65 citations · 75 across the 13 of their papers we have counts for
7 papers · 1 filter
Right Answer, Wrong Tokens: Tail-Aware Credit Calibration for RLVR
Xiuyi Lou, Zicheng Xu, Yu-Neng Chuang +4
Although reinforcement learning (RL) improves the reasoning capabilities of large language models (LLMs), GRPO-style methods can suffer from a positive-credit contamination failure…
DynamicMem: A Long-Horizon Memory Benchmark in Real-World Settings
Wenya Xie, Shengming Zhou, Zelin Li +9
LLM agents increasingly act as personal assistants that must remember a user's profile over months: who they are (attributes), what they routinely do (habits), and what they prefer…
Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learning
Zicheng Xu, Ruixuan Zhang, Yu-Neng Chuang +7
Large Language Models (LLMs) achieve remarkable reasoning capabilities through reinforcement learning (RL) post-training. However, existing RL post-training commonly relies on unif…
Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models
Feng Luo, Yu-Neng Chuang, Guanchu Wang +4
On-policy distillation (OPD) trains student models under their own induced distribution while leveraging supervision from stronger teachers. We identify a failure mode of OPD: as t…
AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models
Feng Luo, Yu-Neng Chuang, Guanchu Wang +8
Reasoning-capable large language models (LLMs) achieve strong performance on complex tasks but often exhibit overthinking after distillation, generating unnecessarily long chain-of…
Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization
Yu-Neng Chuang, Leisheng Yu, Guanchu Wang +6
Large language models (LLMs) are increasingly deployed and democratized on edge devices. To improve the efficiency of on-device deployment, small language models (SLMs) are often a…
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
Zirui Liu, Jiayi Yuan, Hongye Jin +5
Efficiently serving large language models (LLMs) requires batching of many requests to reduce the cost per request. Yet, with larger batch sizes and longer context lengths, the key…