arXiv AI

WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video

WeVisCut is a long‑form script‑to‑video system that unifies narration, editing, and tool execution into a single agent. It uses a four‑stage data pipeline that reconstructs editing intent from finished videos, generating over 130K training examples to train a 9B policy capable of coordinating production and recovering from failures. The system introduces a 100‑task benchmark with five metrics, outperforming its base model, matching Claude Opus 5 in performance while using far fewer tokens, and surpassing task‑matched native editors on the proposed metrics.

arXiv AI

Jun 9

CoVEBench: Can Video Editing Models Handle Complex Instructions?

arXiv:2606. 08415v1 Announce Type: cross Abstract: While recent text-guided video editing models excel at elementary tasks (e.

By Jiangtao Wu, Jiaming Wang, Yiwen He, Yuanxing Zhang, Shihao Li, Dunyuan Liu, Xuedong Zhao, Jialu Chen, Zekun Moore Wang, Jiaheng Liu

benchmarks

arXiv AI

Jul 7

VideoAgent: All-in-One Framework for Video Understanding and Editing

arXiv:2606. 23327v2 Announce Type: replace-cross Abstract: Video editing has become essential in digital media creation, yet existing automated systems are restricted to short segment processing and domain-specific tasks.

By Hengji Zhou, Lingxuan Huang, Jian Wang, Bing Zhou, Si Wu, Lianghao Xia, Chao Huang

llms agents multimodal benchmarks

arXiv AI

1d ago

SemantiScene-Edit: Expert-Synthesized Supervision and Dual-Path Source Conditioning for Instruction-Based Video Editing

arXiv:2609.26015v2 Announce Type: replace Abstract: Instruction-guided video editing requires executing a requested change while preserving the source video's appearance and temporal structure. We pr...

By Xinyu Chen, Song Wu, Dingbao Shao, Jiahang Li, Jiang Lin, Yuhang Liu, Duo Li, Jiaxin Hu, Shengrong Gu, Liang Li, Qian Wang, Junlan Feng, Ying Tai, Jian Yang, Zili Yi

llms rag diffusion multimodal benchmarks safety

Hugging Face Trending Papers

Sep 28

Timeline-Bench: Evaluating Agents on Realistic Video-Editing Tasks, from Raw Footage to Final Cut

Timeline-Bench is a benchmark comprising 56 real video‑editing tasks that require AI agents to transform raw production material into finished videos. Each task includes a brief, source assets, a container, and a set of tests that assess format, content, brief compliance, and quality based on 2,582 blind judgments by 43 video editors. In evaluations, the best agent resolved only 15 of the 56 tasks, and most failures were due to quality tests rather than technical errors.

llms agents benchmarks

arXiv Computer Vision

Sep 3

OmniEdit-Bench: A Comprehensive Benchmark for Instruction-based Video Editing

OmniEdit-Bench introduces a comprehensive benchmark for instruction-based video editing (IVE), addressing limitations of existing datasets by covering spatial, temporal, audio, and reference-based editing tasks and distinguishing explicit from implicit instructions. The evaluation framework assesses editing quality across accuracy, preservation, realism, and consistency, using human judgments and vision-language models, and incorporates an accuracy-aware penalty to ensure instruction fidelity. Experiments reveal that current IVE models perform poorly, highlighting the need for improved methods.

By Chenxuan Miao, Yutong Feng, Yi Lu, Yunfeng Yan, Donglian Qi, Shiwei Zhang, Yu Liu, Xi Chen, Hengshuang Zhao

llms multimodal benchmarks

arXiv AI

Sep 10

Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation

arXiv:2609.08275v1 Announce Type: new Abstract: Recent multi-shot audio-video generators can produce increasingly coherent and cinematic outputs, but coherence does not imply the ability to execute e...

By Tianyi Zeng, Junchao Liao, Yujie Wei, Ziying Zhang, Litao Li, Tianyi Wang, Zhichao Wei, Shuyao Xu, Wenwen Qiang, Siyu Zhu, Zhenghao Zhang, Long Qin

agents diffusion nlp multimodal benchmarks safety

arXiv Computer Vision

Oct 9

From Video Clips to Creation Trajectory: Sora100K for AI-Native Video Creation

The paper introduces Sora100K, a dataset that captures AI‑Native video creation workflows as structured trajectories rather than isolated clips. It categorizes trajectories into text‑to‑video generation roots, single‑turn editing edges, and multi‑turn editing sequences, annotating each with semantic and operation labels via a VLM. A rigorous construction pipeline ensures accurate source‑to‑edit lineage and intermediate states, and lightweight adaptation on LTX‑2 models demonstrates improved visual quality, multi‑shot generation, and cross‑shot consistency, though multi‑turn editing remains challenging.

By Sicong Yang, Ruihuan Yang, Jian Lu, Jianfei Yuan, Xiaodong Cun, Xiuli Bi

diffusion multimodal data-engineering

arXiv Computer Vision

Oct 2

VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation

VideoWeaver is an agent harness and benchmark for long‑video generation that evaluates and evolves reusable skills. It allows an agent to dynamically compose foundation skills into a workflow based on a single high‑level instruction, rather than following a static pipeline. The benchmark includes 16 task categories and 285 cases with multimodal references, and an evidence‑grounded agent‑as‑judge inspects execution traces and final videos to guide skill evolution, improving both process and output quality.

By Jianhui Wei, Yan Zhang, Jie Tan, Hengchuan Zhu, Xiaotian Zhang, Ziyi Chen, Daoan Zhang, Wei Xu, Yeying Jin, Zuozhu Liu

agents diffusion benchmarks

arXiv Computer Vision

Aug 26

CoinVE-200K: A Large-Scale High-Quality Dataset for Compositional Instruction-Guided Video Editing

arXiv:2608.17566v2 Announce Type: replace Abstract: The quality and diversity of instruction-based video editing datasets are steadily improving, yet existing datasets mainly focus on single editing...

By Fuchen Long, Cong Wang, Zitao Gao, Wenhao Zhong, Yu Cheng, Xiaolu Hou, Yan Li, Xiao Cao, Xinlong Sun, Xi Chen, Yu Liu

benchmarks

Hugging Face Trending Papers

Sep 21

VideoGen-Agent: Reinforcing Video Generation Agents

Recent advances in video generative models have enabled high-fidelity, temporally coherent video generation. However, these models often struggle to satisfy prompts requiring specialized knowledge, sp...

agents diffusion reinforcement-learning fine-tuning multimodal benchmarks

Hugging Face Trending Papers

Jun 29

Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing

Existing instruction-based video editing datasets commonly focus on single-task appearance editing, failing to meet the complex creative demands of real-world scenarios. To bridge this gap, we present Goku, a large-scale dataset featuring 2 million high-quality, instruction-aligned video editing pairs, which is the first to extend task boundaries from basic appearance editing to multi-task and structural manipulations(e.

benchmarks

arXiv Computer Vision

Aug 28

Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning

The paper introduces the Multi-Instruction Multi-Shot Long-Video Editing (MMLVE) task, aiming to enable consistent editing of long videos with multiple instructions. It proposes an agentic editing framework that combines Large Language Models and Vision-Language Models for shot-level decoupling and precise instruction parsing. The authors also present the MMLVE-Bench dataset and evaluation metrics, showing that their MMLVE-Agent outperforms existing state‑of‑the‑art methods by eliminating hallucinations and preserving temporal consistency.

By Chenyang Wu, Fuchen Long, Binyuan Huang, Xinlong Sun, Xi Chen, Chun-Le Guo, Chongyi Li

llms rag agents computer-vision multimodal benchmarks safety

Related stories