Beyond Domain-Level Adaptation: Margin-Oriented Semantic-Appearance Interaction Correction for Personalized Federated Vision-Language Models
Research
Research News
New papers, breakthroughs and academic AI research
Rethinking Data Augmentation under Covariate Shift: Invariant-Guided Diffusion and Prototype Reweighting
Research
Match the Distribution, Not the Compute: Post-Training Multi-Token Prediction Heads
Research
Learning to Cover Locally: Graph Neural Combinatorial Optimization under a Hard Information Horizon
Research
Rethinking Memorization Mitigation in Diffusion Models: Reinforcing Text Conditioning
Research
Multi-agent Auditory Scene Analysis: Improved Localization Speed and Robustness by Multi-beamformed Speech Quality Feedback
Research
DeepJEPA: Scaling World Models from Within
Research
Cross-Benchmark Transfer from RL on Agentic Coding Tasks
Research
Code That Works, Environments That Don't: Measuring Environment Reproducibility in AI-Generated Software
Research
Not All Error Yields to Scale: Where Scaling Stops in Vision-Language Inference
Research
Do MLLM Judges Judge the Edit? Auditing Bias in Image Editing Evaluation with Verified Quality Preservation
Research
When Text-to-Image Helps Editing: The Effects of Conditioning During Denoising
Research