Subham Sekhar Sahoo
s-sahoo
AI & ML interests
Diffusion Language Models
Recent Activity
new activity about 14 hours ago
IFM/K2-Horizon-7B:⚡ Up to 5.1x faster inference with DSpark speculative decoding (71 --> 364 tokens/sec) commentedon a paper 11 days ago
Unlocking Lossless Speedups in LLMs via Discrete Diffusion commentedon a paper 11 days ago
Unlocking Lossless Speedups in LLMs via Discrete DiffusionOrganizations
