6 citations · 6 across the 12 of their papers we have counts for
13 papers
RIFT: KV Cache Compression for Draft Models with Complementary Compressibility Training
Dor Tsur, Maor Ashkenazi, Maximilian Golub +7
Speculative decoding is a popular decode acceleration method. As such, it is particularly relevant to long-output generation, which requires an increasingly large KV cache. KV cach…
Task-Centric Acceleration of Small-Language Models
Dor Tsur, Sharon Adar, Ran Levy
Small language models (SLMs) have emerged as efficient alternatives to large language models for task-specific applications. However, they are often employed in high-volume, low-la…
Directed Information: Estimation, Optimization and Applications in Communications and Causality
Dor Tsur, Oron Sabag, Navin Kashyap +2
Directed information (DI) is an information measure that attempts to capture directionality in the flow of information from one random process to another. It is closely related to…
HeavyWater and SimplexWater: Distortion-Free LLM Watermarks for Low-Entropy Next-Token Predictions
Dor Tsur, Carol Xuan Long, Claudio Mayrink Verdun +5
Large language model (LLM) watermarks enable authentication of text provenance, curb misuse of machine-generated text, and promote trust in AI systems. Current watermarks operate b…
Neural Estimation for Scaling Entropic Multimarginal Optimal Transport
Dor Tsur, Ziv Goldfeld, Kristjan Greenewald +1
Multimarginal optimal transport (MOT) is a powerful framework for modeling interactions between multiple distributions, yet its applicability is bottlenecked by a high computationa…
Optimized Couplings for Watermarking Large Language Models
Dor Tsur, Carol Xuan Long, Claudio Mayrink Verdun +3
Large-language models (LLMs) are now able to produce text that is, in many cases, seemingly indistinguishable from human-generated content. This has fueled the development of water…
Efficient Time Series Forecasting via Hyper-Complex Models and Frequency Aggregation
Eyal Yakir, Dor Tsur, Haim Permuter
Time series forecasting is a long-standing problem in statistics and machine learning. One of the key challenges is processing sequences with long-range dependencies. To that end,…
InfoMat: A Tool for the Analysis and Visualization Sequential Information Transfer
Dor Tsur, Haim Permuter
Despite the popularity of information measures in analysis of probabilistic systems, proper tools for their visualization are not common. This work develops a simple matrix represe…
TREET: TRansfer Entropy Estimation via Transformers
Omer Luxembourg, Dor Tsur, Haim Permuter
Transfer entropy (TE) is an information theoretic measure that reveals the directional flow of information between processes, providing valuable insights for a wide range of real-w…
Max-Sliced Mutual Information
Dor Tsur, Ziv Goldfeld, Kristjan Greenewald
Quantifying the dependence between high-dimensional random variables is central to statistical learning and inference. Two classical methods are canonical correlation analysis (CCA…
Data-Driven Optimization of Directed Information over Discrete Alphabets
Dor Tsur, Ziv Aharoni, Ziv Goldfeld +1
Directed information (DI) is a fundamental measure for the study and analysis of sequential stochastic models. In particular, when optimized over input distributions it characteriz…
Neural Estimation and Optimization of Directed Information over Continuous Spaces
Dor Tsur, Ziv Aharoni, Ziv Goldfeld +1
This work develops a new method for estimating and optimizing the directed information rate between two jointly stationary and ergodic stochastic processes. Building upon recent ad…
Capacity of Continuous Channels with Memory via Directed Information Neural Estimator
Ziv Aharoni, Dor Tsur, Ziv Goldfeld +1
Calculating the capacity (with or without feedback) of channels with memory and continuous alphabets is a challenging task. It requires optimizing the directed information (DI) rat…