大模型推理能力

Apriel-H1: Towards Efficient Enterprise Reasoning Models

Oleksiy Ostapenko, Luke Kumar, Raymond Li, Denis Kocetkov, Joel Lamy-Poirier, Shruthan Radhakrishna, Soham Parikh, Shambhavi Mishra, Sebastien Paquet, Srinivas Sunkara, Valérie Bécaert, Sathwik Tejaswi Madhusudhan, Torsten Scholak

机构 * SLAM Lab（SLAM实验室） ； ServiceNow 纠错

专题命中 测试时计算 ：reasoning(title,abstract)；test-time compute(abstract)；分类 cs.AI、cs.LG

DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning

Qi Cao, Ruiyi Wang, Ruiyi Zhang, Sai Ashish Somayajula, Pengtao Xie

机构 * University of California, San Diego（加州大学圣地亚哥分校） ； Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学） 纠错

专题命中 测试时计算 ：reasoning(title,abstract)；分类 cs.AI、cs.LG

Comments 28 pages, 10 figures, to appear in NeurIPS 2025 (Conference on Neural Information Processing Systems)

Inference-Time Chain-of-Thought Pruning with Latent Informativeness Signals

Sophie Li, Nicholas Huang, Nayan Saxena, Nina Luo, Vincent Lin, Kevin Zhu, Sunishchal Dev

专题命中 测试时计算 ：chain-of-thought(title)；reasoning(abstract,comments)；分类 cs.LG

Comments Accepted by NeurIPS 2025 Workshop on Efficient Reasoning

TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers' Guidance

Jingxian Xu, Mengyu Zhou, Weichang Liu, Hanbing Liu, Shi Han, Dongmei Zhang

机构 * Nankai University（南开大学） ； BeijingJiaoTong University（北京交通大学） ； Tsinghua University（清华大学） ； Microsoft Research（微软研究院） 纠错

专题命中 测试时计算 ：reasoning(title,abstract)；分类 cs.CL

The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute

Aman Sharma, Paras Chopra

机构 * Lossfunk 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.AI、cs.LG

Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs

Jiace Zhu, Yuanzhe Huang, Yingtao Shen, Jie Zhao, An Zou

机构 * Shanghai Jiao Tong University（上海交通大学） ； Microsoft Corporation（微软公司） 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL、cs.AI

Training Language Models to Reason Efficiently

Daman Arora, Andrea Zanette

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments NeurIPS 2025