7 papers
Rethinking Groups in Critic-Free RLVR
Yihong Wu, Liheng Ma, Lingfeng Xiao +4
Reinforcement learning (RL) has become a central paradigm for post-training large language models. Existing critic-free RL methods typically generate a group of rollouts for the sa…
Agents' Last Exam
Yiyou Sun, Xinyang Han, Weichen Zhang +306
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional d…
YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition
PSBC LLM Team, Huawei LLM Team, Ruihan Long +56
Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates inf…
Enhancing Table Reasoning with Deterministic Table-State Rewards
Tung Sum Thomas Kwok, Xinyu Wang, Hengzhi He +9
Large Language Models (LLMs) struggle with multi-step reasoning over structured tables. The primary reason is the lack of explicit supervision for intermediate reasoning states. Ex…
It Takes Two: Your GRPO Is Secretly DPO
Yihong Wu, Liheng Ma, Lei Ding +9
GRPO has emerged as a prominent reinforcement learning algorithm for post-training LLMs. Unlike critic-based methods, GRPO computes advantages by estimating the \emph{value baselin…
Diagnostic-Driven Layer-Wise Compensation for Post-Training Quantization of Encoder-Decoder ASR Models
Xinyu Wang, Ziyu Zhao, Yajie Luo +6
Layer-wise post-training quantization reconstructs each layer from inputs already altered by the quantized prefix. QEP compensates for this drift with one model-wide coefficient, c…