4 23 3

Baifeng Shi

bfshi

https://bfshi.github.io

AI & ML interests

computer vision

Recent Activity

published a Space about 4 hours ago

bfshi/VILA-HD-demo

updated a Space about 9 hours ago

bfshi/VILA-HD-demo

upvoted a paper 1 day ago

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling

View all activity

Organizations

bfshi's activity

published a Space about 4 hours ago

VILA-HD

🏆

VILA-HD Playground.

updated a Space about 9 hours ago

VILA-HD

🏆

VILA-HD Playground.

upvoted a paper 1 day ago

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling

Paper • 2504.13169 • Published 3 days ago • 34

upvoted a paper 2 days ago

CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training

Paper • 2504.13161 • Published 3 days ago • 80

upvoted 2 papers 11 days ago

One-Minute Video Generation with Test-Time Training

Paper • 2504.05298 • Published 13 days ago • 94

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published 13 days ago • 162

authored a paper 25 days ago

Scaling Vision Pre-Training to 4K Resolution

Paper • 2503.19903 • Published 26 days ago • 40

upvoted a paper 25 days ago

Scaling Vision Pre-Training to 4K Resolution

Paper • 2503.19903 • Published 26 days ago • 40

commented a paper 25 days ago

Scaling Vision Pre-Training to 4K Resolution

Paper • 2503.19903 • Published 26 days ago • 40 •

published a dataset 2 months ago

bfshi/vstar_bench_lmms_eval

Viewer • Updated Nov 1, 2024 • 191 • 61

New activity in Efficient-Large-Model/NVILA-8B-Video 3 months ago

What is the difference between the nvila 8b base model and video model?

#1 opened 3 months ago by

YoungjaeDev

upvoted 2 papers 3 months ago

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published Jan 28 • 120

An Empirical Study of Autoregressive Pre-training from Videos

Paper • 2501.05453 • Published Jan 9 • 42

New activity in Efficient-Large-Model/NVILA-15B 3 months ago

Ask about demo

#1 opened 4 months ago by

Lanbai44

liked 2 models 4 months ago

Efficient-Large-Model/NVILA-15B

Text Generation • Updated Jan 6 • 21.6k • 15

Efficient-Large-Model/NVILA-8B

Text Generation • Updated Jan 6 • 20.2k • 4

upvoted a collection 4 months ago

NVILA

Collection

9 items • Updated 3 days ago • 9

liked a Space 4 months ago

VILA

🏆

VILA Playground.

authored a paper 4 months ago

NVILA: Efficient Frontier Visual Language Models

Paper • 2412.04468 • Published Dec 5, 2024 • 60

upvoted a paper 4 months ago

NVILA: Efficient Frontier Visual Language Models

Paper • 2412.04468 • Published Dec 5, 2024 • 60