5 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…
Hamiltonian JEPA: Action-Conditioned World Models with an Inherited Control State
Tamim Zoabi, Ameen Ali, Lior Wolf
Planning from pixels needs more than a latent space that is stable and predictable. The state the planner scores must also be organized by how actions move the system. Joint-embedd…
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…
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…
Deep Active Speech Cancellation with Mamba-Masking Network
Yehuda Mishaly, Lior Wolf, Eliya Nachmani
We present a novel deep learning network for Active Speech Cancellation (ASC), advancing beyond Active Noise Cancellation (ANC) methods by effectively canceling both noise and spee…