Towards Scalable Pre-training of Visual Tokenizers for Generation
Paper
•
2512.13687
•
Published
•
105
papers
-
-
MMGR: Multi-Modal Generative Reasoning
Paper • 2512.14691 • Published • 118 -
Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
Paper • 2512.23447 • Published • 97 -
LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation
Paper • 2512.23576 • Published • 65 -
mHC: Manifold-Constrained Hyper-Connections
Paper • 2512.24880 • Published • 292 -
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
Paper • 2512.24618 • Published • 146 -
PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation
Paper • 2512.24551 • Published • 19 -
Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem
Paper • 2512.24873 • Published • 104 -
Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling
Paper • 2512.23959 • Published • 112 -
Agent Learning via Early Experience
Paper • 2510.08558 • Published • 273 -
Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
Paper • 2601.02151 • Published • 104 -
Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization
Paper • 2601.05432 • Published • 165 -
MMFormalizer: Multimodal Autoformalization in the Wild
Paper • 2601.03017 • Published • 105 -
Qwen3-VL Technical Report
Paper • 2511.21631 • Published • 152 -
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
Paper • 2512.08765 • Published • 132 -
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 506