#Video

YouTube's promoted AI music composition tool 'Replace Songs' helps creators resolve audio copyright disputes

YouTube's promoted AI music composition tool 'Replace Songs' allows creators to instantly generate four royalty-free instrumental background music tracks to replace copyrighted audio upon receiving an audio copyright claim, and automatically removes the relevant Content ID copyright notice. This feature currently only generates instrumental background music and does not support vocal or full song creation.

When Latent Prediction Error Supports Physical Anomaly Claims - Research on Video World Models

Research shows that the latent prediction error in video world models reflects appearance and motion rather than reliable measurements of physical anomalies. Comparisons of latent prediction, masked pixel reconstruction, and simple visual statistics on the IntPhys2 benchmark show that appearance is easy to decode, and V-JEPA2 only slightly reveals whether an event is possible.

Reviso: Not All Visual Evidence Should Be Given Equal Attention in Video Caption Generation

Reviso is an intelligent video subtitle framework that prioritizes key visual evidence through hierarchical planning and active perception learning, enhancing subtitle quality and downstream video understanding capabilities. Multimodal large language models (MLLMs) generated video subtitles may overemphasize minor details while ignoring important context and key events.

How Agent Harness Achieves Video Generation and Agent Interaction

Agent Harness Integrates Video Generation and World Model, Supporting Agents in Multi-Camera Video Production for Planning, Tool Use, and Recursive Self-Improvement. The Framework Coordinates Script, Shooting Planning, Asset Management, Production, and Editing, and Analyzes Its Evaluation Challenges; Meanwhile, It Studies Agent-World Model Interaction in Observation, Control, Execution, and State Maintenance, as Well as How They Mutually Evaluate and Improve.

Venus-DefakerOne2: A broader visual forensics base model

Venus-DefakerOne2 extends detection to multiple spoofing forms and media types through alternating LoRA and full-parameter fine-tuning, as well as entropy-based test adaptive, achieving SOTA performance in six benchmark tests including DeepFake faces (96.7%), AI-generated images (93.3%), and tampered documents (87.6%), significantly outperforming expert models and predecessor DefakerOne.

WeVisCut: An integrated smart editing agent from narration to long videos

WeVisCut coordinates video editing tools, recovers from failures, and reduces token usage through a compact strategy trained on 9B parameters, while maintaining output quality. The system employs a four-stage data pipeline, combining editing inversion and validation replay, to generate over 130K training examples from 3,750 finished videos for training a single strategy.

Codex 0.166.0 released: adding keyboard driver transcription selection, Markdown rendering optimization, and GPT-6.1 Terra support

Codex 0.166.0 released, adding keyboard driver transcription selection (supporting word, line, and page operations), integrated search and configurable shortcuts, as well as consistent Markdown rendering in asynchronous questions, options, answers, and transcription responses. Also supports GPT-6.1 Terra and adds codex queue --resume feature to resume unloaded threads.

CodeCap-Bench: Can executable code serve as high-quality video subtitles?

CodeCap-Bench demonstrates that code captions outperform natural language captions in terms of reasoning accuracy and reconstruction fidelity on video question answering and reconstruction tasks. The benchmark includes 323 structured 2D content videos, covering five categories. Evaluation finds that mainstream closed-source MLLMs perform well in code caption generation but struggle to capture complex temporal dynamics, while open-source models have a significant gap.

LociArt: A Unified Free-Style Local Video Styling Paradigm

LociArt achieves precise local video stylization through generating refined networks, automated dataset construction, and dedicated benchmarks, supporting regional style control and temporal consistency. GRNStyle introduces a polarity-aware style perception mask on the basis of generating refined networks, combined with representation-geometric conditioning technology. Experiments show that it outperforms existing methods in regional style quality and spatial control. The LociArt-100K dataset contains 100,000 local stylization pairs, the benchmark includes 80 source videos and 84 target masks, using a style prototype similarity evaluation scheme.

AV-FABLE: Audio-Visual Tampering Forensic Benchmark for Long Videos

AV-FABLE introduces an audio-visual benchmark for sparse tampering in long videos, demonstrating that frozen audio-visual large language models' perceptual features contain forensic evidence that the best recovery is achieved by separating time decoders rather than language outputs. Local AI tampering in long videos often affects brief events that impact the authenticity of other content, making video-level classification insufficient for forensic analysis.

Changhong releases natural light wallpaper TV QX Series: Up to 10000 nits peak brightness, 23040 independent color control zones, starting from 41499 yuan

Dou Bao's reference weight to Douyin has soared to 31.8%

Dou Bao's reference weight to Douyin increased from 10.79% in May to 31.8% in August, with one out of every three references coming from Douyin. The report shows a positive correlation between the semantic similarity of video titles and question words, with Douyin's average reference increase being 51%, and a higher correlation coefficient for keyword coverage.

Understanding the world through video reading, writing, sharing, and interaction

This review unifies video understanding and generation within world modeling, organizing progress around inferring, synthesizing, sharing, and interacting with potential temporal states, emphasizing continuous dynamics rather than segment-level perception. Video foundation models are rapidly developing in understanding and generating visual sequences, while video world models attempt to capture the underlying dynamics of the world they depict.

ByteDance's Imagination AI Short Drama Studio has launched, offering self-developed script, image, and storyboard models.

The Imagination AI Short Drama Studio has launched, offering self-developed script models DreamScript (supporting multi-genre generation, hit diagnosis, and 100,000-character long story analysis), image models Anycook (supporting differentiated character settings and multi-style scene construction), and storyboard models DreamShot (dual-mode creation, 3D director's desk dynamic preview).

Vivix has launched real-time interactive models W1 and A1, aiming to reduce the cost of generating interactive content to the level of YouTube.

Vivix has launched real-time interactive models W1 and A1, aiming to reduce the cost of generating interactive content to the level of YouTube. The W1 model's real-time generation cost is close to YouTube's approximately $0.2 per hour CDN bandwidth cost; compared to the current top video generation models, the cost of generating real-time interactive content can be 1-2 orders of magnitude lower, and the model can generate the next frame within 300-600 milliseconds after user operation. The Vivix team has grown to 150-160 people.

Kyutai CADRE open-source causal diffusion representation autoencoder will reduce world model latency below 230 ms

Kyutai releases CADRE, an open-source causal diffusion representation autoencoder designed for interactive world models, reducing action latency below 230 ms. CADRE includes 7 autoencoders, each with approximately 476M parameters plus 86M frozen DINOv3 ViT-B/16, a world model of 1.2B parameters, video resolution of 288×512, frame rate of 20 fps, running on 1 H100.

Kunlun Wudi's SkyProduction integrates Ke Ling Kling 4.0

SkyProduction, the AI video creation platform under Kunlun Wudi, has integrated the Kling 4.0 AI video generation model, which is a new generation of native multimodal AI video creation large model launched by Ke Ling. It achieves upgrades in audio-visual performance, creative controllability, narrative coherence, and diverse content generation.

Factor-Aware Predictive Learning is released: a multi-modal large language model representation method for cinematic video generation.

Factor-Aware Predictive Learning (FAPL) enables video diffusion Transformers to utilize multi-modal large language model (MLLM) representations for sparse temporal reasoning and cinematic control, achieving this through staged grounding and optimization. FAPL consistently outperforms baselines on three cinematic video generation tasks (sparse-to-video, factor-aware editing, and multi-shot generation), validating its contributions in MLLM feature utilization, temporal control, and factor coordination.

OmniDR-Bench: Video-centric deep report generation benchmark evaluation.

Researchers have introduced the OmniDR-Bench benchmark and evaluation framework for in-depth study of video-centric deep agents, which can synthesize external evidence to generate interactive reports correlated with video moments. This task has direct practical value, helping users locate relevant video segments, verify claims, and reproduce demonstration steps. OmniDR-Bench includes 50 tasks in Chinese and English, covering 19 real-world subcategories, with a total of 6,414 standards, and the best system score is 63.3.

StreamEval: Benchmark for evaluating interactive streaming video generation models

StreamEval benchmarked the performance of interactive streaming video generation models on five tasks, finding reliable request execution and sustained state consistency to be major challenges. The benchmark includes 300 scripted test cases, covering character dialogue, character performance, world generation, instruction editing, and reference editing tasks, scored across four evaluation dimensions (task execution, state consistency, visual fidelity, and audiovisual coordination).

TwelveLabs' Pegasus 1.5 is now available on Amazon Bedrock

TwelveLabs' Pegasus 1.5 video language model is now available on Amazon Bedrock, which can convert long videos into structured, timestamped metadata, supports analyzing the entire video based on user-defined standards and returns JSON data of matching segments, analysis duration extended to two hours per request, no pre-indexing required and data remains within AWS boundaries.

The Monday Morning Agent project trains AI analysts using American football data.

The Monday Morning Agent project uses the NFL public dataset to analyze a controversial American football topic every two weeks, gradually equipping AI agents with analytical capabilities. The project uses 250,000 game clips and current season data, each episode having AI explain a specific tactic (such as 'establishing the offensive line') and verify its analysis results. The AI must state data limitations during analysis and refuse requests beyond the task scope (such as predicting game outcomes).

Higgsfield uses GPT-6 Astra, GPT-Image-2.5, and GPT-Live to provide creators with longer videos, precise visual effects, and voice movie production paths.

Higgsfield launches GPT-6 Astra, GPT-Image-2.5, and GPT-Live, supporting creators in making longer videos, achieving precise visual effects, and providing voice movie production paths.