Article
nanoVLM: The simplest repository to train your VLM in pure PyTorch
•
229
Gullal Singh Cheema
gullalc
AI & ML interests
Multimodality, Vision and Language, Cross-modal relations, Video Understanding
Recent Activity
upvoted
an
article
about 1 month ago
nanoVLM: The simplest repository to train your VLM in pure PyTorch
upvoted
an
article
about 1 month ago
Efficient MultiModal Data Pipeline
upvoted
a
paper
about 1 month ago
FineVision: Open Data Is All You Need
Organizations
None yet
upvoted
2
articles
about 1 month ago
Article
Efficient MultiModal Data Pipeline
•
59
upvoted
a
paper
about 1 month ago
liked
a
dataset
3 months ago
reacted to
sergiopaniego's
post with 🔥
4 months ago
Post
3454
Want to learn how to align a Vision Language Model (VLM) for reasoning using GRPO and TRL? 🌋
🧑🍳 We've got you covered!!
NEW multimodal post training recipe to align a VLM using TRL in @HuggingFace 's Cookbook.
Go to the recipe 👉https://huggingface.co/learn/cookbook/fine_tuning_vlm_grpo_trl
Powered by the latest TRL v0.20 release, this recipe shows how to teach Qwen2.5-VL-3B-Instruct to reason over images 🌋
🧑🍳 We've got you covered!!
NEW multimodal post training recipe to align a VLM using TRL in @HuggingFace 's Cookbook.
Go to the recipe 👉https://huggingface.co/learn/cookbook/fine_tuning_vlm_grpo_trl
Powered by the latest TRL v0.20 release, this recipe shows how to teach Qwen2.5-VL-3B-Instruct to reason over images 🌋
upvoted
a
collection
4 months ago
liked
2
models
4 months ago
commented
a
paper
5 months ago
upvoted
9
papers
5 months ago
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
Paper
•
2506.09985
•
Published
•
29
SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification
Paper
•
2506.15569
•
Published
•
12
CoMemo: LVLMs Need Image Context with Image Memory
Paper
•
2506.06279
•
Published
•
8
Time Blindness: Why Video-Language Models Can't See What Humans Can?
Paper
•
2505.24867
•
Published
•
80
VLM-R^3: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought
Paper
•
2505.16192
•
Published
•
12
VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation
Paper
•
2505.14640
•
Published
•
16
Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning
Paper
•
2505.15966
•
Published
•
53
UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning
Paper
•
2505.14231
•
Published
•
52
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
Paper
•
2505.11049
•
Published
•
60
upvoted
2
papers
6 months ago