12 citations · 14 across the 10 of their papers we have counts for
14 papers
LLM Evolutionary Search Strategies Should be Compared by Tokens
Tal Oved, Roi Pony, Oshri Naparstek +1
LLM evolutionary search is currently evaluated by counting proposals (candidate programs). We demonstrate this metric hides the true cost of search, and redo the comparison using t…
Spotlights: Discovering Improvement Opportunities in Software Repositories
Udi Barzelay, Ophir Azulai, Idan Friedman +9
Coding agents and evolutionary code-search systems can improve implementations once a target and evaluation criterion have been specified. Applying these methods to an existing sof…
Evolution or Illusion? Rethinking Evaluation in LLM Evolutionary Search
Tal Oved, Roi Pony, Oshri Naparstek +1
LLM-driven evolutionary search finds programs by launching seeds and iterating each one. Papers report a single budget setting, usually one seed run for a fixed number of iteration…
Optimize Cheap, Deploy Strong: Cost-Aware Cross-Tier Transfer for Evolutionary Optimization
Tal Oved, Roi Pony, Oshri Naparstek +1
Evolutionary optimization of LLM prompts and agentic programs (e.g., GEPA) is dominated by fitness evaluation: scoring each candidate runs an answering LLM over a validation set, s…
FLASH-MAXSIM: IO-Aware Fused Kernels for Late-Interaction Retrieval
Roi Pony, Daniel Ezer, Adi Raz Goldfarb +3
Late-interaction retrieval (ColBERT, ColPali) scores a query against a document via the MaxSim operator. The standard PyTorch implementation materialises the full query-token $\tim…
Is the Modality Gap a Bug or a Feature? A Robustness Perspective
Rhea Chowers, Oshri Naparstek, Udi Barzelay +1
Many modern multi-modal models (e.g. CLIP) seek an embedding space in which the two modalities are aligned. Somewhat surprisingly, almost all existing models show a strong modality…
VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents
Udi Barzelay, Ophir Azulai, Inbar Shapira +4
We introduce VAREX (VARied-schema EXtraction), a benchmark for evaluating multimodal foundation models on structured data extraction from government forms. VAREX employs a Reverse…
Col-Bandit: Query-Time Top- Estimation for Late-Interaction Retrieval
Roi Pony, Adi Raz Goldfarb, Oshri Naparstek +3
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 inter…
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…
Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence
Granite Vision Team, Leonid Karlinsky, Assaf Arbelle +60
We introduce Granite Vision, a lightweight large language model with vision capabilities, specifically designed to excel in enterprise use cases, particularly in visual document un…
KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business Documents
Oshri Naparstek, Roi Pony, Inbar Shapira +15
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 attra…
BusiNet -- a Light and Fast Text Detection Network for Business Documents
Oshri Naparstek, Ophir Azulai, Daniel Rotman +3
For digitizing or indexing physical documents, Optical Character Recognition (OCR), the process of extracting textual information from scanned documents, is a vital technology. Whe…
Learnable Optimal Sequential Grouping for Video Scene Detection
Daniel Rotman, Yevgeny Yaroker, Elad Amrani +2
Video scene detection is the task of dividing videos into temporal semantic chapters. This is an important preliminary step before attempting to analyze heterogeneous video content…
TAEN: Temporal Aware Embedding Network for Few-Shot Action Recognition
Rami Ben-Ari, Mor Shpigel, Ophir Azulai +2
Classification of new class entities requires collecting and annotating hundreds or thousands of samples that is often prohibitively costly. Few-shot learning suggests learning to…