4 papers
Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards
Bizhe Bai, Xinyue Wang, Peng Ye +1
Reinforcement Learning with Verifiable Rewards (RLVR) improves LLM reasoning, yet growing evidence indicates an exploration ceiling: it often reweights existing solution traces rat…
M-GRPO: Stabilizing Self-Supervised Reinforcement Learning for Large Language Models with Momentum-Anchored Policy Optimization
Bizhe Bai, Hongming Wu, Peng Ye +1
Self-supervised reinforcement learning (RL) presents a promising approach for enhancing the reasoning capabilities of Large Language Models (LLMs) without reliance on expensive hum…
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
Xudong Tan, Yaoxin Yang, Peng Ye +5
Vision-Language-Action (VLA) models have emerged as a powerful paradigm for general-purpose robot control through natural language instructions. However, their high inference cost-…
Local Information Matters: Inference Acceleration For Grounded Conversation Generation Models Through Adaptive Local-Aware Token Pruning
Bizhe Bai, Jianjian Cao, Yadan Luo +1
Grounded Conversation Generation (GCG) is an emerging vision-language task that requires models to generate natural language responses seamlessly intertwined with corresponding obj…