14 papers
VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement
Wenzhuo Xu, Yuchen Zhu, Chongjian Ge +8
Visual fluency in generated video does not imply physical reliability, and a scalar quality score alone is incapable of indicating the obligation a clip violates or the moment it f…
Thinking with Anchors: Grounded and Efficient Document Reasoning
Sichen Zhu, Yuchen Zhu, Wenzhuo Xu +13
Existing document understanding benchmarks have largely focused on locating page elements, yet real-world document intelligence requires models to reason jointly about region seman…
FLARE: Diffusion for Hybrid Language Model
Yuchen Zhu, Jing Shi, Chongjian Ge +9
Autoregressive (AR) large language models (LLMs) have achieved broad practical success, but sequential decoding remains a key bottleneck for low-latency deployment. Recent efficien…
Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration
Zhuoling Li, Jiarui Zhang, Ping Hu +4
Method illustrations (MIs) play a crucial role in conveying the core ideas of scientific papers, yet their generation remains a labor-intensive process. Here, we take inspiration f…
DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generation
Zhuoling Li, Hossein Rahmani, Jiarui Zhang +5
The rapid growth of the text-to-image (T2I) community has fostered a thriving online ecosystem of expert models, which are variants of pretrained diffusion models specialized for d…
SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generation
Shufan Li, Jiuxiang Gu, Kangning Liu +3
Recent advancements in discrete image generation showed that scaling the VQ codebook size significantly improves reconstruction fidelity. However, training generative models with a…
Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models
Shufan Li, Jiuxiang Gu, Kangning Liu +4
Masked Discrete Diffusion Models (MDMs) have achieved strong performance across a wide range of multimodal tasks, including image understanding, generation, and editing. However, t…
OIDA-QA: A Multimodal Benchmark for Analyzing the Opioid Industry Documents Archive
Xuan Shen, Brian Wingenroth, Zichao Wang +12
The opioid crisis represents a significant moment in public health that reveals systemic shortcomings across regulatory systems, healthcare practices, corporate governance, and pub…
Image Tokenizer Needs Post-Training
Kai Qiu, Xiang Li, Hao Chen +7
Recent image generative models typically capture the image distribution in a pre-constructed latent space, relying on a frozen image tokenizer. However, there exists a significant…
Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation
Shufan Li, Jiuxiang Gu, Kangning Liu +4
We propose Lavida-O, a unified Masked Diffusion Model (MDM) for multimodal understanding and generation. Unlike existing multimodal MDMs such as MMaDa and Muddit which only support…
Refer to Any Segmentation Mask Group With Vision-Language Prompts
Shengcao Cao, Zijun Wei, Jason Kuen +6
Recent image segmentation models have advanced to segment images into high-quality masks for visual entities, and yet they cannot provide comprehensive semantic understanding for c…
Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesis
Kai Qiu, Xiang Li, Jason Kuen +7
Recent image generation schemes typically capture image distribution in a pre-constructed latent space relying on a frozen image tokenizer. Though the performance of tokenizer play…
XQ-GAN: An Open-source Image Tokenization Framework for Autoregressive Generation
Xiang Li, Kai Qiu, Hao Chen +5
Image tokenizers play a critical role in shaping the performance of subsequent generative models. Since the introduction of VQ-GAN, discrete image tokenization has undergone remark…
ImageFolder: Autoregressive Image Generation with Folded Tokens
Xiang Li, Kai Qiu, Hao Chen +4
Image tokenizers are crucial for visual generative models, e.g., diffusion models (DMs) and autoregressive (AR) models, as they construct the latent representation for modeling. In…