activity
20232026
most citedDo NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

2 citations · 11 across the 30 of their papers we have counts for

collaborators
Showing cs.LGShow all

12 papers · 1 filter

cs.LG2026

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

Yan Wang, Qifan Zhang, Jiachen Yu +12

Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report, we propose \textbf{Lookahead…

cs.LG2026

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data

Zhenwen Liang, Yujun Zhou, Sidi Lu +3

Reinforcement Learning (RL) enhances LLM reasoning, yet a paradox emerges as models scale: strong base models saturate standard benchmarks (e.g., MATH), yielding correct but homoge…

cs.LG2026

Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM Reasoning

Kishan Panaganti, Zhenwen Liang, Wenhao Yu +2

Recent progress in Large Language Model (LLM) reasoning is increasingly driven by the refinement of post-training loss functions and alignment strategies. However, standard Reinfor…

cs.LG2026

Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning

Haolin Liu, Dian Yu, Sidi Lu +6

Reinforcement learning (RL) has emerged as a powerful framework for improving the reasoning capabilities of large language models (LLMs). However, most existing RL approaches rely…

cs.LG2025

Stable and Efficient Single-Rollout RL for Multimodal Reasoning

Rui Liu, Dian Yu, Lei Ke +6

Reinforcement Learning with Verifiable Rewards (RLVR) has become a key paradigm to improve the reasoning capabilities of Multimodal Large Language Models (MLLMs). However, prevalen…

cs.LG2025

Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values

Dian Yu, Yulai Zhao, Kishan Panaganti +3

We propose Reinforcement Learning with Explicit Human Values (RLEV), a method that aligns Large Language Model (LLM) optimization directly with quantifiable human value signals. Wh…