The Illusion of Replacement: Rethinking Specialized Machine Learning Models in the Foundation Model Era
Research
Research News
New papers, breakthroughs and academic AI research
Trust the Critic More
Research
Semantic Watermarking for Malicious Image Manipulation Detection
Research
BAM! Bayesian Anything Model: a foundation model for generative computational imaging
Research
Client and Training Data Selection for Computationally Efficient Synchronized Federated Learning
Research
RouteRec: Behavior-Guided Sparse Routing for Sequential Recommendation
Research
C-Instrument: Automating RL Data Generation and Hillclimbing with a Constitution-Grid Instrument
Research
Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus
Research
Jacobian Rank Collapse in Decision-Focused Learning
Research
JPO: Juris Policy Optimization for Structured Legal Reasoning in Criminal Judgment Prediction
Research
ExpandDiff: Dynamic Range Expanding Diffusion for Single-Image HDR Reconstruction
Research
Typographic Attack Against VLM-based AI-generated Image Detection
Research