Multimodal Judges Flag, Humans Decide: A Review-and-Edit Framework for AI-Generated Product Video Ads
cs.CV, cs.HC, cs.MM
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/anoubhav/ad-review-and-edit
Terminology
Sources
- AgenticGen: Reward-Guided Agentic Video Generation for Advertising
- CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
- VideoScore2: Think before You Score in Generative Video Evaluation
- Kling-Omni Technical Report
- Zero-shot Voice Conversion with Diffusion Transformers
- Seedance 2.0: Advancing Video Generation for World Complexity
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs