Knowledge Engineering Group (KEG) & Data Mining at Tsinghua University

THUDM's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts

jerytang 

authored a paper 10 days ago

MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models

Paper • 2501.02955 • Published 12 days ago • 40

yuxiaod 

authored a paper 10 days ago

MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models

Paper • 2501.02955 • Published 12 days ago • 40

ShiyuHuang 

authored a paper 10 days ago

MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models

Paper • 2501.02955 • Published 12 days ago • 40

LiquidAmmonia 

authored a paper 10 days ago

MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models

Paper • 2501.02955 • Published 12 days ago • 40

LiquidAmmonia 

updated a dataset 10 days ago

THUDM/MotionBench

Viewer • Updated 10 days ago • 5k • 773 • 2

bys0318 

in THUDM/LongBench-v2 11 days ago

In line 84 of pred.py, it says'retrieved = item["retrieved_context"][:args.rag]'. But where does this'retrieved_context' come from? item->data->data_all

2

#2 opened 26 days ago by

AmamiSora

LiquidAmmonia 

authored 3 papers 11 days ago

LVBench: An Extreme Long Video Understanding Benchmark

Paper • 2406.08035 • Published Jun 12, 2024 • 1

AlignMMBench: Evaluating Chinese Multimodal Alignment in Large Vision-Language Models

Paper • 2406.09295 • Published Jun 13, 2024

DreamPolish: Domain Score Distillation With Progressive Geometry Generation

Paper • 2411.01602 • Published Nov 3, 2024 • 10

ShiyuHuang 

authored a paper 12 days ago

VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation

Paper • 2412.21059 • Published 19 days ago • 18

jerytang 

authored a paper 12 days ago

VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation

Paper • 2412.21059 • Published 19 days ago • 18

yuxiaod 

authored a paper 12 days ago

VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation

Paper • 2412.21059 • Published 19 days ago • 18

xujz0703 

authored a paper 12 days ago

VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation

Paper • 2412.21059 • Published 19 days ago • 18

zRzRzRzRzRzRzR 

in THUDM/CogVideoX-5B-Space 12 days ago

Many errors for me

6

#28 opened about 1 month ago by

elgobe

ShiyuHuang 

updated a Space 14 days ago

Running

6

🐨

MotionBench Leaderboard

THUDM-Space 

updated 2 models 16 days ago

THUDM/glm-edge-v-2b

Image-Text-to-Text • Updated 16 days ago • 32.6k • 8

THUDM/glm-edge-v-5b

Image-Text-to-Text • Updated 16 days ago • 125 • 11

THUDM-Space 

in THUDM/glm-4-9b-chat 16 days ago

Converting to native Transformers

22

#81 opened 4 months ago by

cyrilvallez

适配新版transformers | adapt transformers update (https://github.com/huggingface/transformers/pull/31116)

2

#58 opened 7 months ago by

HibernantBear

Harness Evaluation

2

#56 opened 7 months ago by

VityaVitalich