leverages both vehicle and roadside sensors to jointly perceive the surrounding environment. However, considering the high speed of vehicles, the real-time requirements, and the limitations of communication bandwidth, r…
We present a novel prompt-based personalized federated learning (pFL) method to address data heterogeneity and privacy concerns in traditional medical visual question answering (VQA) methods. Specifically, we regard medical datasets from different organs as clients and use pFL to train personalized…
"∗ Equal contribution † Corresponding authors This paper addresses the challenge of 3D instance segmentation by simultaneously leveraging 3D geometric and multi-view image information. Many previous works have applied deep learning techniques to 3D point clouds for instance segmentation. However, th…
In computer vision, contrastive learning is the most advanced unsupervised learning framework. Yet most previous methods simply apply fixed composition of data augmentations to improve data efficiency, which ignores the changes in their optimal settings over training. Thus, the pre-determined parame…
Hierarchical text classification (HTC) is a challenging subtask of multi-label classification as the labels form a complex hierarchical structure. Existing dual-encoder methods in HTC achieve weak performance gains with huge memory overheads and their structure encoders heavily rely on domain knowle…
Goal-conditioned reinforcement learning (RL) is a powerful approach for learning general-purpose skills by reaching diverse goals. However, it has limitations when it comes to task-conditioned policies, where goals are specified by temporally extended instructions written in the Linear Temporal Logi…
Generating high-quality synonymous perturbations is a core challenge for textual adversarial tasks. However, candidates generated from the masked language model often contain many words that are antonyms or irrelevant to the original words, which limit the perturbation space and affect the attack’s…
Text classification is a primary task in natural language processing (NLP). Recently, graph neural networks (GNNs) have developed rapidly and been applied to text classification tasks. As a special kind of graph data, the tree has a simpler data structure and can provide rich hierarchical informatio…
Deep reinforcement learning (RL) has led to encouraging successes in many challenging control tasks. However, a deep RL model lacks interpretability due to the difficulty of identifying how the model's control logic relates to its network structure. Programmatic policies structured in more interpret…
Differentiable programs have recently attracted much interest due to their interpretability, compositionality, and their efficiency to leverage differentiable training. However, synthesizing differentiable programs requires optimizing over a combinatorial, rapidly exploded space of program architect…