5 papers
Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer
Roman Beliy, Amit Zalcher, Jonathan Kogman +2
Reconstructing images seen by people from their fMRI brain recordings provides a non-invasive window into the human brain. Despite recent progress enabled by diffusion models, curr…
ImpMIA: Leveraging Implicit Bias for Membership Inference Attack
Yuval Golbari, Navve Wasserman, Gal Vardi +1
Determining which data samples were used to train a model, known as Membership Inference Attack (MIA), is a well-studied and important problem with implications on data privacy. So…
DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankers
Navve Wasserman, Oliver Heinimann, Yuval Golbari +3
Rerankers play a critical role in multimodal Retrieval-Augmented Generation (RAG) by refining ranking of an initial set of retrieved documents. Rerankers are typically trained usin…
Don't Judge Before You CLIP: A Unified Approach for Perceptual Tasks
Amit Zalcher, Navve Wasserman, Roman Beliy +2
Visual perceptual tasks aim to predict human judgment of images (e.g., emotions invoked by images, image quality assessment). Unlike objective tasks such as object/scene recognitio…
REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark
Navve Wasserman, Roi Pony, Oshri Naparstek +4
Accurate multi-modal document retrieval is crucial for Retrieval-Augmented Generation (RAG), yet existing benchmarks do not fully capture real-world challenges with their current d…