LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation Paper • 2603.20192 • Published 3 days ago • 18
FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow Paper • 2603.19598 • Published 3 days ago • 18
Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer Paper • 2603.19227 • Published 4 days ago • 40
LaDe: Unified Multi-Layered Graphic Media Generation and Decomposition Paper • 2603.17965 • Published 5 days ago • 5
Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens Paper • 2603.19232 • Published 4 days ago • 31
Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing Paper • 2603.17942 • Published 5 days ago • 5
Running Featured 39 Nemotron 3 Nano WebGPU ⚛ 39 A compact reasoning-capable model running in your browser.
BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs Paper • 2603.16557 • Published 6 days ago • 20
Alignment Makes Language Models Normative, Not Descriptive Paper • 2603.17218 • Published 6 days ago • 45
AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents Paper • 2603.16496 • Published 6 days ago • 12
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models Paper • 2603.16859 • Published 6 days ago • 241
Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training Paper • 2603.16139 • Published 6 days ago • 31
Qianfan-OCR: A Unified End-to-End Model for Document Intelligence Paper • 2603.13398 • Published 12 days ago • 143
Safe and Scalable Web Agent Learning via Recreated Websites Paper • 2603.10505 • Published 12 days ago • 25
AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents Paper • 2603.14465 • Published 8 days ago • 22