Moshe Berchansky
5 papers · 2021–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
Top co-authors
Research topics
Artificial Intelligence
(4)
Machine Learning
(4)
Natural Language Processing
(4)
Application Areas
(4)
Core AI
(4)
Applications
(3)
Deep Learning
(2)
Learning Types · Deep Learning
(2)
Generation
(1)
Learning Types · Machine Learning
(1)
Models
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Resources & Methods
(1)
Keywords
large language model
(2)
question answering
(2)
chain-of-thought reasoning
(1)
masked language model
(1)
efficient computing
(1)
distributed computing
(1)
computational efficiency
(1)
hyperparameter tuning
(1)
inference optimization
(1)
retrieval-augmented generation
(1)
speculative decoding
(1)
model efficiency
(1)
language model pretraining
(1)
decoder optimization
(1)
bert pretraining
(1)
vocabulary alignment
(1)
target model
(1)
token elimination
(1)
passage pruning
(1)
speculative inference
(1)
Papers
Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies
ICML 2025
Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference
ICLR 2025
CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity
EMNLP 2024
Optimizing Retrieval-augmented Reader Models via Token Elimination
EMNLP 2023
How to Train BERT with an Academic Budget
EMNLP 2021