This paper presents the benefits of visual pretraining for foundation model intelligence, outperforming text-only pretraining on multiple backbones and benchmarks.

This paper introduces SkMTEB, a comprehensive text embedding benchmark for Slovak, and develops efficient, locally-deployable Slovak embeddings.

The paper introduces TICoE, a text-image collaborative framework that achieves precise and faithful concept removal from text-to-image generative models, surpassing existing methods in both precision…

The paper introduces MLLM-Microscope, a system that analyzes the internal structure of multimodal large language models (MLLMs), finding that modality fusion significantly impacts the linearity and di…

The paper introduces GPIC, a massive, permissively licensed, and safety-filtered image corpus of 28 trillion pixels, designed to serve as a stable and accessible benchmark for large-scale visual gener…

This paper introduces a new benchmark dataset and evaluation framework for 'data snapshot extraction,' focusing on identifying and localizing semantically meaningful analytical artifacts within operat…

The paper presents SenseNova-Vision, a unified multimodal model for computer vision tasks using natural language instructions and optional visual prompts, trained primarily on a new corpus and requiri…

This paper proposes ReChannel, a method for dense prediction using a pretrained DiT model, which keeps the encoder but removes the decoder and adapts it with task LoRA. ReChannel maps each token to it…

This paper details the systematic construction and training of a high-performing Romanian Vision-Language Model (VLM), demonstrating that language-specific adaptation significantly boosts performance…

PromptEmbedder introduces a dual-LLM framework that efficiently and transferably adapts text embeddings by decoupling task-specific knowledge from the backbone model, significantly reducing computatio…

The paper introduces a new benchmark, E2V-Bench, to evaluate text-to-image models on generating pedagogically accurate visuals from arithmetic equations, finding that current models often fail due to…

The paper systematically compares multimodal transformer and LLM approaches for document type classification, finding that specialized multimodal Transformers outperform LLM-based models, especially w…

The paper introduces PMC-InterCPT, a refined biomedical interleaved corpus that enhances multimodal continued pretraining by integrating figure-referencing body text alongside captions, leading to imp…

This paper systematically analyzes combining dimensionality reduction and quantization to compress text embeddings, showing that this combined approach achieves substantial compression (e.g., 0.1% siz…

This paper introduces MM-IssueLoc, a benchmark and evaluation protocol for repository-level issue localization with visual evidence.

The paper introduces Dr. DocBench, a difficulty-aware, comprehensive benchmark designed to rigorously test expert-level and challenging document parsing capabilities for VLMs, demonstrating that curre…

The paper builds a benchmark to evaluate the ability of multimodal large language models to extract accurate data tables from chart images, and proposes a human-centered approach to improve numerical…

OctoT2I introduces a self-evolving, agentic routing framework that efficiently selects and combines multiple Text-to-Image models, achieving high performance while significantly boosting inference spe…

The paper proposes a novel global sketch-based watermarking technique for diffusion language models that controls the entire sequence's statistics, offering an order-agnostic and context-independent a…