5 papers
Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance
Wenhao Chen, Sirui Sun, Shengyuan Bai +1
Aligning large language models (LLMs) with human values typically relies on post-training or inference-time steering that directly manipulates the backbone's parameters or represen…
ReactBench: A Benchmark for Topological Reasoning in MLLMs on Chemical Reaction Diagrams
Qiang Xu, Shengyuan Bai, Yu Wang +6
Multimodal Large Language Models (MLLMs) excel at recognizing individual visual elements and reasoning over simple linear diagrams. However, when faced with complex topological str…
Gaze patterns predict preference and confidence in pairwise AI image evaluation
Nikolas Papadopoulos, Shreenithi Navaneethan, Sheng Bai +2
Preference learning methods, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on pairwise human judgments, yet little is kno…
Mozi: Governed Autonomy for Drug Discovery LLM Agents
He Cao, Siyu Liu, Fan Zhang +7
Tool-augmented large language model (LLM) agents promise to unify scientific reasoning with computation, yet their deployment in high-stakes domains like drug discovery is bottlene…
ChemLabs on ChemO: A Multi-Agent System for Multimodal Reasoning on IChO 2025
Qiang Xu, Shengyuan Bai, Leqing Chen +2
Olympiad-level benchmarks in mathematics and physics are crucial testbeds for advanced AI reasoning, but chemistry, with its unique multimodal symbolic language, has remained an op…