ICLR

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

This repo contains images for Test-time Robust Personalization for Federated Learning (ICLR 2023)

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without lossing end-to-end metrics across language, image, and video models.

My solution and code for 2020 ICLR Workshop Challenge #2

[ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training

[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

liquid-fixpoint Language.Fixpoint.Solver.PLE