PPaperPicks

Zhuotao Tian

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

Venues

Frequent coauthors

Papers

  1. Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework
  2. SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation
  3. CalibCLIP: Contextual Calibration of Dominant Semantics for Text-Driven Image Retrieval
  4. Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations
  5. Context-Aware Hierarchical Learning: A Two-Step Paradigm towards Safer LLMs
  6. DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception
  7. Edit360: 2D Image Edits to 3D Assets From Any Angle
  8. Enhancing Spatial Reasoning in Multimodal Large Language Models Through Reasoning-Based Segmentation
  9. Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
  10. Mitigating Object Hallucinations via Sentence-Level Early Intervention
  11. RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression Comprehension
  12. VisionZip: Longer is Better but Not Necessary in Vision Language Models
  13. Decoupled Kullback-Leibler Divergence Loss
  14. Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation
  15. GroupContrast: Semantic-Aware Self-Supervised Representation Learning for 3D Understanding
  16. LISA: Reasoning Segmentation via Large Language Model
  17. Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models
  18. OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
  19. Referencing Where to Focus: Improving Visual Grounding with Referential Query
  20. SaCo Loss: Sample-Wise Affinity Consistency for Vision-Language Pre-Training
  21. Scalable Language Model with Generalized Continual Learning
  22. Towards Large-Scale 3D Representation Learning with Multi-Dataset Point Prompt Training
  23. Typicalness-Aware Learning for Failure Detection
  24. Unified Language-Driven Zero-Shot Domain Adaptation