collaborators

13 papers

cs.LG2026

Hierarchical Data Selection via Manifold Coverage and Sparse Feature Coverage in LLM Post-training

Peng Sun, Yi Yang, Antong Zhang +7

As supervised fine-tuning data continues to scale, selecting high-value subsets from large candidate pools is crucial for reducing training cost and improving model performance. Ex…

cs.LG2026

Data-DPO: Direct Preference Optimization for Target Model Data Selection in LLM Post-Training

Peng Sun, Yi Yang, Antong Zhang +7

Data selection in supervised fine-tuning aims to select a small set of effective samples from large-scale candidate data, reducing training cost while preserving model performance.…

cs.AI2026

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…

cs.LG2026

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…

cs.LG2026

ABOPD: Antibody CDR Design via On-Policy Distillation

Zhuo Yang, Jiaying He, Jiaqing Xie +5

Antibodies are essential therapeutic molecules, and their complementarity-determining regions (CDRs) form the primary antigen-recognition interface. Recent protein generative model…

cs.LG2026

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

Wanghan Xu, Shuo Li, Tianlin Ye +48

AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchma…