ZIP Lab

university

https://ziplab.co/

AI & ML interests

Model Effiicency, Diffusion Model, LLM, World Model

Recent Activity

chenfeng1271 authored a paper about 7 hours ago

ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes

lhmd authored a paper about 7 hours ago

ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes

lhmd submitted a paper about 7 hours ago

ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes

View all activity

Papers

Less Detail, Better Answers: Degradation-Driven Prompting for VQA

CoV: Chain-of-View Prompting for Spatial Reasoning

View all Papers

authored a paper about 7 hours ago

ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes

Paper • 2609.01740 • Published 3 days ago • 19

lhmd

authored a paper about 7 hours ago

ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes

Paper • 2609.01740 • Published 3 days ago • 19

lhmd

submitted a paper to Daily Papers about 7 hours ago

ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes

Paper • 2609.01740 • Published 3 days ago • 19

authored 5 papers 9 days ago

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

Paper • 2608.19567 • Published 15 days ago • 33

PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models

Paper • 2606.22540 • Published Jun 21 • 5

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation

Paper • 2605.09430 • Published May 10 • 2

LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models

Paper • 2603.07145 • Published Mar 7 • 4

CoV: Chain-of-View Prompting for Spatial Reasoning

Paper • 2601.05172 • Published Jan 8 • 11

lhmd

submitted a paper to Daily Papers 9 days ago

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

Paper • 2608.19567 • Published 15 days ago • 33

lhmd

authored a paper 11 days ago

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

Paper • 2608.19567 • Published 15 days ago • 33

lhmd

authored a paper 17 days ago

PixVL: Self-Supervised Training of Pixel-Level MLLMs via a Unified Mask--Text Consistency Cycle

Paper • 2608.01354 • Published Aug 2

lhmd

authored 2 papers about 1 month ago

ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation

Paper • 2605.26525 • Published May 26

TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning

Paper • 2605.18109 • Published May 18

submitted a paper to Daily Papers about 2 months ago

VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery

Paper • 2607.06374 • Published Jul 7 • 10

submitted a paper to Daily Papers 2 months ago

PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models

Paper • 2606.22540 • Published Jun 21 • 5

authored 2 papers 2 months ago

GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning

Paper • 2606.17480 • Published Jun 16 • 3

SpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction

Paper • 2606.15659 • Published Jun 14 • 4

submitted 2 papers to Daily Papers 2 months ago

GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning

Paper • 2606.17480 • Published Jun 16 • 3

SpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction

Paper • 2606.15659 • Published Jun 14 • 4

authored a paper 3 months ago

DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects

Paper • 2606.15133 • Published Jun 13 • 75