Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores
Research
Research News
New papers, breakthroughs and academic AI research
TRACE: A Multi-Agent System for Autonomous Physical Reasoning for Seismology
Research
Principled Design of Diffusion-based Optimizers for Inverse Problems
Research
Capabilities Ain't All You Need: Measuring Propensities in AI
Research
Foundations without Fundamentals: Zero-Shot Blind Spots in Time Series FMs
Research
Beyond Localization: A Comprehensive Benchmark of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images
Research
Bridging the Sim-to-Real Gap with multipanda_ros2: A Real-Time ROS2 Framework for Multimanual Systems
Research
MedFeat: Model-Aware and Explainability-Driven Feature Engineering with LLMs for Tabular Prediction
Research
Learn the Directions, Normalize the Gains: Post-Training Normalization for LoRA
Research
SR-Ground: Image Quality Grounding for Super-Resolved Content
Research
Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models
Research
TensorCommitments: A Lightweight Verifiable Inference for Language Models
Research