Moshe Berchansky
Publication record assembled from the DBLP archive of ranked conferences.
Papers indexed
5
Venues
3
Active years
2021–2025
Best venue rank
A*
Where they publish
Papers
5 indexed papers, newest first.
| Year | Venue | Title | Authors |
|---|---|---|---|
| 2025 | ICLR | Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference. | Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky, Oren Pereg, Moshe Wasserblat, Tomer Galanti, Michal Gordon-Kiwkowitz, David Harel |
| 2025 | ICML | Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies. | Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky, Gaurav Jain, Oren Pereg, Moshe Wasserblat, David Harel |
| 2024 | EMNLP | CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity. | Moshe Berchansky, Daniel Fleischer, Moshe Wasserblat, Peter Izsak |
| 2023 | EMNLP | Optimizing Retrieval-augmented Reader Models via Token Elimination. | Moshe Berchansky, Peter Izsak, Avi Caciularu, Ido Dagan, Moshe Wasserblat |
| 2021 | EMNLP | How to Train BERT with an Academic Budget. | Peter Izsak, Moshe Berchansky, Omer Levy |