PPaperPicks

Jian Li

44 papers at tracked venues · 32 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding
  2. Deep Incomplete Multi-View Clustering via Hierarchical Imputation and Alignment
  3. FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning
  4. Gentle Manipulation Policy Learning via Demonstrations from VLM Planned Atomic Skills
  5. HSGraphAgent: Knowledge-Graph-Guided Large Language Models for Harmonized System Code Classification
  6. Kronos: A Foundation Model for the Language of Financial Markets
  7. Predicting Video Slot Attention Queries from Random Slot-Feature Pairs
  8. RadarMP: Motion Perception for 4D mmWave Radar in Autonomous Driving
  9. Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models
  10. UniMo: Unified Motion Generation and Understanding with Chain of Thought
  11. Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs
  12. Ambiguity Awareness Optimization: Towards Semantic Disambiguation for Direct Preference Optimization
    EMNLP 2025 · Jian Li
  13. Block-Based Multi-Scale Image Rescaling
    AAAI 2025 · Jian Li
  14. CodeTool: Enhancing Programmatic Tool Invocation of LLMs via Process Supervision
  15. CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards
  16. CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models
  17. Constrained Feedback Learning for Non-Stationary Multi-Armed Bandits
  18. Decentralized Federated Learning with Model Caching on Mobile Agents
  19. Edge-Guided Lighting Adaptation: Real-Time Detection of Transparent Objects for Cell Culture Robot
  20. Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
  21. From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective
  22. MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving
  23. Micro-UAV with Ant-Inspired Bistable Gripper for Adaptive Perching and Wildlife Detection
  24. MiniClean: A Single-Machine System for Cleaning Big Graphs
  25. Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints
  26. On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations
  27. OpenFE++: Efficient Automated Feature Generation via Feature Interaction
  28. Provably Efficient Exploration in Inverse Constrained Reinforcement Learning
  29. Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior
  30. Rethinking Learner Modeling: A Feedback-Centric Cognitive Disentanglement Perspective
  31. The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement
  32. Towards Fine-Grained Human Motion Video Captioning
  33. Understanding Constraint Inference in Safety-Critical Inverse Reinforcement Learning
  34. Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws
  35. pFedGPT: Hierarchically Optimizing LoRA Aggregation Weights for Personalized Federated GPT Models
  36. 6-DoF Grasp Detection in Clutter with Enhanced Receptive Field and Graspable Balance Sampling
  37. Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game
  38. Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models
  39. Convolutional Spectral Kernel Learning with Generalization Guarantees (Abstract Reprint)
    AAAI 2024 · Jian Li
  40. LoRA-GA: Low-Rank Adaptation with Gradient Approximation
  41. Online Restless Multi-Armed Bandits with Long-Term Fairness Constraints
  42. Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection
  43. Towards Reliable Advertising Image Generation Using Human Feedback
  44. Visual Loop Closure Detection with Thorough Temporal and Spatial Context Exploitation