HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing
Paper • 2610.05842 • Published • 9
ZIP Lab
university
AI & ML interests
Model Effiicency, Diffusion Model, LLM, World Model
Recent Activity
View all activity
Papers
Less Detail, Better Answers: Degradation-Driven Prompting for VQA
CoV: Chain-of-View Prompting for Spatial Reasoning
chenfeng1271
submitted a
paper to Daily Papers 4 days ago
chenfeng1271
authored a
paper 4 days ago
chenfeng1271
submitted a
paper to Daily Papers 4 days ago
SteveZeyuZhang
authored a
paper 5 days ago
SteveZeyuZhang
submitted a
paper to Daily Papers 5 days ago
SteveZeyuZhang
authored 3
papers 9 days ago
SteveZeyuZhang
submitted a
paper to Daily Papers 9 days ago
SteveZeyuZhang
authored 11
papers 11 days ago
WorldAttention: An Efficient Attention Architecture for Interactive Video World Models
Paper • 2609.34606 • Published • 50
DeltaWAM: Delta World Action Models for Bimanual Manipulation
Paper • 2609.28811 • Published • 20
UniMo: Unifying Human and Animal Motion Generation
Paper • 2609.12342 • 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
VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery
Paper • 2607.06374 • Published • 5
Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding
Paper • 2606.27922 • Published
MotionVLA: Vision-Language-Action Model for Humanoid Motion
Paper • 2606.15142 • Published • 6
PartRAG: Retrieval-Augmented Part-Level 3D Generation and Editing
Paper • 2602.17033 • Published
StereoAdapter-2: Globally Structure-Consistent Underwater Stereo Depth Estimation
Paper • 2602.16915 • Published
MMA: Multimodal Memory Agent
Paper • 2602.16493 • Published • 9