Zhongguancun Academy

university

https://www.bjzgca.edu.cn/

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

VLyb submitted a paper 2 days ago

FrameSkip: Learning from Fewer but More Informative Frames in VLA Training

MaplesWCT submitted a paper 3 months ago

ScalSelect: Scalable Training-Free Multimodal Data Selection for Efficient Visual Instruction Tuning

VLyb submitted a paper 4 months ago

TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers

View all activity

Papers

FrameSkip: Learning from Fewer but More Informative Frames in VLA Training

ScalSelect: Scalable Training-Free Multimodal Data Selection for Efficient Visual Instruction Tuning

View all Papers

ZGCA 's Papers 8

Submitted by

yubin

FrameSkip: Learning from Fewer but More Informative Frames in VLA Training

Zhongguancun Academy

2 1

Submitted by

Changti Wu

ScalSelect: Scalable Training-Free Multimodal Data Selection for Efficient Visual Instruction Tuning

Zhongguancun Academy

4 2

Submitted by

Shijie Lian

BayesianVLA: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries

Zhongguancun Academy

7 4

Submitted by

yubin

TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers

Zhongguancun Academy

27 3

DynaSolidGeo: A Dynamic Benchmark for Genuine Spatial Mathematical Reasoning of VLMs in Solid Geometry

Zhongguancun Academy

Submitted by

yubin

TrajSelector: Harnessing Latent Representations for Efficient and Effective Best-of-N in Large Reasoning Model

Zhongguancun Academy

Submitted by

bohan zeng

MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning

Zhongguancun Academy

13 3

Submitted by

Shijie Lian

Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks

Zhongguancun Academy

28 3

AI & ML interests

Recent Activity

Papers

Team members 1