2 papers
cs.LG2026
Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation
Zhiqi Yu, Zhangquan Chen, Mengting Liu +2
Reinforcement Learning with Verifiable Rewards (RLVR), particularly GRPO, has become the standard for eliciting LLM reasoning. However, its efficiency in exploration and difficulty…
cs.CV2025
Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains
Zitian Tang, Rohan Myer Krishnan, Zhiqiu Yu +1
Learning from (procedural) videos has increasingly served as a pathway for embodied agents to acquire skills from human demonstrations. To do this, video understanding models must…