71 citations · 90 across the 10 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
OASIS: Online Activation Subspace Learning for Memory-Efficient Training
Sakshi Choudhary, Utkarsh Saxena, Kaushik Roy
Training large language models (LLMs) is constrained by memory requirements, with activations accounting for a substantial fraction of the total footprint. Existing approaches redu…
cs.CV2026
DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking
Akash Haridas, Utkarsh Saxena, Parsa Ashrafi Fashi +3
Diffusion Transformers rely on static patchify tokenization, assigning the same token budget to smooth backgrounds, detailed object regions, noisy early timesteps, and late-stage r…