CVPR大爆料!百万级真机数据 + 自动驾驶新方向, 扩散模型又立大功!

Title	Authors	Summary
Benchmarking and Evaluating Large Video Generation Models	Yaofang Liu, Xiaodong Cun, Xuebo Liu	The paper proposes a comprehensive evaluation framework for large video generation models that have grown rapidly. Existing academic metrics are inadequate for evaluating these models trained on massive datasets. The proposed evaluation pipeline comprises prompt curation, objective evaluation, subjective studies, and opinion alignment. The models are evaluated based on 17 objective metrics covering visual quality, content quality, motion quality, and text-caption alignment. Additionally, it provides a comparison table of various video generation models across different metrics and capabilities.
ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object	Chenshuang Zhang, Fei Pan, Junmo Kim	ImageNet-D is a new benchmark for evaluating neural network robustness in visual perception tasks. It generates synthetic images with diverse backgrounds, textures, and materials, making it more challenging than other synthetic datasets. Key features include diversified image generation, high visual fidelity, and significant accuracy reduction of various vision models. The benchmark is created by combining object categories and refining through human verification. ImageNet-D is effective in evaluating neural network robustness, as accuracy on it improves with accuracy on ImageNet.
Polos: Multimodal Metric Learning from Human Feedback for Image Captioning	Yuiga Wada, Kanta Kaneda, Daichi Saito, Komei Sugiura	The Polaris dataset, used to train the model, contains 131,020 human judgments from 550 evaluators on the appropriateness of image captions. The dataset is much larger than existing ones and is capable of training image captioning metrics. The captions in Polaris are more diverse, collected from humans and generated by 10 modern image captioning models. This demonstrates the effectiveness and robustness of Polos compared to previous metrics.
VBench: Comprehensive Benchmark Suite for Video Generative Models	Ziqi Huang, Yinan He, Jiashuo Yu	VBench is a tool that evaluates video generation models across 16 quality dimensions. These dimensions fall under Video Quality and Video-Condition Consistency. VBench provides valuable insights by evaluating models across multiple dimensions, content categories, and comparing video vs image generation. The tool's authors plan to expand VBench to more models and video generation tasks. Checkout the leaderboard on HF here: https://huggingface.co/spaces/Vchitect/VBench_Leaderboard

Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features	Niladri Shekhar Dutt, Sanjeev Muralikrishnan, Niloy J. Mitra	Diff3F is a feature descriptor for untextured 3D shapes. It computes 3D semantic features using pre-trained 2D diffusion models, rendering depth and normal maps from multiple views, and lifting the 2D diffusion features back to the 3D surface. This produces semantic descriptors on the 3D shape without requiring additional training data or part segmentation.
One-step Diffusion with Distribution Matching Distillation	Tianwei Yin	Distribution Matching Distillation (DMD accelerates multi-step diffusion models into a one-step generator without compromising image quality. DMD matches the distribution of the original diffusion model by minimizing KL divergence and using two score functions - one for the actual data distribution and one for the generated distribution. A regression loss matches the large-scale structure of the multi-step diffusion outputs.

天工造物局

北京人形旗下天工造物具身智能开源社区，聚焦具身天工与慧思开物两大平台

更多推荐

graphify 视频音视频转写全流程解析：从 detect 结果到知识图谱文档的 Step 2.5

graphify 的核心能力是把任意语料（代码、文档、PDF、图片）转化为可查询的知识图谱，而视频与音频文件无法被直接阅读，必须先把它们转写成文本。本文围绕 `graphify` 运行手册中的转写参考文档 [transcribe.md](https://link.gitcode.com/i/d3285781588e0f1b84886dfdbc4fe7f6)，完整讲解 "Step 2.5 - Tra

天工造物局

ML-For-Beginners 终章：经典机器学习在金融、医疗、零售等八大行业中的真实落地场景

本篇技术指南基于开源课程仓库 ML-For-Beginners 的收尾课程《Postscript: Machine learning in the real world》（对应仓库目录 [9-Real-World/1-Applications](https://link.gitcode.com/i/6b23002df80861c20abf34d7db63ef41)）编写。该课此前 11 周的教学带

天工造物局

graphify 知识图谱查询实战：query / path / explain 与可审计的答案闭环

本指南以 graphify 的 Trae 版查询技能参考（[graphify/skills/trae/references/query.md](https://link.gitcode.com/i/72a7875d46ec6d3706d31791f3cdcbe0)）为主体，系统讲解如何针对**已构建好的知识图谱**执行三类查询：语义相关节点遍历（query）、两概念间最短路径（path）、单节点关