17 papers
FigMirror: Ground It, Code It, Plot It
Xiaohan Zhao, Jiacheng Liu, Yaxin Luo +1
Converting scientific figures into executable code has gained increasing attention, yet existing methods primarily focus on reproducing the reference figure itself. A more practica…
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Yaxin Luo, Haobin Jiang, Jialv Zou +11
Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a model-harness system…
DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees
Tianyi Li, Yaxin Luo, Xinyi Shang +1
Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel. Diffusion-based drafters further reduce proposal latency…
Simple Domain Generalization for Strong Pixel-Level Image Tampering Detection in Modern VLMs
Yi Tang, Xinyi Shang, Jiacheng Cui +12
Modern vision-language models (VLMs) have significantly improved image generation and editing capabilities, making pixel-level image tampering detection increasingly important yet…
LLMSurgeon: Diagnosing Data Mixture of Large Language Models
Yaxin Luo, Jiacheng Cui, Xiaohan Zhao +5
The pretraining data mixture of Large Language Models (LLMs) constitutes their "digital DNA", shaping model behaviors, capabilities, and failure modes. Yet this composition is rare…
Language-Pretraining-Induced Bias: A Strong Foundation for General Vision Tasks
Yaxin Luo, Zhiqiang Shen
The ratio of outlier parameters in language pre-training models and vision pre-training models differs significantly, making cross-modality (language and vision) inherently more ch…
From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering
Xinyi Shang, Yi Tang, Jiacheng Cui +9
Existing tampering detection benchmarks largely rely on object masks, which severely misalign with the true edit signal: many pixels inside a mask are untouched or only trivially m…
Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting
Xiaohan Zhao, Zhaoyi Li, Yaxin Luo +2
Black-box adversarial attacks on Large Vision-Language Models (LVLMs) are challenging due to missing gradients and complex multimodal boundaries. Prior state-of-the-art transfer-ba…
Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense
Jiacheng Liu, Yaxin Luo, Jiacheng Cui +3
The rapid evolution of GUI-enabled agents has rendered traditional CAPTCHAs obsolete. While previous benchmarks like OpenCaptchaWorld established a baseline for evaluating multimod…
Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift
Jiacheng Cui, Bingkui Tong, Xinyue Bi +3
Soft labels from teacher models are a de facto practice for knowledge transfer and large-scale dataset distillation (e.g., SRe2L, LPLD). However, when we limit the number of crops…
Learning Robust Diffusion Models from Imprecise Supervision
Dong-Dong Wu, Jiacheng Cui, Wei Wang +2
Conditional diffusion models have achieved remarkable success in various generative tasks recently, but their training typically relies on large-scale datasets that inevitably cont…
FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation
Jiacheng Cui, Xinyue Bi, Yaxin Luo +3
Residual connection has been extensively studied and widely applied at the model architecture level. However, its potential in the more challenging data-centric approaches remains…
DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation
Jennifer Chen, Aidar Myrzakhan, Yaxin Luo +3
Retrieval-Augmented Generation (RAG) methods have proven highly effective for tasks requiring factual consistency and robust knowledge retrieval. However, large-scale RAG systems c…
Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents
Yaxin Luo, Zhaoyi Li, Jiacheng Liu +3
CAPTCHAs have been a critical bottleneck for deploying web agents in real-world applications, often blocking them from completing end-to-end automation tasks. While modern multimod…
A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
Zhaoyi Li, Xiaohan Zhao, Dong-Dong Wu +2
Despite promising performance on open-source large vision-language models (LVLMs), transfer-based targeted attacks often fail against closed-source commercial LVLMs. Analyzing fail…
Dataset Distillation via Committee Voting
Jiacheng Cui, Zhaoyi Li, Xiaochen Ma +3
Dataset distillation aims to synthesize a compact yet representative dataset that preserves the essential characteristics of the original data for efficient model training. Existin…
MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models
Yaxin Luo, Gen Luo, Jiayi Ji +4
Despite the significant progress in multimodal large language models (MLLMs), their high computational cost remains a barrier to real-world deployment. Inspired by the mixture of d…