PPaperPicks

Di Huang

31 papers at tracked venues · 28 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. QiMeng-CRUX: Narrowing the Gap Between Natural Language and Verilog via Core Refined Understanding eXpression
  2. QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization
  3. Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning
  4. Rhombus: Incentivizing Coordination in Parallel Thinking through Reinforcement Learning
  5. Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigation
  6. Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions
  7. StepFun-Formalizer: Unlocking the Autoformalization Potential of LLMs Through Knowledge-Reasoning Fusion
  8. ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems
  9. Constraint-Aware Feature Learning for Parametric Point Cloud
  10. Depth Any Video with Scalable Synthetic Data
  11. GigaGS: 3D Gaussian Based Planar Representation for Large-Scene Surface Reconstruction
  12. GraphSeqLM: A Unified Graph Language Framework for Omic Graph Learning
  13. InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct
  14. MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers
  15. MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions
  16. ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction
  17. QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation
  18. QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code
  19. QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation
  20. Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction
  21. Agent3D-Zero: An Agent for Zero-Shot 3D Understanding
  22. Emergent Communication for Numerical Concepts Generalization
  23. FiT: Flexible Vision Transformer for Diffusion Model
  24. Freehand Sketch Generation from Mechanical Components
  25. GVGEN: Text-to-3D Generation with Volumetric Representation
  26. Hypothesis, Verification, and Induction: Grounding Large Language Models with Self-Driven Skill Learning
  27. MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators
  28. NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction
  29. Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning
  30. PredBench: Benchmarking Spatio-Temporal Prediction Across Diverse Disciplines
  31. UniPAD: A Universal Pre-Training Paradigm for Autonomous Driving