The Year in AI Papers
The year/Topics/Vision-language models

Research collection

Vision-language models

Multimodal LLM architecture and training: unified understanding and generation, visual representation alignment, and general-purpose VLM technical reports.

Papers
65
Research labs
5
Official code
52

51–65 of 65 papers in this collection

51

arXiv.org

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation

The paper introduces Puffin, a unified multimodal model that jointly performs camera-centric understanding and generation. It treats camera parameters as a first-class modality, introducing 'thinking with camera' to align spatially grounded visual cues with professional photographic terms. Puffin integrates language regression and diffusion-based…

Kang Liao, Size Wu, Zhonghua Wu, Linyi Jin, et al.
Published
Oct 2025
Citations
15
Code
420 stars
Read summary Original
52

arXiv.org

UniVideo: Unified Understanding, Generation, and Editing for Videos

UniVideo is a unified multimodal framework for video understanding, generation, and editing, presented at ICLR 2026. It uses a dual-stream architecture combining a frozen Multimodal Large Language Model (MLLM, Qwen2.5VL-7B) for understanding and a Multimodal DiT (MMDiT, HunyuanVideo-T2V-13B) for generation, connected via a trainable MLP connector. This…

Cong Wei, Quande Liu, Zixuan Ye, Qiulin Wang, et al.
Published
Oct 2025
Citations
68
Code
546 stars
Read summary Original
53

arXiv.org

Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer

Ming-UniVision introduces MingTok, a continuous visual tokenizer with a three-stage architecture (low-level encoder, semantic decoder, pixel decoder) that unifies image understanding and generation in a single autoregressive framework. Unlike discrete tokenizers, MingTok avoids quantization errors, balancing compact latents for generation with…

Ziyuan Huang, DanDan Zheng, Cheng Zou, Rui Liu, et al.
Published
Oct 2025
Citations
26
Code
143 stars
Read summary Original
54

arXiv.org

Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding

Lumina-DiMOO is an open-source, 8B-parameter unified multi-modal model based on a fully discrete diffusion architecture, built on the LLaDA-Base dLLM. It supports text-to-image generation at arbitrary resolutions, image-to-image tasks (editing, style transfer, subject-driven, controllable, multi-view), and image understanding. The model uses a unified…

Yi Xin, Qi Qin, Siqi Luo, Kaiwen Zhu, et al.
Published
Oct 2025
Citations
87
Code
1K stars
Read summary Original
55

arXiv.org

Apriel-1.5-15b-Thinker

Apriel-1.5-15B-Thinker is a 15-billion-parameter open-weights multimodal reasoning model developed by ServiceNow's SLAM Lab. It achieves frontier-level performance through a data-centric mid-training approach rather than scale, starting from Pixtral-12B. The methodology involves three stages: depth upscaling to expand reasoning capacity, staged continual…

Shruthan Radhakrishna, Aman Tiwari, Aanjaneya Shukla, Masoud Hashemi, et al.
Published
Oct 2025
Citations
2
Code
Not linked
Read summary Original
56

Qwen

Qwen3-Omni Technical Report

Qwen3-Omni is a single multimodal model that achieves state-of-the-art performance across text, image, audio, and video without degradation relative to single-modal counterparts. It matches the performance of same-sized Qwen single-modal models and excels on audio tasks, achieving open-source SOTA on 32 of 36 audio benchmarks and overall SOTA on 22,…

Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu, et al.
Published
Sep 2025
Citations
405
Code
3.9K stars
Read summary Original
57

arXiv.org

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

Manzano is a unified multimodal LLM that integrates image understanding and generation using a hybrid vision tokenizer. A single shared vision encoder feeds two lightweight adapters: a continuous adapter for understanding tasks and a discrete adapter (using FSQ with a 64K codebook) for generation, producing tokens in a common semantic space. A unified…

Yanghao Li, Rui Qian, Bowen Pan, Haotian Zhang, et al.
Published
Sep 2025
Citations
15
Code
Not linked
Read summary Original
58

arXiv.org

MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

MiniCPM-V 4.5 is an 8B-parameter multimodal large language model (MLLM) designed for high efficiency and strong performance. It introduces three core improvements: a unified 3D-Resampler architecture that compresses images and videos into compact token sequences (up to 16x for images and an additional 6x for videos), a unified learning paradigm for…

Tianyu Yu, Zefan Wang, Chongyi Wang, Fuwei Huang, et al.
Published
Sep 2025
Citations
124
Code
26K stars
Read summary Original
59

arXiv.org

Visual Representation Alignment for Multimodal Large Language Models

Multimodal large language models (MLLMs) trained with visual instruction tuning underperform on vision-centric tasks like object counting and spatial reasoning. The authors attribute this to text-only supervision, which provides indirect guidance for the visual pathway, causing MLLMs to discard fine-grained visual details from the vision encoder. They…

Heeji Yoon, Jaewoo Jung, Junwan Kim, Hyungyu Choi, et al.
Published
Sep 2025
Citations
35
Code
162 stars
Read summary Original
60

arXiv.org

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

InternVL3.5 is a new family of open-source multimodal models that improves versatility, reasoning, and efficiency over its predecessor InternVL3. Key innovations include Cascade Reinforcement Learning (Cascade RL), which combines offline RL (MPO) for stable convergence and online RL (GSPO) for refined alignment, boosting reasoning performance by up to…

Weiyun Wang, Zhangwei Gao, Lixin Gu, Hengjun Pu, et al.
Published
Aug 2025
Citations
1.2K
Code
Not linked
Read summary Original
61

Independent research

Intern-S1: A Scientific Multimodal Foundation Model

Intern-S1 is a multimodal Mixture-of-Experts (MoE) foundation model with 28 billion activated parameters (241B total), designed to bridge the gap between open-source and closed-source models in scientific domains. It was continually pre-trained on 5T tokens, including over 2.5T scientific tokens, using pipelines for PDF parsing, domain-centric web data,…

Lei Bai, Zhongrui Cai, Yuhang Cao, Maosong Cao, et al.
Published
Aug 2025
Citations
13
Code
842 stars
Read summary Original
62

arXiv.org

Thyme: Think Beyond Images

The paper introduces Thyme (Think Beyond Images), a paradigm for multimodal large language models (MLLMs) that autonomously generates and executes code for image manipulations (cropping, rotation, contrast enhancement) and complex computations, going beyond existing 'think with images' approaches. Thyme uses a two-stage training: Supervised Fine-Tuning…

Yi-Fan Zhang, Xingyu Lu, Shukang Yin, Chaoyou Fu, et al.
Published
Aug 2025
Citations
119
Code
586 stars
Read summary Original
63

arXiv.org

Ovis2.5 Technical Report

Ovis2.5 is a multimodal large language model from Alibaba Group, succeeding Ovis2. It introduces native-resolution visual perception using a NaViT vision transformer, which processes images at their original resolutions to preserve fine details and global layout, crucial for complex charts. The model also adds an optional 'thinking mode' for deep…

Shiyin Lu, Yang Li, Yu Xia, Yuwei Hu, et al.
Published
Aug 2025
Citations
81
Code
1.5K stars
Read summary Original
64

Meta AI

DINOv3

DINOv3 is a self-supervised vision foundation model that scales to 7B parameters, trained on a curated dataset of 1.689 billion images (LVD-1689M) from Instagram, combined with ImageNet-1k. The model uses a ViT architecture with RoPE embeddings and constant hyperparameter schedules. A key contribution is Gram anchoring, a regularization technique that…

Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, et al.
Published
Aug 2025
Citations
1.2K
Code
11K stars
Read summary Original
65

arXiv.org

Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation

Skywork UniPic is a 1.5B-parameter autoregressive model that unifies image understanding, text-to-image generation, and image editing in a single architecture without task-specific adapters. It achieves a GenEval score of 0.86, a DPG-Bench score of 85.5, and GEditBench-EN and ImgEdit-Bench scores of 5.83 and 3.49, respectively, while generating 1024x1024…

Peiyu Wang, Yi Peng, Yimeng Gan, Liang Hu, et al.
Published
Aug 2025
Citations
17
Code
871 stars
Read summary Original