9 papers
Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models
Shengchao Zhou, Yuxin Chen, Yuying Ge +4
Vision-language models (VLM) excel at general understanding yet remain weak at dynamic spatial reasoning (DSR), i.e., reasoning about the evolvement of object geometry and relation…
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
Wei Huang, Yi Ge, Shuai Yang +11
We propose QeRL, a Quantization-enhanced Reinforcement Learning framework for large language models (LLMs). While RL is essential for LLMs' reasoning capabilities, it is resource-i…
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…
EmbRACE-3K: Embodied Reasoning and Action in Complex Environments
Mingxian Lin, Wei Huang, Yitang Li +6
Recent advanced vision-language models(VLMs) have demonstrated strong performance on passive, offline image and video understanding tasks. However, their effectiveness in embodied…
2D Instance Editing in 3D Space
Yuhuan Xie, Aoxuan Pan, Ming-Xian Lin +3
Generative models have achieved significant progress in advancing 2D image editing, demonstrating exceptional precision and realism. However, they often struggle with consistency a…
Scaling RL to Long Videos
Yukang Chen, Wei Huang, Baifeng Shi +11
We introduce a full-stack framework that scales up reasoning in vision-language models (VLMs) to long videos, leveraging reinforcement learning. We address the unique challenges of…