Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward
Jingpei Wu, Xiao Han, Weixiang Shen +3
Visual question answering increasingly requires multi-step reasoning. Recent post-training with reinforcement learning under verifiable rewards (RLVR) and Group Relative Policy Opt…
cs.CL2024
PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference
Dongjie Yang, XiaoDong Han, Yan Gao +3
Large Language Models (LLMs) have shown remarkable comprehension abilities but face challenges in GPU memory usage during inference, hindering their scalability for real-time appli…