Xi'an Jiaotong University

university

http://en.xjtu.edu.cn/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

shuojiang updated a Space 29 days ago

XJTU-AI/README

xufangzhi authored a paper about 2 months ago

OS-ATLAS: A Foundation Action Model for Generalist GUI Agents

qizekun authored a paper 6 months ago

Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast

View all activity

XJTU-AI's activity

shuojiang

updated a Space 29 days ago

README

xufangzhi

authored a paper about 2 months ago

OS-ATLAS: A Foundation Action Model for Generalist GUI Agents

Paper • 2410.23218 • Published Oct 30, 2024 • 46

qizekun

authored 2 papers 6 months ago

Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast

Paper • 2305.19623 • Published May 31, 2023

DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation

Paper • 2406.16855 • Published Jun 24, 2024 • 54

xufangzhi

authored 4 papers 6 months ago

Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond

Paper • 2306.09841 • Published Jun 16, 2023 • 2

Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models

Paper • 2311.09278 • Published Nov 15, 2023 • 7

PathReasoner: Modeling Reasoning Path with Equivalent Extension for Logical Question Answering

Paper • 2405.19109 • Published May 29, 2024 • 2

Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models

Paper • 2406.11736 • Published Jun 17, 2024 • 5

xufangzhi

posted an update 6 months ago

Post

468

📣Thrilled to make public our recent work ENVISIONS !!!

- Without human annotations !
- Without Distilling Strong LLMs !
- Self-improve LLMs in the environment
- Amazing performances on agentic and reasoning tasks
- Insightful analysis on "why" questions

📝 Title: Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models

📎 Repo: https://github.com/xufangzhi/ENVISIONS

qizekun

authored 3 papers 9 months ago

VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation

Paper • 2307.16605 • Published Jul 28, 2023

Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining

Paper • 2302.02318 • Published Feb 5, 2023

Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?

Paper • 2212.08320 • Published Dec 16, 2022

qizekun

authored a paper 10 months ago

ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

Paper • 2402.17766 • Published Feb 27, 2024

xjcvcvxj

authored 2 papers about 1 year ago

Towards Garment Sewing Pattern Reconstruction from a Single Image

Paper • 2311.04218 • Published Nov 7, 2023 • 2

Instant3D: Instant Text-to-3D Generation

Paper • 2311.08403 • Published Nov 14, 2023 • 45

qizekun

authored a paper over 1 year ago

DreamLLM: Synergistic Multimodal Comprehension and Creation

Paper • 2309.11499 • Published Sep 20, 2023 • 58

xjcvcvxj

authored a paper over 1 year ago

NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF

Paper • 2307.09112 • Published Jul 18, 2023 • 8

shuojiang

updated a Space over 1 year ago

README