pith. sign in

Conghui He

Identifiers

  • name variant Conghui He 0.60 · backfill

Papers (35)

  1. FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection cs.CV · 2026 · author #5
  2. Exascale Hybrid Numerical-AI Ensembles for Operational Flood-Season Forecasting in East Asia: 15-km Decadal Hindcasts and 1-km High-Resolution Capability cs.CE · 2026 · author #17
  3. PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control cs.AI · 2026 · author #10
  4. Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning cs.AI · 2026 · author #4
  5. CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence cs.CL · 2026 · author #11
  6. NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation cs.AI · 2026 · author #14
  7. PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents cs.AI · 2026 · author #7
  8. MolRecBench-Wild: A Real-World Benchmark for Optical Chemical Structure Recognition cs.AI · 2026 · author #17
  9. Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists cs.AI · 2026 · author #13
  10. Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora cs.SE · 2026 · author #7
  11. Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs cs.AI · 2026 · author #11
  12. MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale cs.CV · 2026 · author #43
  13. MoDora: Tree-Based Semi-Structured Document Analysis System cs.IR · 2026 · author #10
  14. ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch cs.CV · 2026 · author #14
  15. OmniAID: Decoupling Semantic and Artifacts for Universal AI-Generated Image Detection in the Wild cs.CV · 2025 · author #6
  16. MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing cs.CV · 2025 · author #61
  17. Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature cs.CL · 2025 · author #6
  18. InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency cs.CV · 2025 · author #39
  19. InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models cs.CV · 2025 · author #28
  20. FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding cs.CV · 2025 · author #6
  21. Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling cs.CV · 2024 · author #20
  22. Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction cs.MM · 2024 · author #7
  23. PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction cs.CV · 2024 · author #8
  24. MinerU: An Open-Source Solution for Precise Document Content Extraction cs.CV · 2024 · author #18
  25. InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output cs.CV · 2024 · author #21
  26. How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites cs.CV · 2024 · author #16
  27. InternLM2 Technical Report cs.CL · 2024 · author #22
  28. InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model cs.CV · 2024 · author #19
  29. Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization cs.CV · 2023 · author #6
  30. ShareGPT4V: Improving Large Multi-Modal Models with Better Captions cs.CV · 2023 · author #5
  31. InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition cs.CV · 2023 · author #17
  32. InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation cs.CV · 2023 · author #11
  33. MMBench: Is Your Multi-modal Model an All-around Player? cs.CV · 2023 · author #9
  34. LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model cs.CV · 2023 · author #9
  35. swCaffe: a Parallel Framework for Accelerating Deep Learning Applications on Sunway TaihuLight cs.DC · 2019 · author #6

Mentions

  • 2605.30062 #5 · arxiv_oai · confidence 0.70 Conghui He
  • 2511.08423 #6 · arxiv_oai · confidence 0.70 Conghui He
  • 2605.24896 #17 · arxiv_oai · confidence 0.70 Conghui He
  • 2605.15963 #10 · arxiv_oai · confidence 0.70 Conghui He
  • 2309.15112 #17 · arxiv_oai · confidence 0.70 Conghui He
  • 2509.22186 #61 · arxiv_oai · confidence 0.70 Conghui He
  • 2311.16839 #6 · arxiv_oai · confidence 0.70 Conghui He
  • 2407.03320 #21 · arxiv_oai · confidence 0.70 Conghui He
  • 2401.16420 #19 · arxiv_oai · confidence 0.70 Conghui He
  • 2409.18839 #18 · arxiv_oai · confidence 0.70 Conghui He

Frequent Coauthors