7 papers
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…
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…