19 papers
TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control
Yuteng Sun, Haoran Wang, Ruofei Bai +4
Large-scale Vision-Language-Action (VLA) models offer semantic generalization but suffer from high inference latency, limiting them to low-frequency batch-and-execute paradigm. Thi…
DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation
Zhenghao Li, Zhi Zheng, Wei Chen +4
Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving.…
SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs
Hao Wang, Jialun Zhong, Changcheng Wang +5
Knowledge-based conversational question answering (KBCQA) confronts persistent challenges in resolving coreference, modeling contextual dependencies, and executing complex logical…
Near-Optimal Sample Complexities of Divergence-based S-rectangular Distributionally Robust Reinforcement Learning
Zhenghao Li, Shengbo Wang, Nian Si
Distributionally robust reinforcement learning (DR-RL) has recently gained significant attention as a principled approach that addresses discrepancies between training and testing…
Key-Value Pair-Free Continual Learner via Task-Specific Prompt-Prototype
Haihua Luo, Xuming Ran, Zhengji Li +6
Continual learning aims to enable models to acquire new knowledge while retaining previously learned information. Prompt-based methods have shown remarkable performance in this dom…
Intermittent Semi-Working Mask: A New Masking Paradigm for LLMs
HaoYuan Hu, Mingcong Lu, Di Luo +10
Multi-turn dialogues and context-intensive tasks challenge Large Language Models (LLMs) to integrate long histories without sacrificing generation quality. Although prefix LLMs can…