PPaperPicks

Biqing Qi

34 papers at tracked venues · 29 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. A Survey of Inductive Reasoning for Large Language Models
  2. D²Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning
  3. GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning
  4. LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing
  5. MARS²: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation
  6. Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism
  7. SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding
  8. SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation
  9. WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement
  10. Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration
  11. DePass: Unified Feature Attributing by Simple Decomposed Forward Pass
  12. Fast and Slow Gradient Approximation for Binary Neural Network Optimization
  13. Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization
  14. Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning
  15. Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process
  16. Less is More: Efficient Model Merging with Binary Task Switch
    CVPR 2025 · Biqing Qi
  17. Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System
  18. OpenPRM: Building Open-domain Process-based Reward Models with Preference Trees
  19. Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines
  20. ReviewRL: Towards Automated Scientific Review with RL
  21. T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge Retrieval
  22. TTRL: Test-Time Reinforcement Learning
  23. An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning
  24. CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following
  25. Exploring Adversarial Robustness of Deep State Space Models
    NeurIPS 2024 · Biqing Qi
  26. Interactive Continual Learning: Fast and Slow Thinking
    CVPR 2024 · Biqing Qi
  27. MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making
  28. Neural Residual Diffusion Models for Deep Scalable Vision Generation
  29. On Large Language Models' Hallucination with Regard to Known Facts
  30. On the token distance modeling ability of higher RoPE attention dimension
  31. PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning
  32. SMR: State Memory Replay for Long Sequence Modeling
    ACL 2024 · Biqing Qi
  33. Safe-SD: Safe and Traceable Stable Diffusion with Text Prompt Trigger for Invisible Generative Watermarking
  34. UltraMedical: Building Specialized Generalists in Biomedicine