~ similar to 2606.02535· 17 results
The paper argues that benchmarking Vision-Language Models (VLMs) for urban perception must treat human disagreement and non-response as key measurement outcomes, rather than assuming perfect consensus…
The paper introduces the Image Reconstruction Game, a benchmark showing that the quality of the descriptive model is the primary determinant of image reconstruction success, while the generator's role…
The paper analyzes token reduction for efficient unified VLM training, finding that while task-specific acceleration saves computation, it destroys the mutual performance gains achieved through joint…
The paper introduces Staged Executable Inverse Graphics (SEIG), an agentic framework that uses general-purpose Vision-Language Models (VLMs) to reconstruct editable 3D scenes directly into executable…
Yipeng Gao, Lei Shu, Genzhi Ye, Xi Xiong +4 more
The paper introduces 3DCodeBench, a systematic benchmark and platform for evaluating Vision-Language Model (VLM) agents' ability to generate procedural 3D models from text and images using code.
Haolin Deng, Xin Zou, Zhiwei Jin, Chen Chen +2 more
The paper proposes In-Context Visual Contrastive Optimization (IC-VCO) to rigorously mitigate multimodal hallucinations in Vision-Language Models by optimizing contrastive learning within a shared mul…
Haitian Li, Yanghao Zhou, Heyan Huang, Liangji Chen +14 more
The paper introduces MTAVG-Bench 2.0, a new benchmark designed to diagnose high-level failure modes of cinematic expressiveness in multi-talker audio-video generation, showing that even advanced model…
The paper introduces GPIC, a massive, permissively licensed, and safety-filtered image corpus of 28 trillion pixels, designed to serve as a stable and accessible benchmark for large-scale visual gener…
The paper proposes a unified framework to systematically redefine instance matching for Panoptic Quality evaluation, moving beyond the standard One-to-One matching to accommodate complex scenarios lik…
The paper introduces Responsible Contrastive Soft Prompting (RCSP), a parameter-efficient method using soft prompts to improve LLM reliability by simultaneously suppressing hallucinations, encouraging…
This paper proposes using color statistics, specifically through novel color transformations, to detect AI-generated synthetic images by exploiting the color-imitation weaknesses of current generative…
The paper introduces SEED, a large-scale benchmark dataset for tracing sequential deepfake facial edits, and proposes FAITH, a frequency-aware Transformer model that effectively detects and orders the…
The paper proposes BRACS, a training-free steering framework that adaptively corrects visual grounding failures in large vision-language models, significantly reducing object hallucination without sac…
Jiazheng Xing, Hangjie Yuan, Lingling Cai, Xinyu Liu +8 more
Lumos-Nexus is a training-efficient framework that enhances video generation quality by progressively bridging generation from a lightweight model to a high-fidelity generator in a shared latent space…
The paper introduces CalArena, a large-scale, standardized benchmark covering nearly 2000 experiments to comprehensively evaluate post-hoc calibration methods, finding that smooth calibration function…
This study systematically evaluates Vision Mamba models for detecting AI-generated images, finding that while they show promise, their current strengths and limitations must be understood relative to…
肖代替了视觉令牌的永久删除，通过可恢复的路由来改进视觉语言模型的性能