VAMR: Multi-Question Agentic Reasoning for Efficient Long-Form Video Understanding
Research
Research News
New papers, breakthroughs and academic AI research
IntactWorld: Joint World Modeling with Intact Features
Research
Does Modern Standard Arabic (MSA) Dominate Arabic Dialects in LLMs? A Representation-Level Analysis
Research
Multimodal Remote Sensing Image Registration: A Comprehensive Review, Challenges and Prospects
Research
When Can You Prune Your Network? A Study of Intermediate Neurons in Multilingual Speech Parsing
Research
MATE4D: Matrix-Guided Editable 4D Generation from a Single Image
Research
Prosody-to-Text: Predicting text from low-pass filtered speech
Research
WorldFact-Bench: Beyond Image-Internal Plausibility to Image-World Consistency
Research
Intervention anchors and scientific verification in synthetic vascular predictive representations
Research
SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction
Research
RGBD-to-3D Object Mesh Refinement via Depth Matching and Symmetry Propagation
Research
Dissecting Representation Structure in Vision Transformers: A Rigorous Architectural Study
Research