activity
20242026
collaborators

13 papers

cs.CL2026

Linguistically Informed Evaluation of Multilingual ASR for African Languages

Fei-Yueh Chen, Lateef Adeleke, C. M. Downey

Word Error Rate (WER) mischaracterizes ASR models' performance for African languages by combining phonological, tone, and other linguistic errors into a single lexical error. By co…

cs.LG2025

Edit Flows: Flow Matching with Edit Operations

Marton Havasi, Brian Karrer, Itai Gat +1

Autoregressive generative models naturally generate variable-length sequences, while non-autoregressive models struggle, often imposing rigid, token-wise structures. We propose Edi…

cs.LG2025

Set Block Decoding is a Language Model Inference Accelerator

Itai Gat, Heli Ben-Hamu, Marton Havasi +6

Autoregressive next token prediction language models offer powerful capabilities but face significant challenges in practical deployment due to the high computational and memory co…

cs.LG2025

Transition Matching: Scalable and Flexible Generative Modeling

Neta Shaul, Uriel Singer, Itai Gat +1

Diffusion and flow matching models have significantly advanced media generation, yet their design space is well-explored, somewhat limiting further improvements. Concurrently, auto…

cs.LG2025

Corrector Sampling in Language Models

Itai Gat, Neta Shaul, Uriel Singer +1

Autoregressive language models accumulate errors due to their fixed, irrevocable left-to-right token generation. To address this, we propose a new sampling method called Resample-P…

cs.LG2025

Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking

Heli Ben-Hamu, Itai Gat, Daniel Severo +2

Recent masked diffusion models (MDMs) have shown competitive performance compared to autoregressive models (ARMs) for language modeling. While most literature has focused on perfor…