14 papers
Progress Reward Modeling for Robotic Learning: A Comprehensive Survey
Jianshu Zhang, Keliang Wu, Haoran Lu +8
Robotic learning takes place in dynamic environments with large behavior spaces. A terminal success signal only tells the robot whether the task is completed. It does not explain w…
LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents
Haoyang Fang, Wei Zhu, Boran Han +11
RL post-training strategies are dataset-dependent and reveal a recurring empirical pattern: capacity parameters accumulate monotonically across stages, while regularization paramet…
Attention Sinks and Outliers in Attention Residuals
Haozheng Luo, Haoran Dai, Shaoyang Zhang +10
We propose OASIS, an outlier- and sink-aware technique built on inter-layer null signaling. As AttnResidual architectures introduce an additional depth-wise normalization channel,…
SciSciGPT: Advancing Human-AI Collaboration in the Science of Science
Erzhuo Shao, Yifang Wang, Yifan Qian +3
The increasing availability of large-scale datasets has fueled rapid progress across many scientific fields, creating unprecedented opportunities for research and discovery while p…
Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
Yolo Y. Tang, Jing Bi, Pinxin Liu +24
Video understanding represents the most challenging frontier in computer vision, requiring models to reason about complex spatiotemporal relationships, long-term dependencies, and…
MetaFind: Scene-Aware 3D Asset Retrieval for Coherent Metaverse Scene Generation
Zhenyu Pan, Yucheng Lu, Han Liu
We present MetaFind, a scene-aware tri-modal compositional retrieval framework designed to enhance scene generation in the metaverse by retrieving 3D assets from large-scale reposi…