QU Tianyuan

TainU's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 9 days ago

N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models

Paper • 2512.16561 • Published 10 days ago • 19

upvoted a paper 10 days ago

RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing

Paper • 2512.16864 • Published 10 days ago • 10

upvoted a paper 17 days ago

MotionEdit: Benchmarking and Learning Motion-Centric Image Editing

Paper • 2512.10284 • Published 18 days ago • 25

upvoted 2 papers 3 months ago

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Paper • 2510.11696 • Published Oct 13 • 176

LongLive: Real-time Interactive Long Video Generation

Paper • 2509.22622 • Published Sep 26 • 184

upvoted a paper 5 months ago

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning

Paper • 2507.13348 • Published Jul 17 • 77

upvoted a paper 7 months ago

VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning

Paper • 2505.12081 • Published May 17 • 18

upvoted a collection 7 months ago

Perception LM

Collection

7 items • Updated Apr 17 • 63

upvoted a paper 9 months ago

Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?

Paper • 2503.12496 • Published Mar 16 • 1

upvoted a paper 10 months ago

Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement

Paper • 2503.06520 • Published Mar 9 • 11

upvoted 2 papers about 1 year ago

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition

Paper • 2412.09501 • Published Dec 12, 2024 • 48

VisionZip: Longer is Better but Not Necessary in Vision Language Models

Paper • 2412.04467 • Published Dec 5, 2024 • 117