4 papers
Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling
Yiran Guo, Zhongjian Qiao, Yingqi Xie +5
Effective exploration is a key challenge in reinforcement learning for large language models: discovering high-quality trajectories within a limited sampling budget from the vast n…
ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models
Wenhao Liu, Hao Shi, Yunhe Li +7
Long chain-of-thought (CoT) trajectories in large language model (LLM) reasoning cause severe inference bottlenecks due to rapid key-value (KV) cache growth. Current decoding-time…
Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation
Changwang Mei, Peisong Wang, Zekun Li +7
Visual Autoregressive (VAR) models deliver high-quality image generation but suffer from significant inference latency at high resolutions. Recent acceleration approaches most rely…
Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent
Yao Shu, Chenxing Wei, Hongbin Lin +2
Online reinforcement learning with verifiable rewards (RLVR) turns checkable outcomes into a scalable training signal, but it keeps rollout generation, verifier scoring, and refere…