pith. machine review for the scientific record. sign in

Zihan Wang

Identifiers

  • name variant Zihan Wang 0.60 · backfill

Papers (44)

  1. WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors cs.CV · 2026 · author #11
  2. From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning cs.AI · 2026 · author #5
  3. The JWST early galaxy crisis resolved by a reionization degeneracy astro-ph.CO · 2026 · author #1
  4. A structural degeneracy explains reionization tensions and limits dark matter constraints astro-ph.CO · 2026 · author #1
  5. Jailbroken Frontier Models Retain Their Capabilities cs.LG · 2026 · author #2
  6. Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG cs.IR · 2026 · author #2
  7. Factorized Latent Reasoning for LLM-based Recommendation cs.IR · 2026 · author #3
  8. GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents cs.CV · 2026 · author #33
  9. Learning from Medical Entity Trees: An Entity-Centric Medical Data Engineering Framework for MLLMs cs.CL · 2026 · author #7
  10. MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG cs.CL · 2026 · author #2
  11. MTRouter: Cost-Aware Multi-Turn LLM Routing with History-Model Joint Embeddings cs.CL · 2026 · author #3
  12. Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study cs.CR · 2026 · author #1
  13. Breaking the UV Luminosity Function Degeneracy:Self-Interacting Dark Matter Constraints from Reionization Topology astro-ph.CO · 2026 · author #1
  14. Allo{SR}$^2$: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows cs.CV · 2026 · author #1
  15. The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview cs.CV · 2026 · author #87
  16. VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects cs.CV · 2026 · author #13
  17. Reionization Topology as a Probe of Self-Interacting Dark Matter astro-ph.CO · 2026 · author #1
  18. Time Series Gaussian Chain Graph Models stat.ME · 2026 · author #3
  19. Variational Feature Compression for Model-Specific Representations cs.CV · 2026 · author #2
  20. Precise Aggressive Aerial Maneuvers with Sensorimotor Policies cs.RO · 2026 · author #3
  21. RAGEN-2: Reasoning Collapse in Agentic RL cs.LG · 2026 · author #1
  22. LensAgent: A Self Evolving Agent for Autonomous Physical Inference of Sub-galactic Structure astro-ph.GA · 2026 · author #2
  23. ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding cs.CV · 2026 · author #18
  24. Wilson loop in AdS$_3 \times S^3 \times T^4$ from quantum M2 brane hep-th · 2026 · author #2
  25. Model Editing for New Document Integration in Generative Information Retrieval cs.IR · 2026 · author #2
  26. GLM-5: from Vibe Coding to Agentic Engineering cs.LG · 2026 · author #51
  27. Kimi K2.5: Visual Agentic Intelligence cs.CL · 2026 · author #213
  28. Dark QCD Origin of the NANOGrav Signal and Self-Interacting Dark Matter astro-ph.CO · 2026 · author #1
  29. Scalar-Mediated Inelastic Dark Matter as a Solution to Small-Scale Structure Anomalies hep-ph · 2025 · author #1
  30. Re-Key-Free, Risky-Free: Adaptable Model Usage Control cs.CR · 2025 · author #1
  31. Magnon-mediated Radiation and Phonon-driven Quenching of Excitons in a Layered Semiconductor cond-mat.mtrl-sci · 2025 · author #3
  32. EMCompress: Video-LLMs with Endomorphic Multimodal Compression cs.CV · 2025 · author #4
  33. GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models cs.CL · 2025 · author #25
  34. GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning cs.CV · 2025 · author #85
  35. RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning cs.LG · 2025 · author #1
  36. Humanity's Last Exam cs.LG · 2025 · author #38
  37. CogVLM2: Visual Language Models for Image and Video Understanding cs.CV · 2024 · author #17
  38. ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools cs.CL · 2024 · author #57
  39. Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis cs.CV · 2024 · author #7
  40. DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model cs.CL · 2024 · author #154
  41. GLM-130B: An Open Bilingual Pre-trained Model cs.CL · 2022 · author #4
  42. ECG Identification under Exercise and Rest Situations via Various Learning Methods eess.SP · 2019 · author #1
  43. A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies cs.RO · 2018 · author #2
  44. Why It Takes So Long to Connect to a WiFi Access Point cs.NI · 2017 · author #4

Mentions

  • 2408.16500 #17 · arxiv_oai · confidence 0.70 Zihan Wang
  • 2603.27064 #18 · backfill · confidence 0.70 Zihan Wang

Frequent Coauthors