Author name cluster

Xinyu Wei

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO

Chengzhuo Tong
Ziyu Guo
Renrui Zhang
Wenyu Shan
Xinyu Wei
Zhenghao Xing
Hongsheng Li
Pheng-Ann Heng

Recent advancements underscore the significant role of Reinforcement Learning (RL) in enhancing the Chain-of-Thought (CoT) reasoning capabilities of large language models (LLMs). Two prominent RL algorithms, Direct Preference Optimization (DPO) and Group Relative Policy Optimization (GRPO), are central to these developments, showcasing different pros and cons. Autoregressive image generation, also interpretable as a sequential CoT reasoning process, presents unique challenges distinct from LLM-based CoT reasoning. These encompass ensuring text-image consistency, improving image aesthetic quality, and designing sophisticated reward models, rather than relying on simpler rule-based rewards. While recent efforts have extended RL to this domain, these explorations typically lack an in-depth analysis of the domain-specific challenges and the characteristics of different RL strategies. To bridge this gap, we provide the first comprehensive investigation of the GRPO and DPO algorithms in autoregressive image generation, evaluating their in-domain performance and out-of-domain generalization, while scrutinizing the impact of different reward models on their respective capabilities. Our findings reveal that GRPO and DPO exhibit distinct advantages, and crucially, that reward models possessing stronger intrinsic generalization capabilities potentially enhance the generalization potential of the applied RL algorithms. Furthermore, we systematically explore three prevalent scaling strategies to enhance both their in-domain and out-of-domain proficiency, deriving unique insights into efficiently scaling performance for each paradigm. We hope our study paves a new path for inspiring future work on developing more effective RL algorithms to achieve robust CoT reasoning in the realm of autoregressive image generation.

PDF Details

ICLR Conference 2025 Conference Paper

Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want

Weifeng Lin
Xinyu Wei
Ruichuan An
Peng Gao 0007
Bocheng Zou
Yulin Luo
Siyuan Huang 0004
Shanghang Zhang

In this paper, we present the Draw-and-Understand framework, exploring how to integrate visual prompting understanding capabilities into Multimodal Large Language Models (MLLMs). Visual prompts allow users to interact through multi-modal instructions, enhancing the models' interactivity and fine-grained image comprehension. In this framework, we propose a general architecture adaptable to different pre-trained MLLMs, enabling it to recognize various types of visual prompts (such as points, bounding boxes, and free-form shapes) alongside language understanding. Additionally, we introduce MDVP-Instruct-Data, a multi-domain dataset featuring 1.2 million image-visual prompt-text triplets, including natural images, document images, scene text images, mobile/web screenshots, and remote sensing images. Building on this dataset, we introduce MDVP-Bench, a challenging benchmark designed to evaluate a model's ability to understand visual prompting instructions. The experimental results demonstrate that our framework can be easily and effectively applied to various MLLMs, such as SPHINX-X and LLaVA. After training with MDVP-Instruct-Data and image-level instruction datasets, our models exhibit impressive multimodal interaction capabilities and pixel-level understanding, while maintaining their image-level visual perception performance.

Details

AAAI Conference 2025 Conference Paper

Event2Tracking: Reconstructing Multi-Agent Soccer Trajectories Using Long-Term Multimodal Context

Harry Hughes
Michael Horton
Xinyu Wei
Harshala Gammulle
Clinton Fookes
Sridha Sridharan
Patrick Lucey

Soccer is a rich testbed for studying multi-agent adversarial systems. In this work we focus on the task of reconstructing the noisy trajectories of soccer agents (players and the ball). Previous works that model the behaviours of agents in soccer are limited in two respects: (i) they only focus on short-term context windows (less than or equal to 10 seconds) which are not suitable for reconstructing trajectories impacted by long-term noise, and (ii) they exclusively rely on trajectory context, and do not leverage soccer's auxiliary data streams that can provide additional context. Our Event2Tracking model addresses these limitations. First, our architecture models soccer's long-term structure by processing long-term trajectories (60 seconds in duration). Secondly, our architecture is multimodal. Specifically, it fuses soccer tracking data with event data (which specifies the high-level semantic events that transpire in a game), providing rich context that cannot strictly be inferred from the raw trajectories. We evaluate our method empirically using a reconstruction loss metric. Compared to state-of-the-art approaches, our method substantially improves the accuracy of the ball's and players' reconstructed trajectories.

PDF Details DOI

ICLR Conference 2025 Conference Paper

MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine

Renrui Zhang
Xinyu Wei
Dongzhi Jiang
Ziyu Guo
Yichi Zhang
Chengzhuo Tong
Jiaming Liu 0003
Aojun Zhou

Multi-modal Large Language Models (MLLMs) have recently showcased superior proficiency in general visual scenarios. However, we identify their mathematical capabilities remain under-explored with three areas to be improved: visual encoding of math diagrams, diagram-language alignment, and chain-of-thought (CoT) reasoning. This draws forth an urgent demand for an effective training paradigm and a large-scale, comprehensive dataset with detailed CoT rationales, which is challenging to collect and costly to annotate manually. To tackle this issue, we propose MAVIS, a MAthematical VISual instruction tuning pipeline for MLLMs, featuring an automatic data engine to efficiently create mathematical visual datasets. We design the data generation process to be entirely independent of human intervention or GPT API usage, while ensuring the diagram-caption correspondence, question-answer correctness, and CoT reasoning quality. With this approach, we curate two datasets, MAVIS-Caption (558K diagram-caption pairs) and MAVIS-Instruct (834K visual math problems with CoT rationales), and propose four progressive stages for training MLLMs from scratch. First, we utilize MAVIS-Caption to fine-tune a math-specific vision encoder (CLIP-Math) through contrastive learning, tailored for improved diagram visual encoding. Second, we also leverage MAVIS-Caption to align the CLIP-Math with a large language model (LLM) by a projection layer, enhancing vision-language alignment in mathematical domains. Third, we adopt MAVIS-Instruct to perform the instruction tuning for robust problem-solving skills, and term the resulting model as MAVIS-7B. Fourth, we apply Direct Preference Optimization (DPO) to enhance the CoT capabilities of our model, further refining its step-wise reasoning performance. On various mathematical benchmarks, our MAVIS-7B achieves leading results among open-source MLLMs, e.g., surpassing other 7B models by +9.3% and the second-best LLaVA-NeXT (110B) by +6.9%, demonstrating the effectiveness of our method.

Details

NeurIPS Conference 2025 Conference Paper

Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos

Weifeng Lin
Xinyu Wei
Ruichuan An
Tianhe Ren
Tingwei Chen
Renrui Zhang
Ziyu Guo
Wentao Zhang

We present Perceive Anything Model (PAM), a conceptually straightforward and efficient framework for comprehensive region-level visual understanding in images and videos. Our approach extends the powerful segmentation model SAM 2 by integrating Large Language Models (LLMs), enabling simultaneous object segmentation with the generation of diverse, region-specific semantic outputs, including categories, label definition, functional explanations, and detailed captions. A key component, Semantic Perceiver, is introduced to efficiently transform SAM 2's rich visual features, which inherently carry general vision, localization, and semantic priors into multi-modal tokens for LLM comprehension. To support robust multi-granularity understanding, we also develop a dedicated data refinement and augmentation pipeline, yielding a high-quality dataset of 1. 5M image and 0. 6M video region-semantic annotations, including novel region-level streaming video caption data. PAM is designed for lightweightness and efficiency, while also demonstrates strong performance across a diverse range of region understanding tasks. It runs 1. 2$-$2. 4$\times$ faster and consumes less GPU memory than prior approaches, offering a practical solution for real-world applications. We believe that our effective approach will serve as a strong baseline for future research in region-level visual understanding.

PDF Details

ICLR Conference 2025 Conference Paper

PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions

Weifeng Lin
Xinyu Wei
Renrui Zhang
Le Zhuo
Shitian Zhao
Siyuan Huang 0004
Junlin Xie
Peng Gao 0007

This paper presents a versatile image-to-image visual assistant, PixWizard, designed for image generation, manipulation, and translation based on free-from language instructions. To this end, we tackle a variety of vision tasks into a unified image-text-to-image generation framework and curate an Omni Pixel-to-Pixel Instruction-Tuning Dataset. By constructing detailed instruction templates in natural language, we comprehensively include a large set of diverse vision tasks such as text-to-image generation, image restoration, image grounding, dense image prediction, image editing, controllable generation, inpainting/outpainting, and more. Furthermore, we adopt Diffusion Transformers (DiT) as our foundation model and extend its capabilities with a flexible any resolution mechanism, enabling the model to dynamically process images based on the aspect ratio of the input, closely aligning with human perceptual processes. The model also incorporates structure-aware and semantic-aware guidance to facilitate effective fusion of information from the input image. Our experiments demonstrate that PixWizard not only shows impressive generative and understanding abilities for images with diverse resolutions but also exhibits generalization capabilities with unseen tasks and human instructions.

Details