2 citations · 2 across the 12 of their papers we have counts for
15 papers
Phonological Interference in Multilingual Speech Models
Moran Yanuka, Raja Giryes, Morris Alper +1
Phoneme-level models transcribe or generate speech as a sequence of phonemes, the smallest sound units that distinguish words. These models enable fine-grained pronunciation contro…
Local Support Learning
Assaf Ben-Kish, Akarsh Kumar, James Glass +1
We explore catastrophic forgetting in the context of large pre-trained models. By considering forgetting as a geometric problem in the input space of each weight matrix, we uncover…
On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing
Yuval Koren, Assaf Ben-Kish, Raja Giryes +2
Associative Recall (AR) is the cognitive ability to learn and retrieve links between items in memory. In NLP, AR is used as a benchmark for evaluating the in-context memory capacit…
Entropy-Preserving Reinforcement Learning
Aleksei Petrenko, Ben Lipkin, Kevin Chen +4
Policy gradient algorithms have driven many recent advancements in language model reasoning. An appealing property is their ability to learn from exploration on their own trajector…
Principled Coarse-Grained Acceptance for Speculative Decoding in Speech
Moran Yanuka, Paul Dixon, Eyal Finkelshtein +2
Speculative decoding accelerates autoregressive speech generation by letting a fast draft model propose tokens that a larger target model verifies. However, for speech LLMs that ge…
ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline
Morris Alper, Moran Yanuka, Raja Giryes +1
Constructed languages (conlangs) such as Esperanto and Quenya have played diverse roles in art, philosophy, and international communication. Meanwhile, foundation models have revol…
Mamba Knockout for Unraveling Factual Information Flow
Nir Endy, Idan Daniel Grosbard, Yuval Ran-Milo +3
This paper investigates the flow of factual information in Mamba State-Space Model (SSM)-based language models. We rely on theoretical and empirical connections to Transformer-base…
Performance Gap in Entity Knowledge Extraction Across Modalities in Vision Language Models
Ido Cohen, Daniela Gottesman, Mor Geva +1
Vision-language models (VLMs) excel at extracting and reasoning about information from images. Yet, their capacity to leverage internal knowledge about specific entities remains un…
Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions
Moran Yanuka, Assaf Ben Kish, Yonatan Bitton +2
Recent research increasingly focuses on training vision-language models (VLMs) with long, detailed image captions. However, small-scale VLMs often struggle to balance the richness…
Provable Benefits of Complex Parameterizations for Structured State Space Models
Yuval Ran-Milo, Eden Lumbroso, Edo Cohen-Karlik +3
Structured state space models (SSMs), the core engine behind prominent neural networks such as S4 and Mamba, are linear dynamical systems adhering to a specified structure, most no…
DeciMamba: Exploring the Length Extrapolation Potential of Mamba
Assaf Ben-Kish, Itamar Zimerman, Shady Abu-Hussein +4
Long-range sequence processing poses a significant challenge for Transformers due to their quadratic complexity in input length. A promising alternative is Mamba, which demonstrate…
ICC: Quantifying Image Caption Concreteness for Multimodal Dataset Curation
Moran Yanuka, Morris Alper, Hadar Averbuch-Elor +1
Web-scale training on paired text-image data is becoming increasingly central to multimodal learning, but is challenged by the highly noisy nature of datasets in the wild. Standard…
Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States
Noam Razin, Yotam Alexander, Edo Cohen-Karlik +3
In modern machine learning, models can often fit training data in numerous ways, some of which perform well on unseen (test) data, while others do not. Remarkably, in such cases gr…
Mitigating Open-Vocabulary Caption Hallucinations
Assaf Ben-Kish, Moran Yanuka, Morris Alper +2
While recent years have seen rapid progress in image-conditioned text generation, image captioning still suffers from the fundamental issue of hallucinations, namely, the generatio…
TOP-GAN: Label-Free Cancer Cell Classification Using Deep Learning with a Small Training Set
Moran Rubin, Omer Stein, Nir A. Turko +6
We propose a new deep learning approach for medical imaging that copes with the problem of a small training set, the main bottleneck of deep learning, and apply it for classificati…