4 papers
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
Yingtie Lei, Zhongwei Wan, Jiankun Zhang +13
Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience can be distilled into reusabl…
Does Semantic Noise Initialization Transfer from Images to Videos? A Paired Diagnostic Study
Yixiao Jing, Chaoyu Zhang, Zixuan Zhong +1
Semantic noise initialization has been reported to improve robustness and controllability in image diffusion models. Whether these gains transfer to text-to-video (T2V) generation…
DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning
Zhongwei Wan, Yun Shen, Zhihao Dou +9
Reinforcement learning with verifiers (RLVR) is a central paradigm for improving large language model (LLM) reasoning, yet existing methods often suffer from limited exploration. P…
MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents
Peizhou Huang, Zixuan Zhong, Zhongwei Wan +12
Deep Research Agents (DRAs) generate citation-rich reports via multi-step search and synthesis, yet existing benchmarks mainly target text-only settings or short-form multimodal QA…