Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models Paper • 2610.31198 • Published 16 days ago • 22
Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models Paper • 2602.02600 • Published Feb 1 • 15
On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction Paper • 2610.22543 • Published 12 days ago • 29
Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models Paper • 2610.31198 • Published 16 days ago • 22
VEDJE: Video-Efficient Discriminative Joint Encoder for Scalable Video-Text Retrieval Paper • 2610.11850 • Published 26 days ago • 34
Breaking the Bubble: Asynchronous Pipeline Parallel Training with Bounded Weight Inconsistency Paper • 2606.07881 • Published Jun 5 • 8