Bezen

Your daily digest

Research papers, made simple to understand

The AI and machine learning papers people are reading most, each one rewritten in plain words: the problem, the idea, what was found and why it matters.

Image & Video Generation9 papers, newest first

    • Multimodal & Vision
    • Image & Video Generation

    Factor-Aware Predictive Learning improves cinematic video generation using MLLM latents

    FAPL trains a Video Diffusion Transformer to effectively use multimodal large language model latents for temporal inference and factor-aware control, achieving better action sequencing, camera fidelity, and factor-specific editing on cinematic video tasks.

    Paper: Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation · Songlin Yang, Zhe Wang, Xiaotong Zhao and 8 others

    165 upvotes on Hugging Face23 Oct 20266 min readRead the article

    • Image & Video Generation
    • Benchmarks & Evaluation

    StreamEval benchmark measures interactive streaming video generation across five tasks

    StreamEval introduces a unified benchmark with 300 scripted test cases and ten metrics to evaluate real-time interactive video generation models on avatar dialogue, avatar performance, world generation, instruction editing, and reference editing, revealing challenges in request execution and state consistency.

    Paper: StreamEval: Evaluating Interactive Streaming Video Generation Models · StreamEval Team

    363 upvotes on Hugging Face22 Oct 20267 min readRead the article

    • AI Agents
    • Image & Video Generation

    ATAS framework improves spatial and temporal consistency in agentic video generation

    ATAS compiles screenplays into shot requests with explicit spatial and temporal references, maintaining persistent scene and event memories to improve cross-shot consistency and enable spatial revisits and event replays, outperforming prior methods on multiple benchmarks and human evaluations.

    Paper: Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation · Weijie Wang, Haomin Zhang, Ye Li and 7 others

    328 upvotes on Hugging Face15 Oct 20266 min readRead the article

    • Reinforcement Learning & Alignment
    • Image & Video Generation

    DiffusionART stabilizes and speeds up reinforcement learning fine-tuning of diffusion models

    DiffusionART improves efficiency and stability in online reinforcement learning fine-tuning of diffusion models by aggregating reward signals before updating states and using a drift-adaptive restoration update, achieving up to 12x faster training and higher rewards without per-task tuning.

    Paper: DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models · Zhenglin Wan, Jiayu Chen, Zhengfeiyang Zhang and 6 others

    230 upvotes on Hugging Face12 Oct 20268 min readRead the article

    • Image & Video Generation
    • Benchmarks & Evaluation

    UltraText Bench evaluates dense bilingual visual text rendering in image generation

    UltraText Bench is a bilingual benchmark with 432 prompts across 24 scene categories and three difficulty levels, assessing image generators on dense visual text reproduction in English and Chinese using a vision-language model for multi-dimensional scoring.

    Paper: UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation · Deyuan Liu, Yihao Hu, Jingxuan Zhang and 13 others

    153 upvotes on Hugging Face10 Oct 20266 min readRead the article

    • Image & Video Generation

    DuoMatching improves few-step video generation by combining joint and marginal distribution matching

    DuoMatching enhances few-step video generation by jointly matching video-level and frame-level distributions using a video teacher and an image teacher, improving visual quality and semantic alignment while preserving motion dynamics, with human preference rates above 80%.

    Paper: DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation · Jiahao Zhan, Yan Wang, Yongrui Ma and 5 others

    70 upvotes on Hugging Face7 Oct 20267 min readRead the article

    • Image & Video Generation
    • Speech & Audio

    Kandinsky 6.0 Video generates synchronized 5-second videos with 44 kHz audio using dual-stream diffusion models

    Kandinsky 6.0 Video introduces two diffusion models (3B and 29B parameters) that generate 5-second Full-HD videos with synchronized high-quality audio and lip-sync from text or images, using a dual-stream CrossDiT architecture and multi-stage training including reinforcement learning and distillation.

    Paper: Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation · Team Kandinsky, Julia Agafonova, Bulat Akhmatov and 85 others

    117 upvotes on Hugging Face6 Oct 20266 min readRead the article

    • Image & Video Generation

    In-Distribution Forcing stabilizes long video generation by controlling KV cache provenance

    Drifting in long autoregressive video diffusion arises from out-of-distribution KV cache entries due to unseen provenance during rollout. In-Distribution Forcing aligns KV caching and conditioning with training, enabling stable minute-scale video generation and reducing drift.

    Paper: In-Distribution Forcing for Long Video Generation at Test Time · Jeongwoo Shin, Youngyoon Choi, Sangwoo Jo and 5 others

    34 upvotes on Hugging Face6 Oct 20266 min readRead the article

    • Image & Video Generation

    FrameMorrow selects historical video frames by predicting future needs for better long-horizon generation

    FrameMorrow improves long-horizon video generation by predicting compact prospective tokens that represent future information needs, guiding selection of relevant past frames. This plug-and-play method enhances consistency, quality, and action alignment across 11 models and 5 benchmarks with minimal overhead.

    Paper: FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation · Bo Yin, Xiaobin Hu, Jiaqi Zhao and 1 other

    91 upvotes on Hugging Face5 Oct 20266 min readRead the article