9 papers
SAF-OPD: Stable Advantage Fusion for On-Policy Distillation
Yifan Ding, Xincheng Wei, Yoshua Y. Li +7
Reinforcement learning with verifiable rewards (RLVR) broadcasts a single response-level reward to every token, while on-policy distillation (OPD) scores each token against a stron…
Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
Kun Zeng, Yu Huo, Siyu Zhang +6
Skill-augmented agents increasingly rely on large reusable skill libraries, but retrieving relevant skills is not the same as presenting usable context. Existing methods typically…
Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
Zhiqing Cui, Haotong Xie, Jiahao Yuan +11
Large language model (LLM) multi-agent systems typically rely on rigid orchestration, committing either to flat per-query routing or to hand-engineered task decomposition, so decom…
From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning
Beining Wu, Fuyou Mao, Jiong Lin +7
Generative engines (GEs) are reshaping information access by replacing ranked links with citation-grounded answers, yet current Generative Engine Optimization (GEO) methods optimiz…
Sparse but not Simpler: A Multi-Level Interpretability Analysis of Vision Transformers
Siyu Zhang
Sparse neural networks are often hypothesized to be more interpretable than dense models, motivated by findings that weight sparsity can produce compact circuits in language models…
Zero-Forgetting CISS via Dual-Phase Cognitive Cascades
Yuquan Lu, Yifu Guo, Zishan Xu +6
Continual semantic segmentation (CSS) is a cornerstone task in computer vision that enables a large number of downstream applications, but faces the catastrophic forgetting challen…
Shape of Thought: Progressive Object Assembly via Visual Chain-of-Thought
Yu Huo, Siyu Zhang, Kun Zeng +7
Multimodal models for text-to-image generation have achieved strong visual fidelity, yet they remain brittle under compositional structural constraints, notably generative numeracy…
RepoShapley: Shapley-Enhanced Context Filtering for Repository-Level Code Completion
Yu Huo, Kun Zeng, Siyu Zhang +4
Repository-level code completion benefits from retrieval-augmented generation (RAG). However, controlling cross-file evidence is difficult because chunk utility is often interactio…
Decoupling Continual Semantic Segmentation
Yifu Guo, Yuquan Lu, Wentao Zhang +5
Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgettin…