arXiv Computer Vision August 27, 2026 By Xiaolong Wang, Lixiang Ru, Ziyuan Huang, Kaixiang Ji, Dandan Zheng, Jingdong Chen, Jun Zhou

ARGenSeg: Image Segmentation with Autoregressive Image Generation Model

Read the original on arXiv Computer Vision →

ARGenSeg introduces an autoregressive generation-based approach for image segmentation that integrates seamlessly with multimodal large language models (MLLMs). Unlike prior methods that use boundary points or dedicated segmentation heads, ARGenSeg generates dense masks directly through visual token output and detokenization via a universal VQ‑VAE, enabling fine‑grained pixel‑level perception. The framework employs a next‑scale‑prediction strategy to parallelize token generation, resulting in faster inference while outperforming state‑of‑the‑art segmentation models on multiple datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Jun 2

DenseMLLM: Standard Multimodal LLMs for Dense Prediction

arXiv:2602. 14134v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in high-level visual understanding.

By Yi Li, Hongze Shen, Lexiang Tang, Xin Li, Xinpeng Ding, Yinsong Liu, Deqiang Jiang, Xing Sun, Xiaomeng Li

llms computer-vision multimodal benchmarks

arXiv Computation and Language

1d ago

Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models

arXiv:2608.26580v1 Announce Type: cross Abstract: Diffusion multimodal large language models (dMLLMs) have recently emerged as a new decoding paradigm for multimodal generation. Starting from a fully...

By Insu Lee, Wooje Park, Wonseok Shin, Jinwoo Son, Byonghyo Shim

llms diffusion multimodal benchmarks

arXiv AI

Jun 26

Semantic Generative Tuning for Unified Multimodal Models

arXiv:2605. 18714v2 Announce Type: replace-cross Abstract: Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture.

By Songsong Yu, Yuxin Chen, Ying Shan, Yanwei Li

computer-vision multimodal benchmarks

arXiv AI

Jun 2

An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation

arXiv:2606. 00987v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have shown strong visual understanding and language-guided grounding abilities, yet their capacity for multi-temporal visual reasoning remains underexplored.

By Bingyu Li, Da Zhang, Tao Huo, Zhiyuan Zhao, Junyu Gao, Xuelong Li

llms agents computer-vision fine-tuning multimodal benchmarks

Hugging Face Trending Papers

Jul 7

Vision as Unified Multimodal Generation

We formulate computer vision as unified multimodal generation, where heterogeneous visual tasks are expressed in the native text and image generation spaces of a unified multimodal model, without task-specific architectures. Under this formulation, SenseNova-Vision uses natural-language instructions and optional visual prompts to specify tasks, target regions or views, and decoding conventions, and generates responses as text for symbolic outputs, images for dense spatial predictions, or mixed text-and-image outputs for compositional tasks.

diffusion computer-vision multimodal

Hugging Face Trending Papers

Jul 7

Segmentation before Answering: Pixel Grounding for MLLM Visual Reasoning

Recent advancements in Multimodal Large Language Models (MLLMs) have evolved from static perception to interleaved visual-language reasoning, often referred to as ``thinking with images''. A basic operation in this reasoning process is to zoom in on regions of interest (often represented with bounding boxes) to acquire finer visual details.

llms rag computer-vision multimodal benchmarks safety

One email a morning, machine-written

Related stories

DenseMLLM: Standard Multimodal LLMs for Dense Prediction

Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models

Semantic Generative Tuning for Unified Multimodal Models

An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation

Vision as Unified Multimodal Generation

Segmentation before Answering: Pixel Grounding for MLLM Visual Reasoning