RL checkpoints of Octopus-8B and baselines of paper: Learning Self-Correction in Vision–Language Models via Rollout Augmentation
Yi Ding
Tuwhy
AI & ML interests
None yet
Recent Activity
authored a paper 2 days ago
Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control authored a paper 2 days ago
Learning Self-Correction in Vision-Language Models via Rollout Augmentation updated a collection 3 days ago
On-Policy Self-AdaptationOrganizations
Series model of paper "Sherlock: Self-Correcting Reasoning in Vision-Language Models"
-
Tuwhy/Llama-3.2V-11B-Sherlock-SFT
Image-Text-to-Text • 11B • Updated • 3 -
Tuwhy/Llama-3.2V-11B-Sherlock-Offline
Image-Text-to-Text • 11B • Updated -
Tuwhy/Llama-3.2V-11B-Sherlock-iter1
Image-Text-to-Text • 11B • Updated • 5 -
Tuwhy/Llama-3.2V-11B-Sherlock-iter2
Image-Text-to-Text • 11B • Updated • 18 • 2
Official model collection of paper: Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
RL checkpoints of Octopus-8B and baselines of paper: Learning Self-Correction in Vision–Language Models via Rollout Augmentation
Series model of paper "Sherlock: Self-Correcting Reasoning in Vision-Language Models"
-
Tuwhy/Llama-3.2V-11B-Sherlock-SFT
Image-Text-to-Text • 11B • Updated • 3 -
Tuwhy/Llama-3.2V-11B-Sherlock-Offline
Image-Text-to-Text • 11B • Updated -
Tuwhy/Llama-3.2V-11B-Sherlock-iter1
Image-Text-to-Text • 11B • Updated • 5 -
Tuwhy/Llama-3.2V-11B-Sherlock-iter2
Image-Text-to-Text • 11B • Updated • 18 • 2
Official dataset collection of paper: Rethinking Bottleneck in Safety Fine-Tuning of Vision Language Models
Official model collection of paper: Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models