PPaperPicks

Jun Wang

48 papers at tracked venues · 33 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. "I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?
  2. Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning
  3. Compression Artifacts Removal for VVC with Frequency Domain Mixture of Experts Network
  4. FollowTable: A Benchmark for Instruction-Following Table Retrieval
  5. LSAP-PV: High-Fidelity Palm Vein Image Synthesis via Layered Spectral Absorption Projection-Guided Diffusion Model
  6. POP: Prefill-Only Pruning for Efficient Large Model Inference
  7. STCRank: Spatio-temporal Collaborative Ranking for Interactive Recommender System at Kuaishou E-shop
  8. TopFGL: A Topology-Aware and Distributionagnostic Federated Learning Framework Tackling Topological Heterogeneity on Graph Data
  9. 4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance
  10. A Bilevel Reinforcement Learning Framework with Language Prior Knowledge
  11. AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification
  12. Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization
  13. CIKT: A Collaborative and Iterative Knowledge Tracing Framework with Large Language Models
  14. CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels
  15. Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning
  16. DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL
  17. DUQ: Dual Uncertainty Quantification for Text-Video Retrieval
  18. Decoupled Global-Local Alignment for Improving Compositional Understanding
  19. DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment
  20. E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning
  21. Efficient Reinforcement Learning with Large Language Model Priors
  22. Enabling On-Chip Adaptive Linear Optimal Control via Linearized Gaussian Process
  23. FaceSpeak: Expressive and High-Quality Speech Synthesis from Human Portraits of Different Styles
  24. FedEcover: Fast and Stable Converging Model-Heterogeneous Federated Learning with Efficient-Coverage Submodel Extraction
  25. GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning
  26. MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading
  27. NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results
  28. OAgents: An Empirical Study of Building Effective Agents
  29. Plug-and-Play Physics-Informed Learning Using Uncertainty Quantified Port-Hamiltonian Models
  30. Recovery of Causal Graph Involving Latent Variables via Homologous Surrogates
  31. STaR-SQL: Self-Taught Reasoner for Text-to-SQL
  32. Self-Evolving Pseudo-Rehearsal for Catastrophic Forgetting with Task Similarity in LLMs
    NeurIPS 2025 · Jun Wang
  33. TUBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
  34. U-ViLAR: Uncertainty-Aware Visual Localization for Autonomous Driving via Differentiable Association and Registration
  35. Unified Adversarial Augmentation for Improving Palmprint Recognition
  36. WISE: A Framework for Gigapixel Whole-Slide-Image Lossless Compression
  37. An LLM-driven Framework for Multiple-Vehicle Dispatching and Navigation in Smart City Landscapes
  38. Boundary-aware Decoupled Flow Networks for Realistic Extreme Rescaling
  39. Bridge to Non-Barrier Communication: Gloss-Prompted Fine-Grained Cued Speech Gesture Generation with Diffusion Model
  40. CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation
    CVPR 2024 · Jun Wang
  41. Exploring NeuroDesign in Cultivating Empathy and Creativity in Primary Education in China
  42. GazePointAR: A Context-Aware Multimodal Voice Assistant for Pronoun Disambiguation in Wearable Augmented Reality
  43. Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf
  44. Mudslide: A Universal Nuclear Instance Segmentation Method
    CVPR 2024 · Jun Wang
  45. PointAttN: You Only Need Attention for Point Cloud Completion
    AAAI 2024 · Jun Wang
  46. Provable Acceleration of Nesterov's Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks
  47. Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives