Wanjia Zhao

OpenThoughts: Data Recipes for Reasoning Models

Sample Lottery: Unsupervised Discovery of Critical Instances for LLM Reasoning

PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning

GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters

Rethink GraphODE Generalization within Coupled Dynamical System

Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language Models

DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search

SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning