PPaperPicks

Jian Liu

29 papers at tracked venues · 26 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning
  2. Rethinking Semantic-Collaborative Integration: Why Alignment Is Not Enough
  3. TextShield-R1: Reinforced Reasoning for Tampered Text Detection
  4. ABase: the Multi-Tenant NoSQL Serverless Database for Diverse and Dynamic Workloads in Large-scale Cloud Environments
  5. Adaptive Merchant-Centric Risk Control via Unbiased Decision-Making and Dynamic Optimization in E-Commerce
  6. Backdooring Self-Supervised Contrastive Learning by Noisy Alignment
  7. Boosting Single-Domain Generalized Object Detection via Vision-Language Knowledge Interaction
  8. EmoRLTalk: Speech-Driven Emotional Facial Animation With Offline Reinforcement Learning
  9. FerretNet: Efficient Synthetic Image Detection via Local Pixel Dependencies
  10. FlexQuant: A Flexible and Efficient Dynamic Precision Switching Framework for LLM Quantization
  11. G-DexGrasp: Generalizable Dexterous Grasping Synthesis via Part-Aware Prior Retrieval and Prior-Assisted Generation
  12. Generalizable Audio Deepfake Detection via Hierarchical Structure Learning and Feature Whitening in Poincaré sphere
  13. Generalizable Audio Deepfake Detection via Risk-Aware Style Alignment and Structural Empirical Risk Minimization
  14. KGCRR: An Effective Metric-Driven Knowledge Graph Completion Framework by Designing a Novel Upper Bound Function with Adaptive Approximation to Reciprocal Rank
  15. Learning Discrepant Transformations for Face Privacy Protection
  16. MTA-VPS: A Large-scale Benchmark for Video-Based Person Search
  17. MambaMl: Exploring State Space Models for Multi-Label Image Classification
  18. MoFRR: Mixture of Diffusion Models for Face Retouching Restoration
  19. OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM
  20. PSBench: a large-scale benchmark for estimating the accuracy of protein complex structural models
  21. PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection
  22. Scalable Autoregressive Monocular Depth Estimation
  23. TAET: Two-Stage Adversarial Equalization Training on Long-Tailed Distributions
  24. Towards Generalized Physical Occlusion Detection On Documents
  25. Divide-and-Aggregate Learning for Evaluating Performance on Unlabeled Data
  26. LavaStore: ByteDance's Purpose-built, High-performance, Cost-effective Local Storage Engine for Cloud Services
  27. Position: TrustLLM: Trustworthiness in Large Language Models
  28. SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment
  29. Towards Better Question Generation in QA-based Event Extraction