PPaperPicks

Zihan Wang

59 papers at tracked venues · 43 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. CIRAG: Construction-Integration Retrieval and Adaptive Generation for Multi-hop Question Answering
  2. CloserToMe: A Unified Framework for Accurate and Transferable Latency Prediction Across Heterogeneous Devices
  3. ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models
    AAAI 2026 · Zihan Wang
  4. CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges
    ACL 2026 · Zihan Wang
  5. DeepMed: Building a Medical DeepResearch Agent via Multi-hop Med-Search Data and Turn-Controlled Agentic Training & Inference
    ACL 2026 · Zihan Wang
  6. EMCompress: Video-LLMs with Endomorphic Multimodal Compression
  7. Factorized Latent Reasoning for LLM-based Recommendation
  8. GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities
  9. Is He Extroverted? Identifying Missing Relevant Personas for Faithful User Simulation
  10. KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference
  11. MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG
  12. MPMA: Preference Manipulation Attack Against Model Context Protocol
    AAAI 2026 · Zihan Wang
  13. MTAttack: Multi-Target Backdoor Attacks Against Large Vision-Language Models
    AAAI 2026 · Zihan Wang
  14. MTRouter: Cost-Aware Multi-Turn LLM Routing with History-Model Joint Embeddings
  15. MessToClean: Evidence-Grounded Structure-Preserving Reconstruction for Real-World Degraded Exam Paper Images
  16. Negotiating the Punchline: Contextual Meme Understanding via Discrete Semantic Energy Minimization
  17. Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG
  18. STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision
  19. VPN: Visual Prompt Navigation
  20. X-Router: Decoupling Knowledge and Reasoning for Cost-Effective LLM Inference
  21. AI Model Modulation with Logits Redistribution
    WWW 2025 · Zihan Wang
  22. Alignment for Efficient Tool Calling of Large Language Models
  23. Auxiliary Prompt Tuning of Vision-Language Models for Few-Shot Out-of-Distribution Detection
  24. CodeContests+: High-Quality Test Case Generation for Competitive Programming
    EMNLP 2025 · Zihan Wang
  25. Data Reconstruction Attacks and Defenses: A Systematic Evaluation
  26. Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
    NeurIPS 2025 · Zihan Wang
  27. Elastic Representation: Mitigating Spurious Correlations for Group Robustness
  28. FMM-Diff: A Feature Mapping and Merging Diffusion Model for MRI Generation with Missing Modality
  29. Flying on Point Clouds with Reinforcement Learning
  30. H-PRM: A Pluggable Hotword Pre-Retrieval Module for Various Speech Recognition Systems
  31. InfoGain-RAG: Boosting Retrieval-Augmented Generation through Document Information Gain-based Reranking and Filtering
    EMNLP 2025 · Zihan Wang
  32. InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning
  33. MUSE: A Multimodal Conversational Recommendation Dataset with Scenario-Grounded User Profiles
    ACL 2025 · Zihan Wang
  34. Modeling Cell Dynamics and Interactions with Unbalanced Mean Field Schrödinger Bridge
  35. MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion
    ICCV 2025 · Zihan Wang
  36. MorphingSkin: A Skin-like Platform that Integrates Multimodal Hydraulic Actuators Based on Flexible Electroosmotic Pumps
  37. NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLM
    ACL 2025 · Zihan Wang
  38. Reducing Tool Hallucination via Reliability Alignment
  39. Semantic-tailored Variational-Contrastive Graph Learning for Cognitive Diagnosis
  40. Towards Universal Perception through Language-Guided Open-World Object Detection
    ACM MM 2025 · Zihan Wang
  41. UniECS: Unified Multimodal E-Commerce Search Framework with Gated Cross-modal Fusion
  42. Variational Regularized Unbalanced Optimal Transport: Single Network, Least Action
  43. Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
  44. Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse
  45. g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks
    CVPR 2025 · Zihan Wang
  46. ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline
  47. CogAgent: A Visual Language Model for GUI Agents
  48. Commentary Generation from Data Records of Multiplayer Strategy Esports Game
    NAACL 2024 · Zihan Wang
  49. Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing
  50. Graph Bottlenecked Social Recommendation
  51. Implicit bias of SGD in L2-regularized linear DNNs: One-way jumps from high to low rank
    ICLR 2024 · Zihan Wang
  52. Learning Fair Representations for Recommendation via Information Bottleneck Principle
  53. Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation
    CVPR 2024 · Zihan Wang
  54. MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning
  55. Multimodal Inplace Prompt Tuning for Open-set Object Detection
  56. ONLS: Optimal Noise Level Search in Diffusion Autoencoders Without Fine-Tuning
    ICLR 2024 · Zihan Wang
  57. SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models
  58. Self-Renewal Prompt Optimizing with Implicit Reasoning
  59. Synergistic Reinforcement and Imitation Learning for Vision-driven Autonomous Flight of UAV Along River
    IROS 2024 · Zihan Wang