9 papers
HEAPr: Hessian-based Efficient Atomic Expert Pruning in Output Space
Ke Li, Zheng Yang, Zhongbin Zhou +3
Mixture-of-Experts (MoE) architectures in large language models (LLMs) deliver exceptional performance and reduced inference costs compared to dense LLMs. However, their large para…
ProOPF: Benchmarking and Improving LLMs for Professional-Grade Power Systems Optimization Modeling
Chao Shen, Zihan Guo, Xu Wan +6
Growing renewable penetration introduces substantial uncertainty into power system operations, necessitating frequent adaptation of dispatch objectives and constraints and challeng…
Boosting LLM Reasoning via Human-Inspired Reward Shaping
Wenze Lin, Zhen Yang, Xitai Jiang +2
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for enhancing reasoning in Large Language Models (LLMs). However, existing reward formulat…
Fixturize: Bridging the Fixture Gap in Test Generation
Chengyi Wang, Pengyu Xue, Zhen Yang +8
Current Large Language Models (LLMs) have advanced automated unit test generation but face a critical limitation: they often neglect to construct the necessary test fixtures, which…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
MathSight: A Benchmark Exploring Have Vision-Language Models Really Seen in University-Level Mathematical Reasoning?
Yuandong Wang, Yao Cui, Yuxin Zhao +3
Recent advances in Vision-Language Models (VLMs) have achieved impressive progress in multimodal mathematical reasoning. Yet, how much visual information truly contributes to reaso…