activity
20242026
collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2026

QUADS: Stabilizing NVFP4 Reinforcement Learning for MoE via QUantization-error Alignment across Dual Sides

Zhengyang Zhuge, Hao Yu, Xin Wang +4

Rollout generation is a major bottleneck in Reinforcement Learning (RL) for Mixture-of-Experts (MoE) Large Language Models, motivating low-precision rollout acceleration such as FP…

cs.LG2026

Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL

Sophia Xiao Pu, Zhaotian Weng, Chengzhi Liu +4

Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels. Recent systems report strong reasoning…

cs.LG2026

AGPO: Adaptive Group Policy Optimization with Dual Statistical Feedback

Miaobo Hu, Shuhao Hu, Bokun Wang +5

Reinforcement learning improves LLM reasoning, but PPO/GRPO typically use fixed clipping and decoding temperature, which makes training brittle and tuning-heavy. We propose Adaptiv…

cs.LG2026

QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models

Jingxuan Zhang, Yunta Hsieh, Zhongwei Wan +5

Vision-language-action (VLA) models unify perception, language, and control for embodied agents but face significant challenges in practical deployment due to rapidly increasing co…

cs.LG2025

The Impact of Quantization on Large Reasoning Model Reinforcement Learning

Medha Kumar, Zifei Xu, Xin Wang +1

Strong reasoning capabilities can now be achieved by large-scale reinforcement learning (RL) without any supervised fine-tuning. Although post-training quantization (PTQ) and quant…

cs.LG2025

Early Attentive Sparsification Accelerates Neural Speech Transcription

Zifei Xu, Sayeh Sharify, Hesham Mostafa +3

Transformer-based neural speech processing has achieved state-of-the-art performance. Since speech audio signals are known to be highly compressible, here we seek to accelerate neu…