new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

Dec 12

Submitted by

SYZhang0805

LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations

·
12 authors

Submitted by

YuanLiuuuuuu

POINTS1.5: Building a Vision-Language Model towards Real World Applications

·
7 authors

2

Submitted by

jianhongbai

SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

·
9 authors

Submitted by

franciszzj

Learning Flow Fields in Attention for Controllable Person Image Generation

·
14 authors

Submitted by

xhluca

The BrowserGym Ecosystem for Web Agent Research

·
20 authors

Submitted by

hyeonho-jeong-video

Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation

·
5 authors

2

Submitted by

jjjjh

StreamChat: Chatting with Streaming Video

·
8 authors

2

Submitted by

Gynjn

Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction

·
6 authors

Submitted by

zixuan-ye

StyleMaster: Stylize Your Video with Artistic Generation and Translation

·
6 authors

Submitted by

Inbarhub

FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models

Technion

Technion Israel institute of technology

Submitted by

wufeim

3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark

·
6 authors

2

Submitted by

chansung

KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models

·
5 authors

Submitted by

Frag1le

Mogo: RQ Hierarchical Causal Transformer for High-Quality 3D Human Motion Generation

·
1 authors

2

Submitted by

garyzhao9012

Video Creation by Demonstration

·
10 authors

2

Submitted by

roicohen9

I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token

·
4 authors

Submitted by

DrChiZhang

StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements

·
5 authors

Submitted by

ZunWang

Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel

·
11 authors

Submitted by

liboaccn

MIT-10M: A Large Scale Parallel Corpus of Multilingual Image Translation

·
3 authors

2