ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule
Research
Research News
New papers, breakthroughs and academic AI research
A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss
Research
Conformal Factuality Control for Multi-Hop Retrieval-Augmented Generation
Research
Generative AI Purpose-built for Social and Mental Health: A Real-World Pilot
Research
Functional Subspace, where language models can use vector algebra to solve problems
Research
A Dynamical Theory of LoRA in Continual Learning
Research
Inference-Layer Security: Defending Against Adversarial Inference and Infrastructure Abuse
Research
EDGC: Entropy-driven Dynamic Gradient Compression for Efficient LLM Training
Research
DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes
Research
Reasoning with Sampling: Cutting at Decision Points
Research
CoVisco: Codec-Native Vision Encoder with Native Token Compression for Unified Image-Video Understanding
Research
Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective
Research