PPaperPicks

Wei Wu

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

Venues

Frequent coauthors

Papers

  1. Beyond Static Alignment: Adaptive Arbitration for Semantic Incongruence in Semi-Supervised Multimodal Sentiment Analysis
  2. Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models
  3. Explicit Modeling of Causal Factors and Confounders for Image Classification
    AAAI 2026 · Wei Wu
  4. Introducing Decomposed Causality with Spatiotemporal Object-Centric Representation for Video Classification
  5. BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge Distillation
  6. Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning
  7. Causal Inference over Visual-Semantic-Aligned Graph for Image Classification
  8. Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling
  9. Empowering Vision Transformers with Multi-Scale Causal Intervention for Long-Tailed Image Classification
  10. Generalized and Invariant Single-Neuron In-Vivo Activity Representation Learning
    NeurIPS 2025 · Wei Wu
  11. Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access
  12. KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment
  13. LEMMA: Learning from Errors for MatheMatical Advancement in LLMs
  14. LLMs as Workers in Human-Computational Algorithms? Replicating Crowdsourcing Pipelines with LLMs
  15. Learning Visual Generative Priors without Text
  16. Neuron Platonic Intrinsic Representation From Dynamics Using Contrastive Learning
    ICLR 2025 · Wei Wu
  17. OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models
  18. Real-time Whole-body Motion Planning Based on Optimized NMPC in Static and Dynamic Environments for Mobile Manipulator
    IROS 2025 · Wei Wu
  19. Semantic-Space-Intervened Diffusive Alignment for Visual Classification
  20. TIETracker: A CLIP-based RGB-T Tracking via Feature Interaction and Semantic Enhancement
  21. Towards Doctor-Like Reasoning: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients
  22. Transitive self-consistency evaluation of NLI models without gold labels
    EMNLP 2025 · Wei Wu
  23. Unsupervised Morphological Tree Tokenizer
  24. Augmenting Transformers with Recursively Composed Multi-grained Representations
  25. Bridge-IF: Learning Inverse Protein Folding with Markov Bridges
  26. FreeDiff: Progressive Frequency Truncation for Image Editing with Diffusion Models
    ECCV 2024 · Wei Wu
  27. Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale
  28. LoTLIP: Improving Language-Image Pre-training for Long Text Understanding
    NeurIPS 2024 · Wei Wu