← authors · overview

• A Materials Foundation Model via Hybrid Invariant-Equivariant Architectures
  2025 · 6 citations
• CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning
  2025 · 1 citations
• StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception
  2026
• SG-VLA: Learning Spatially-Grounded Vision-Language-Action Models for Mobile Manipulation
  2026
• Randomized Antipodal Search Done Right for Data Pareto Improvement of LLM Unlearning
  2026
• GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training
  2026
• FFT-Accelerated Auxiliary Variable MCMC for Fermionic Lattice Models: A Determinant-Free Approach with $O(Nłog N)$ Complexity
  2025
• DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion
  2025
• Augmenting Molecular Graphs with Geometries via Machine Learning Interatomic Potentials
  2025
• DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion
  2025
• Latent Adaptive Planner for Dynamic Manipulation
  2025
• OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning
  2025
• Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark
  2025