Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation
Paper • 2610.20571 • Published • 239
Bohan Zhuang
BohanZ
AI & ML interests
AI infra; Efficient AI; Multimodal agent
Recent Activity
authored a paper 15 days ago
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation authored a paper 15 days ago
MixTok: Adaptive Visual Tokenization with Global 1D Tokens and Sparse 2D Refinement authored a paper 15 days ago
HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic MixingOrganizations
authored 20
papers 15 days ago
MixTok: Adaptive Visual Tokenization with Global 1D Tokens and Sparse 2D Refinement
Paper • 2610.13181 • Published • 12
HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing
Paper • 2610.05842 • Published • 14
HLA-WM: Hybrid Linear Attention for Long-Horizon Video World Models
Paper • 2610.05739 • Published • 21
WorldAttention: An Efficient Attention Architecture for Interactive Video World Models
Paper • 2609.34606 • Published • 52
EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models
Paper • 2310.03270 • Published
ZipAR: Accelerating Autoregressive Image Generation through Spatial Locality
Paper • 2412.04062 • Published • 8
Evaluating and Advancing Multimodal Large Language Models in Ability Lens
Paper • 2411.14725 • Published
MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
Paper • 2411.04924 • Published
ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification and KV Cache Compression
Paper • 2410.08584 • Published • 12
InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generation
Paper • 2407.10061 • Published
ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes
Paper • 2609.01740 • Published • 29
Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion
Paper • 2608.19567 • Published • 34
Unified Hallucination Fuzzing for Multimodal Large Language Models
Paper • 2608.07525 • Published
Agent-as-a-Router: Agentic Model Routing for Coding Tasks
Paper • 2606.22902 • Published • 39
World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
Paper • 2604.24764 • Published • 121
WorldOlympiad: Can Your World Model Survive a Triathlon?
Paper • 2606.11129 • Published • 33
K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling
Paper • 2606.10820 • Published • 1
Latent Spatial Memory for Video World Models
Paper • 2606.09828 • Published • 71
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
Paper • 2604.14025 • Published • 15