pith. the verified trust layer for science. sign in

Xingyu Chen

Identifiers

  • name variant Xingyu Chen 0.60 · backfill

Papers (13)

  1. SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding cs.CV · 2026 · author #8
  2. PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models cs.RO · 2026 · author #7
  3. ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models cs.RO · 2026 · author #7
  4. VoxAfford: Multi-Scale Voxel-Token Fusion for Open-Vocabulary 3D Affordance Detection cs.CV · 2026 · author #7
  5. GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens cs.CV · 2026 · author #4
  6. AffordSim: A Scalable Data Generator and Benchmark for Affordance-Aware Robotic Manipulation cs.RO · 2026 · author #11
  7. HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model cs.RO · 2026 · author #2
  8. Toward Reliable Sim-to-Real Predictability for MoE-based Robust Quadrupedal Locomotion cs.RO · 2026 · author #7
  9. Generation-Augmented Generation: A Plug-and-Play Framework for Private Knowledge Injection in Large Language Models cs.CL · 2026 · author #7
  10. SAM 3D: 3Dfy Anything in Images cs.CV · 2025 · author #2
  11. TTT3R: 3D Reconstruction as Test-Time Training cs.CV · 2025 · author #1
  12. DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning cs.CL · 2025 · author #5
  13. Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs cs.CL · 2024 · author #1

Mentions

  • 2509.26645 #1 · arxiv_oai · confidence 0.70 Xingyu Chen
  • 2504.11456 #5 · arxiv_oai · confidence 0.70 Xingyu Chen

Frequent Coauthors