"au:"Nikhil Bhendawade"" — arXiv2 Search

/ Date/ Name

/ Date/ Name

"au:"Nikhil Bhendawade"" — arXiv2 Search

Showing 1–9 of 9 results

/ Date/ Name

Oct 15, 2025Mirror Speculative Decoding: Breaking the Serial Barrier in LLM Inference Feb 16, 2024Speculative Streaming: Fast LLM Inference without Auxiliary Models Feb 4, 2025M2R2: Mixture of Multi-Rate Residuals for Efficient Transformer Inference May 11, 2021EL-Attention: Memory Efficient Lossless Attention for Generation Feb 25, 2026The Design Space of Tri-Modal Masked Diffusion Models Jun 8, 2021FastSeq: Make Sequence Generation Faster Jul 29, 2024Apple Intelligence Foundation Language Models Jul 17, 2025Apple Intelligence Foundation Language Models: Tech Report 2025 Sep 24, 2025FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models