OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
Paper • 2602.08683 • Published • 52
vibe_ov2
classroom
AI & ML interests
None defined yet.
xiangan
authored a
paper about 2 months ago
xiangan
authored 2
papers 2 months ago
jankin123
submitted a
paper to Daily Papers 2 months ago
jankin123
authored 8
papers 6 months ago
VisRL: Intention-Driven Visual Perception via Reinforced Reasoning
Paper • 2503.07523 • Published • 1
Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling
Paper • 2508.03404 • Published • 4
SIFThinker: Spatially-Aware Image Focus for Visual Reasoning
Paper • 2508.06259 • Published • 2
Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow
Paper • 2509.21789 • Published • 9
Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
Paper • 2510.18632 • Published • 23
NFR: Neural Feature-Guided Non-Rigid Shape Registration
Paper • 2505.22445 • Published
CodingTeachLLM: Empowering LLM's Coding Ability via AST Prior Knowledge
Paper • 2403.15426 • Published
DV-Matcher: Deformation-based Non-Rigid Point Cloud Matching Guided by Pre-trained Visual Features
Paper • 2408.08568 • Published
xiangan
authored 4
papers 6 months ago
ForCenNet: Foreground-Centric Network for Document Image Rectification
Paper • 2507.19804 • Published • 12
Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval
Paper • 2509.09118 • Published • 8
UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
Paper • 2510.13515 • Published • 12
ORID: Organ-Regional Information Driven Framework for Radiology Report Generation
Paper • 2411.13025 • Published • 2
luodian
authored 2
papers 7 months ago
xiangan
authored a
paper 7 months ago
luodian
authored a
paper 7 months ago