7 papers
EmbodiedSkills: World Action Model-augmented Cascaded Skills for Vision-Language-Action Agent
Wei Wang, Wenqiao Zhang, Yutong Lin +14
Vision-language-action (VLA) policies generate executable robot actions, but plausible proposals can have different consequences for the task. We present EmbodiedSkills, a skill-ba…
VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
Mingjian Gao, Wenqiao Zhang, Yuqian Yuan +9
Recent work has begun to equip vision-language-action (VLA) policies with explicit intermediate reasoning. In embodied control, however, textual chain-of-thought is a poor fit: irr…
OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning
Kaihang Pan, Qi Tian, Jianwei Zhang +12
While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, the academic research community lags far behind: most of its model…
Enhancing Post-Training Quantization via Future Activation Awareness
Zheqi Lv, Zhenxuan Fan, Qi Tian +2
Post-training quantization (PTQ) is a widely used method to compress large language models (LLMs) without fine-tuning. It typically sets quantization hyperparameters (e.g., scaling…
CtrlCoT: Dual-Granularity Chain-of-Thought Compression for Controllable Reasoning
Zhenxuan Fan, Jie Cao, Yang Dai +5
Chain-of-thought (CoT) prompting improves LLM reasoning but incurs high latency and memory cost due to verbose traces, motivating CoT compression with preserved correctness. Existi…
Scaling and Transferability of Annealing Strategies in Large Language Model Training
Siqi Wang, Zhengyu Chen, Teng Xiao +5
Learning rate scheduling is crucial for training large language models, yet understanding the optimal annealing strategies across different model configurations remains challenging…
Fast Thinking for Large Language Models
Haoyu Zheng, Zhuonan Wang, Yuqian Yuan +7
Reasoning-oriented Large Language Models (LLMs) often rely on generating explicit tokens step by step, and their effectiveness typically hinges on large-scale supervised fine-tunin…