← Search

Irina Belousova

2 accepted papers

2026

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

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 0SourcecodeScholar
2025

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

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 0SourcePDFScholar