Emu3.5: Native Multimodal Models are World Learners
Paper • 2510.26583 • Published • 114
papers
-
-
RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging
Paper • 2510.20479 • Published • 12 -
A Definition of AGI
Paper • 2510.18212 • Published • 36 -
Video-As-Prompt: Unified Semantic Control for Video Generation
Paper • 2510.20888 • Published • 50 -
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 48 -
DeepAgent: A General Reasoning Agent with Scalable Toolsets
Paper • 2510.21618 • Published • 103 -
PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity
Paper • 2510.23603 • Published • 26 -
Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
Paper • 2510.23451 • Published • 28 -
ACG: Action Coherence Guidance for Flow-based VLA models
Paper • 2510.22201 • Published • 37 -
Rethinking Visual Intelligence: Insights from Video Pretraining
Paper • 2510.24448 • Published • 6 -
Latent Chain-of-Thought for Visual Reasoning
Paper • 2510.23925 • Published • 10 -
From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors
Paper • 2510.17439 • Published • 28 -
RoboOmni: Proactive Robot Manipulation in Omni-modal Context
Paper • 2510.23763 • Published • 62 -
The Principles of Diffusion Models
Paper • 2510.21890 • Published • 64 -
Reasoning-Aware GRPO using Process Mining
Paper • 2510.25065 • Published • 42 -
Scaling Latent Reasoning via Looped Language Models
Paper • 2510.25741 • Published • 229 -
Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning
Paper • 2510.23473 • Published • 86 -
Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark
Paper • 2510.26802 • Published • 34 -
Exploring Conditions for Diffusion models in Robotic Control
Paper • 2510.15510 • Published • 40