UniSpark: Exploring Hybrid Attention for Multimodal Understanding and Generation Paper • 2611.16517 • Published 6 days ago • 15
Duo: A Reciprocal World Model for Full-Duplex Interaction Paper • 2611.15131 • Published 7 days ago • 48
G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation Paper • 2611.13004 • Published 10 days ago • 47
Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents Paper • 2611.17167 • Published 6 days ago • 39
JoVox: Joint Hierarchical Flow Matching for Lightweight Voxel Generation Paper • 2611.10690 • Published 10 days ago • 5
WMIP: A Working-Memory-Inspired Programmable Probe of Cumulative State Tracking in Large Language Models Paper • 2603.27343 • Published 19 days ago • 9
GTAGym: AAA Game Tasks Environment for Evaluation and Reinforcement Learning Paper • 2611.13028 • Published 7 days ago • 16
DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction Paper • 2611.03142 • Published 16 days ago • 16
VidDub: Replacement-Aware Distillation for Two-Step Video Dubbing Paper • 2611.03404 • Published 16 days ago • 9
Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion Paper • 2610.25276 • Published about 1 month ago • 8
Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers Paper • 2610.40647 • Published 20 days ago • 27
LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers Paper • 2611.05304 • Published 14 days ago • 11
VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation Paper • 2611.06796 • Published 14 days ago • 11
Is Forgetting Unified? Exploring Concept Unlearning in Unified Multimodal Models Paper • 2611.04467 • Published 15 days ago • 6
VidUEU-Agent: A Data-Curation Agent for Multimodal Understanding, Editing, and Unified Tasks Paper • 2611.04418 • Published 15 days ago • 27
SIMIT: Self-Improving Vision-Language Models via Imagination at Test-Time Paper • 2611.00053 • Published Oct 11 • 6
Latent Reasoning in Continuous Space for Unified Multimodal Models Paper • 2610.42149 • Published 19 days ago • 45
FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation Paper • 2610.36545 • Published 22 days ago • 35
OpenFlyV2: An onboard vision-language-action model for aerial perception and navigation Paper • 2610.39287 • Published 20 days ago • 9