Nikhil Bhendawade — accepted AI-conference papers

2026

FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models

Amin Karimi Monsefi, Nikhil Bhendawade, Manuel Rafael Ciosici, Dominic Culver, Yizhe Zhang, Irina Belousova

ICLR 2026poster

Autoregressive language models (ARMs) deliver strong likelihoods, but are inherently serial: they generate one token per forward pass, which limits throughput and inflates latency for long sequences. Diffusion Language Models (DLMs) parallelize across positions and thus appear promising for language…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention

Nikhil Bhendawade, Irina Belousova, Qichen Fu, Henry Mason, Antonie Lin, Mohammad Rastegari +1

EMNLP 2025

Speculative decoding is a prominent technique for accelerating LLM inference by leveraging an auxiliary draft model, but its effectiveness is limited by the autoregressive nature of draft generation, where acceptance rates depend on the draft model’s size. Scaling the draft model improves acceptance

Cited by 0 Source ↗PDF ↗Scholar ↗

2021

EL-Attention: Memory Efficient Lossless Attention for Generation

Yu Yan, Jiusheng Chen, Weizhen Qi, Nikhil Bhendawade, Yeyun Gong, Nan Duan +1

ICML 2021spotlight

Transformer model with multi-head attention requires caching intermediate results for efficient inference in generation tasks. However, cache brings new memory-related costs and prevents leveraging larger batch size for faster speed. We propose memory-efficient lossless attention (called EL-attentio…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗