DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs Paper • 2503.07067 • Published 3 days ago • 26
Learning from Failures in Multi-Attempt Reinforcement Learning Paper • 2503.04808 • Published 9 days ago • 15
LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM Paper • 2503.04724 • Published 7 days ago • 58
Token-Efficient Long Video Understanding for Multimodal LLMs Paper • 2503.04130 • Published 7 days ago • 76
DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks Paper • 2502.17157 • Published 17 days ago • 51
The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve? Paper • 2502.17535 • Published 17 days ago • 8