1 citations · 2 across the 12 of their papers we have counts for
7 papers · 1 filter
SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning
Fangxun Shu, Yongjie Ye, Yue Liao +6
We introduce SAIL-RL, a reinforcement learning (RL) post-training framework that enhances the reasoning capabilities of multimodal large language models (MLLMs) by teaching them wh…
MC#: Mixture Compressor for Mixture-of-Experts Large Models
Wei Huang, Yue Liao, Yukang Chen +6
Mixture-of-Experts (MoE) effectively scales large language models (LLMs) and vision-language models (VLMs) by increasing capacity through sparse activation. However, preloading all…
Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Models
Zhifei Xie, Ziyang Ma, Zihang Liu +7
Reasoning is essential for effective communication and decision-making. While recent advances in LLMs and MLLMs have shown that incorporating explicit reasoning significantly impro…
SAIL-VL2 Technical Report
Weijie Yin, Yongjie Ye, Fangxun Shu +11
We introduce SAIL-VL2, an open-suite vision-language foundation model (LVM) for comprehensive multimodal understanding and reasoning. As the successor to SAIL-VL, SAIL-VL2 achieves…
Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation
Yue Liao, Pengfei Zhou, Siyuan Huang +11
We introduce Genie Envisioner (GE), a unified world foundation platform for robotic manipulation that integrates policy learning, evaluation, and simulation within a single video-g…
Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
Hongyu Li, Songhao Han, Yue Liao +4
Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large langua…
RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation
Songhao Han, Boxiang Qiu, Yue Liao +4
Recent advances in vision-language models (VLMs) have enabled instruction-conditioned robotic systems with improved generalization. However, most existing work focuses on reactive…