12 papers
Reachability Is Not Realization: Tracing the Sources of LLM Benchmark Gains
Yanchao Li, Wanhao Liu, Jiaqing Xie +4
Benchmark gains are often treated as evidence of greater LLM capability. Yet the same gain can reflect different changes in model behavior. A model may reach new answers, or produc…
Disagree to Accelerate: Closing the Loop on Diffusion Feature Forecasts
Yanchao Li, Jiaqing Xie, Ben Gao +6
Training-free feature forecasting accelerates diffusion sampling by predicting features at skipped denoising steps. Recent work has mainly focused on designing stronger forecasters…
OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science Subfields
Wanhao Liu, Jiaqing Xie, Qian Tan +10
As multimodal language models play an increasingly important role in scientific research, materials science offers a critical testbed due to its interdisciplinary, multimodal, and…
SkillsInjector: Dynamic Skill Context Construction for LLM Agents
Yanchao Li, Wanhao Liu, Ben Gao +5
LLM agents now draw on growing skill libraries to handle complex tasks. However, injecting more skills does not always improve task completion and can even degrade it. Existing met…
PolyReal: A Benchmark for Real-World Polymer Science Workflows
Wanhao Liu, Weida Wang, Jiaqing Xie +12
Multimodal Large Language Models (MLLMs) excel in general domains but struggle with complex, real-world science. We posit that polymer science, an interdisciplinary field spanning…
MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization
Zhuo Yang, Yeyun Chen, Jiaqing Xie +7
Molecular editing and optimization are multi-step problems that require iteratively improving properties while keeping molecules chemically valid and structurally similar. We frame…