Daily Papers of 2025-11-28

1. Video Generation Models Are Good Latent Reward Models 44 upvotes, #1 of 2025-11-28
2. Canvas-to-Image: Compositional Image Generation with Multimodal Controls 31 upvotes, #2 of 2025-11-28
3. ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction 15 upvotes, #3 of 2025-11-28
4. MIRA: Multimodal Iterative Reasoning Agent for Image Editing 10 upvotes, #4 of 2025-11-28
5. Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following 10 upvotes, #4 of 2025-11-28
6. Agentic Learner with Grow-and-Refine Multimodal Semantic Memory 10 upvotes, #4 of 2025-11-28
7. What does it mean to understand language? 9 upvotes, #7 of 2025-11-28

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.