TVRBench: Target Viewpoint Reproduction Benchmark

university

https://github.com/aim-uofa/TVRBench

AI & ML interests

Embodied AI, Spatial Intelligence, Vision-Language Models

Recent Activity

llysglz updated a model about 18 hours ago

TVRBench/tvr-qwen3.5-9b-va-sft

llysglz published a model about 18 hours ago

TVRBench/tvr-qwen3.5-9b-va-sft

llysglz updated a dataset about 1 month ago

TVRBench/tvr-sft-va-cot

View all activity

models 2

TVRBench/tvr-qwen3.5-9b-va-sft

Image-Text-to-Text • 9B • Updated about 18 hours ago

TVRBench/tvr-qwen3.5-9b-va-sft-rl

Image-Text-to-Text • 9B • Updated Jun 2 • 5

datasets 2

TVRBench/tvr-sft-va-cot

Viewer • Updated Jun 2 • 1.6k • 72

TVRBench/tvr-sft-va

Viewer • Updated Jun 2 • 1.6k • 2.69k