PPaperPicks

Zihan Zhang

40 papers at tracked venues · 23 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration
  2. Generative-to-Discriminative Test-Time Adaptation via Manifold-Aware Diffusion and Bayesian Distillation
  3. GraphRAG-Induced Dual Knowledge Structure Graphs for Personalized Learning Path Recommendation
  4. Harmonizing the Senses: Designing a Cross-Modal Interactive Art System to Enhance Older Adults' Affective Experiences
  5. Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth Analysis Using a Neuropsychology-Inspired Benchmark
    ACL 2026 · Zihan Zhang
  6. Knowledge-Enhanced Explainable Hypergraph Convolution Network for Medication Recommendation
    AAAI 2026 · Zihan Zhang
  7. NavMapFusion: Diffusion-based Fusion of Navigation Maps for Online Vectorized HD Map Construction
  8. Online Learning for Uninformed Markov Games: Empirical Nash-Value Regret and Non-Stationarity Adaptation
  9. ProjecTA: A Semi-Humanoid Robotic Teaching Assistant with In-Situ Projection for Guided Tours
  10. AISHELL-5: The First Open-Source In-Car Multi-Channel Multi-Speaker Speech Dataset for Automatic Speech Diarization and Recognition
  11. Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits
    ICLR 2025 · Zihan Zhang
  12. Anytime Acceleration of Gradient Descent
    COLT 2025 · Zihan Zhang
  13. Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving
  14. Breaking Barriers or Building Dependency? Exploring Team-LLM Collaboration in AI-infused Classroom Debate
    CHI 2025 · Zihan Zhang
  15. CabinSep: IR-Augmented Mask-Based MVDR for Real-Time In-car Speech Separation with Distributed Heterogeneous Arrays
  16. Context-DPO: Aligning Language Models for Context-Faithfulness
  17. Deployment Efficient Reward-Free Exploration with Linear Function Approximation
    NeurIPS 2025 · Zihan Zhang
  18. Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning
  19. LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement
  20. MapDiffusion: Generative Diffusion for Vectorized Online HD Map Construction and Uncertainty Estimation in Autonomous Driving
  21. Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback
    ICML 2025 · Zihan Zhang
  22. NL2Lean: Translating Natural Language into Lean 4 through Multi-Aspect Reinforcement Learning
  23. Robust Model-Free Path Tracking Algorithm for Hydraulic Center-Articulated Scooptrams
    IROS 2025 · Zihan Zhang
  24. Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs
  25. SiriusBI: A Comprehensive LLM-powered Solution for Data Analytics in Business Intelligence
  26. Towards Distributionally Balanced End-to-End Generative Retrieval
  27. Achieving Tractable Minimax Optimal Regret in Average Reward MDPs
  28. BS-PLCNet 2: Two-stage Band-split Packet Loss Concealment Network with Intra-model Knowledge Distillation
    InterSpeech 2024 · Zihan Zhang
  29. Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning
  30. Exploiting Multifaceted Nature of Items and Users for Session-based Recommendation
  31. HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition
  32. Horizon-Free Regret for Linear Markov Decision Processes
    ICLR 2024 · Zihan Zhang
  33. MedINST: Meta Dataset of Biomedical Instructions
  34. OSM vs HD Maps: Map Representations for Trajectory Prediction
  35. Optimal Multi-Distribution Learning
    COLT 2024 · Zihan Zhang
  36. ResLoRA: Identity Residual Mapping in Low-Rank Adaption
  37. RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering
    ACL 2024 · Zihan Zhang
  38. Settling the sample complexity of online reinforcement learning
    COLT 2024 · Zihan Zhang
  39. Text Diffusion with Reinforced Conditioning
  40. Vision-Language Dual-Pattern Matching for Out-of-Distribution Detection
    ECCV 2024 · Zihan Zhang