Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models
Paper • 2610.31198 • Published • 22
shahaf w
shahafw
AI & ML interests
None yet
Recent Activity
upvoted a paper 23 days ago
VEDJE: Video-Efficient Discriminative Joint Encoder for Scalable Video-Text Retrieval updated a model 10 months ago
shahafw/edje-vl-image-retrieval-rerankerOrganizations
None yet