PPaperPicks

Zhangyue Yin

22 papers at tracked venues · 13 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models
    ACL 2026 · Zhangyue Yin
  2. Demystifying GNN-to-MLP Knowledge Transfer: Theoretical Grounding and Dual-Stream Distillation Method
  3. Efficient KL Divergence Estimation via Truncated Top-K Integration for Large Language Models
  4. OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows
  5. Thermometer of Thoughts: Enhancing LLM's Exploration via Attention Temperature Modulation
  6. Are LLMs Rational Investors? A Study on the Financial Bias in LLMs
  7. Contextual Structure Knowledge Transfer for Graph Neural Networks
  8. Dynamic and Generalizable Process Reward Modeling
    ACL 2025 · Zhangyue Yin
  9. Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework
    EMNLP 2025 · Zhangyue Yin
  10. R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
  11. Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
  12. VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks
  13. VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction
  14. Can AI Assistants Know What They Don't Know?
  15. Explicit Memory Learning with Expectation Maximization
    EMNLP 2024 · Zhangyue Yin
  16. LLatrieval: LLM-Verified Retrieval for Verifiable Generation
  17. Memorize Step by Step: Efficient Long-Context Prefilling with Incremental Memory and Decremental Chunk
  18. Pixel-Level Semantic Correspondence Through Layout-Aware Representation Learning and Multi-Scale Matching Integration
  19. Reasoning in Flux: Enhancing Large Language Models Reasoning through Uncertainty-aware Adaptive Guidance
    ACL 2024 · Zhangyue Yin
  20. R³-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL
  21. Turn Waste into Worth: Rectifying Top-k Router of MoE
  22. Unified Active Retrieval for Retrieval Augmented Generation