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

Jul 3

Submitted by

yifanzhang114

Kwai Keye-VL Technical Report

·
60 authors

Submitted by

CNcreator0331

LongAnimation: Long Animation Generation with Dynamic Global-Local Memory

·
4 authors

Submitted by

BBBBCHAN

Depth Anything at Any Condition

·
4 authors

Submitted by

Yifan-Zhong

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective

·
14 authors

Submitted by

yukangcao

FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model

·
4 authors

Submitted by

zhuoyang20

Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation

·
7 authors

Submitted by

penfever

MARVIS: Modality Adaptive Reasoning over VISualizations

·
4 authors

Submitted by

SiyouLi

μ^2Tokenizer: Differentiable Multi-Scale Multi-Modal Tokenizer for Radiology Report Generation

·
7 authors

Submitted by

jslee525

STR-Match: Matching SpatioTemporal Relevance Score for Training-Free Video Editing

·
3 authors

Submitted by

alex4727

JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching

·
5 authors

1

Submitted by

multimodalart

ARIG: Autoregressive Interactive Head Generation for Real-time Conversations

·
5 authors