Towards Pixel-Level VLM Perception via Simple Points Prediction
Paper
• 2601.19228 • Published
• 18
MLLM
-
-
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
Paper • 2601.19895 • Published • 25 -
Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision
Paper • 2601.19798 • Published • 42 -
OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models
Paper • 2601.21639 • Published • 50 -
PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
Paper • 2601.21957 • Published • 19 -
CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
Paper • 2602.01785 • Published • 95 -
WorldVQA: Measuring Atomic World Knowledge in Multimodal Large Language Models
Paper • 2602.02537 • Published • 6 -
STEM: Scaling Transformers with Embedding Modules
Paper • 2601.10639 • Published • 2 -
SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?
Paper • 2602.03916 • Published • 11 -
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
Paper • 2601.15876 • Published • 91 -
MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
Paper • 2601.21821 • Published • 60 -
Agentic Very Long Video Understanding
Paper • 2601.18157 • Published • 19 -
P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads
Paper • 2602.09443 • Published • 57 -
MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation
Paper • 2602.11337 • Published • 6 -
Code2World: A GUI World Model via Renderable Code Generation
Paper • 2602.09856 • Published • 200