26 citations · 39 across the 14 of their papers we have counts for
16 papers
WIRE: Weight Space Implicit Representation Encoding of Frozen Video LLMs
Ameen Ali, Tamim Zoabi, Lior Wolf +1
Video language models represent a video as a long sequence of visual embeddings in a decoder's input. Every visual embedding is processed by every decoder layer during prefill, sto…
Wiener Representation Filtering for VLM Hallucination Suppression
Ameen Ali, Tamim Zoabi, Lidor Brami +1
Vision-language models (VLMs) excel at open-ended captioning and visual QA but often describe objects, attributes, or relations absent from the image, a phenomenon known as object…
Mean-Field Parallel Decoding for Discrete Diffusion Language Models
Tamim Zoabi, Ameen Ali, Liran Ringel +1
Discrete diffusion language models enable parallel token generation, offering a pathway to low-latency decoding. However, selecting tokens independently by marginal confidence limi…
Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
Liran Ringel, Ameen Ali, Yaniv Romano
Discrete diffusion language models (dLLMs) accelerate text generation by unmasking multiple tokens in parallel. However, parallel decoding introduces a distributional mismatch: it…
Suppressing VLM Hallucinations with Spectral Representation Filtering
Ameen Ali, Tamim Zoabi, Lior Wolf
Vision-language models (VLMs) frequently produce hallucinations in the form of descriptions of objects, attributes, or relations that do not exist in the image due to over-reliance…
Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models
Ameen Ali, Shahar Katz, Lior Wolf +1
Large language models (LLMs) often develop learned mechanisms specialized to specific datasets, such as reliance on domain-specific correlations, which yield high-confidence predic…
Mitigating Copy Bias in In-Context Learning through Neuron Pruning
Ameen Ali, Lior Wolf, Ivan Titov
Large language models (LLMs) have demonstrated impressive few-shot in-context learning (ICL) abilities. Still, we show that they are sometimes prone to a `copying bias', where they…
Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation
Itamar Zimerman, Ameen Ali, Lior Wolf
Recent advances in efficient sequence modeling have led to attention-free layers, such as Mamba, RWKV, and various gated RNNs, all featuring sub-quadratic complexity in sequence le…
The Hidden Attention of Mamba Models
Ameen Ali, Itamar Zimerman, Lior Wolf
The Mamba layer offers an efficient selective state space model (SSM) that is highly effective in modeling multiple domains, including NLP, long-range sequence processing, and comp…
Degree-based stratification of nodes in Graph Neural Networks
Ameen Ali, Hakan Cevikalp, Lior Wolf
Despite much research, Graph Neural Networks (GNNs) still do not display the favorable scaling properties of other deep neural networks such as Convolutional Neural Networks and Tr…
Centered Self-Attention Layers
Ameen Ali, Tomer Galanti, Lior Wolf
The self-attention mechanism in transformers and the message-passing mechanism in graph neural networks are repeatedly applied within deep learning architectures. We show that this…
XAI for Transformers: Better Explanations through Conservative Propagation
Ameen Ali, Thomas Schnake, Oliver Eberle +3
Transformers have become an important workhorse of machine learning, with numerous applications. This necessitates the development of reliable methods for increasing their transpar…
Video and Text Matching with Conditioned Embeddings
Ameen Ali, Idan Schwartz, Tamir Hazan +1
We present a method for matching a text sentence from a given corpus to a given video clip and vice versa. Traditionally video and text matching is done by learning a shared embedd…
Explainability Guided Multi-Site COVID-19 CT Classification
Ameen Ali, Tal Shaharabany, Lior Wolf
Radiologist examination of chest CT is an effective way for screening COVID-19 cases. In this work, we overcome three challenges in the automation of this process: (i) the limited…
Weakly Supervised Recovery of Semantic Attributes
Ameen Ali, Tomer Galanti, Evgeniy Zheltonozhskiy +2
We consider the problem of the extraction of semantic attributes, supervised only with classification labels. For example, when learning to classify images of birds into species, w…
Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization
Shir Gur, Ameen Ali, Lior Wolf
Neural network visualization techniques mark image locations by their relevancy to the network's classification. Existing methods are effective in highlighting the regions that aff…