PPaperPicks

Lingxi Xie

19 papers at tracked venues · 16 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Few-step Flow for 3D Generation via Marginal-Data Transport Distillation
  2. WorldGrow: Generating Infinite 3D World
  3. Adaptive Keyframe Sampling for Long Video Understanding
  4. CLIP-Adapted Region-to-Text Learning for Generative Open-Vocabulary Semantic Segmentation
  5. ChatterBox: Multimodal Referring and Grounding with Chain-of-Questions
  6. ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension
  7. Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models
  8. SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation
  9. Segment Any 3D Gaussians
  10. Tackling View-Dependent Semantics in 3D Language Gaussian Splatting
  11. 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
  12. AlignZeg: Mitigating Objective Misalignment for Zero-Shot Semantic Segmentation
  13. Artemis: Towards Referential Understanding in Complex Videos
  14. Cascade-Zero123: One Image to Highly Consistent 3D with Self-prompted Nearby Views
  15. GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models
  16. GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions
  17. Parameter Efficient Fine-Tuning via Cross Block Orchestration for Segment Anything Model
  18. QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
  19. VMamba: Visual State Space Model