Roi pony

Roi Pony, Adi Raz Goldfarb, Idan Friedman et al.

Late-interaction retrieval (ColBERT, ColPali) scores a query against a document with the MaxSim operator: for every query token, the maximum similarity over the document tokens, summed over query tokens. The standard implementation materializes the full query-token x document-token similarity tensor in GPU memory; for visual ColPali at 10K documents this tensor alone is 21 GB in FP16, created only to be reduced to one score per document and discarded. It exhausts a 40 GB GPU and bounds the achievable batch size in both inference and training. We present Flash-MaxSim, an IO-aware fused GPU kernel that computes exactly the same scores without ever materializing the tensor, by streaming query and document tiles through on-chip SRAM and folding the row-maximum reduction into the same pass. We extend the IO-aware principle through the training backward pass, an inverse-grid CSR construction that reuses the forward argmax for an atomic-free, destination-owned gradient reduction, and through INT8xINT8 quantization and variable-length (padding-free) scoring. Flash-MaxSim is up to 3.9x faster on an A100 (4.7x on an H100) than naive PyTorch at matched precision, uses up to 16x less inference memory and ~28x less training memory, unlocks corpus and batch sizes that exhaust PyTorch entirely, preserves the exact ranking (100% top-20 agreement with an FP32 reference)

Roi Pony, Adi Raz Goldfarb, Oshri Naparstek et al.

Multi-vector late-interaction retrievers such as ColBERT achieve state-of-the-art quality, but their query-time cost is dominated by exhaustively computing token-level MaxSim interactions for every candidate document. The MaxSim scores of $N$ candidates against $T$ query tokens form an $N\times T$ matrix whose row-sums are the late-interaction scores, and identifying the top-$K$ rarely requires every entry. We introduce Col-Bandit, a query-time estimator of the exhaustive-MaxSim top-$K$: it reveals matrix entries in batches, maintains a finite-population Bernstein-Serfling confidence interval on each candidate's score, and permanently drops any document whose upper bound falls below the $K$-th largest lower bound, computing only the cells needed to separate the top-$K$. A single relaxation knob $α_{\mathrm{ef}}\in(0,1]$ tunes the compute-fidelity trade-off. We deploy $α_{\mathrm{ef}}{=}0.2$, while $α_{\mathrm{ef}}{=}1$ admits a $δ$-PAC guarantee under a simplified radius. On BEIR and REAL-MM-RAG, Col-Bandit preserves $\geq 90\%$ fidelity to the exhaustive top-$5$ on every corpus while cutting MaxSim FLOPs by up to ${\sim}8\times$, for up to ${\sim}13\times$ single-thread CPU speedups across x86 and ARM. A drop-in reranking layer, it needs no retraining or index changes.

Omri Uzan, Asaf Yehudai, Roi pony et al.

Multimodal encoders have pushed the boundaries of visual document retrieval, matching textual query tokens directly to image patches and achieving state-of-the-art performance on public benchmarks. Recent models relying on this paradigm have massively scaled the sizes of their query and document representations, presenting obstacles to deployment and scalability in real-world pipelines. Furthermore, purely vision-centric approaches may be constrained by the inherent modality gap still exhibited by modern vision-language models. In this work, we connect these challenges to the paradigm of hybrid retrieval, investigating whether a lightweight dense text retriever can enhance a stronger vision-centric model. Existing hybrid methods, which rely on coarse-grained fusion of ranks or scores, fail to exploit the rich interactions within each model's representation space. To address this, we introduce Guided Query Refinement (GQR), a novel test-time optimization method that refines a primary retriever's query embedding using guidance from a complementary retriever's scores. Through extensive experiments on visual document retrieval benchmarks, we demonstrate that GQR allows vision-centric models to match the performance of models with significantly larger representations, while being up to 14x faster and requiring 54x less memory. Our findings show that GQR effectively pushes the Pareto frontier for performance and efficiency in multimodal retrieval. We release our code at https://github.com/IBM/test-time-hybrid-retrieval

Navve Wasserman, Roi Pony, Oshri Naparstek et al.

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 design. We introduce REAL-MM-RAG, an automatically generated benchmark designed to address four key properties essential for real-world retrieval: (i) multi-modal documents, (ii) enhanced difficulty, (iii) Realistic-RAG queries and (iv) accurate labeling. Additionally, we propose a multi-difficulty-level scheme based on query rephrasing to evaluate models' semantic understanding beyond keyword matching. Our benchmark reveals significant model weaknesses, particularly in handling table-heavy documents and robustness to query rephrasing. To mitigate these shortcomings, we curate a rephrased training set and introduce a new finance-focused, table-heavy dataset. Fine-tuning on these datasets enables models to achieve state-of-the-art retrieval performance on REAL-MM-RAG benchmark. Our work offers a better way to evaluate and improve retrieval in multi-modal RAG systems while also providing training data and models that address current limitations.

Oshri Naparstek, Roi Pony, Inbar Shapira et al.

In recent years, the challenge of extracting information from business documents has emerged as a critical task, finding applications across numerous domains. This effort has attracted substantial interest from both industry and academy, highlighting its significance in the current technological landscape. Most datasets in this area are primarily focused on Key Information Extraction (KIE), where the extraction process revolves around extracting information using a specific, predefined set of keys. Unlike most existing datasets and benchmarks, our focus is on discovering key-value pairs (KVPs) without relying on predefined keys, navigating through an array of diverse templates and complex layouts. This task presents unique challenges, primarily due to the absence of comprehensive datasets and benchmarks tailored for non-predetermined KVP extraction. To address this gap, we introduce KVP10k , a new dataset and benchmark specifically designed for KVP extraction. The dataset contains 10707 richly annotated images. In our benchmark, we also introduce a new challenging task that combines elements of KIE as well as KVP in a single task. KVP10k sets itself apart with its extensive diversity in data and richly detailed annotations, paving the way for advancements in the field of information extraction from complex business documents.

Roi Pony, Itay Naeh, Shie Mannor

Deep neural networks for video classification, just like image classification networks, may be subjected to adversarial manipulation. The main difference between image classifiers and video classifiers is that the latter usually use temporal information contained within the video. In this work we present a manipulation scheme for fooling video classifiers by introducing a flickering temporal perturbation that in some cases may be unnoticeable by human observers and is implementable in the real world. After demonstrating the manipulation of action classification of single videos, we generalize the procedure to make universal adversarial perturbation, achieving high fooling ratio. In addition, we generalize the universal perturbation and produce a temporal-invariant perturbation, which can be applied to the video without synchronizing the perturbation to the input. The attack was implemented on several target models and the transferability of the attack was demonstrated. These properties allow us to bridge the gap between simulated environment and real-world application, as will be demonstrated in this paper for the first time for an over-the-air flickering attack.