-
UCSC-VLAA/ClinSeek-35B-A3B
Text Generation • 35B • Updated • 61 • 3 -
UCSC-VLAA/ClinSeek-Bench
Viewer • Updated • 2.79k • 177 • 2 -
UCSC-VLAA/ClinSeek-Evaluation-Results
Preview • Updated • 59 -
ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
Paper • 2605.20176 • Published • 12
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Chain-of-Experience for Continual LLM Improvement
VisualClaw: A Real-Time, Personalized Agent for the Physical World
A Family of Unified Visual Encoder with Unified Visual Representation.
-
UCSC-VLAA/gpt-image-edit-training
Image-to-Image • Updated • 26 -
UCSC-VLAA/GPT-Image-Edit-1.5M
Viewer • Updated • 2.78M • 5.6k • 89 -
GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset
Paper • 2507.21033 • Published • 23 -
UCSC-VLAA/gpt-image-edit-benchmark-results
Viewer • Updated • 1.21k • 44 • 1
-
UCSC-VLAA/MedVLThinker-3B-SFT_m23k
Image-Text-to-Text • 4B • Updated • 9 -
UCSC-VLAA/MedVLThinker-3B-SFT_PMC
Image-Text-to-Text • 4B • Updated • 16 -
UCSC-VLAA/MedVLThinker-7B-SFT_m23k
Image-Text-to-Text • 8B • Updated • 33 -
UCSC-VLAA/MedVLThinker-3B-SFT_m23k-RL_PMC
Image-Text-to-Text • 4B • Updated • 10 • 1
-
UCSC-VLAA/VLAA-Thinker-Qwen2.5VL-3B
Image-Text-to-Text • 4B • Updated • 829 • 5 -
UCSC-VLAA/VLAA-Thinker-Qwen2.5VL-7B
Image-Text-to-Text • 8B • Updated • 778 • 2 -
UCSC-VLAA/VLAA-Thinker-Qwen2VL-2B
Image-Text-to-Text • 2B • Updated • 670 • 1 -
UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B
Image-Text-to-Text • 8B • Updated • 610
-
UCSC-VLAA/m1-7B-1K
Question Answering • 8B • Updated • 41 • 1 -
m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models
Paper • 2504.00869 • Published • 11 -
UCSC-VLAA/m1-32B-1K
Question Answering • 33B • Updated • 15 -
UCSC-VLAA/m1-7B-23K
Question Answering • 8B • Updated • 292
CLIPS
Staged post-training along the perception → reasoning capability axis. Models, datasets, paper. ICML 2026.
-
UCSC-VLAA/VLM-CapCurriculum-Qwen3-VL-8B-Staged
Image-Text-to-Text • 9B • Updated • 13 -
UCSC-VLAA/VLM-CapCurriculum-Qwen2.5-VL-7B-Staged
Image-Text-to-Text • 8B • Updated • 5 -
UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged
Image-Text-to-Text • 8B • Updated • 8 -
UCSC-VLAA/VLM-CapCurriculum-InternVL3.5-8B-Staged
Image-Text-to-Text • 9B • Updated • 14
-
UCSC-VLAA/openvision2-vit-huge-patch14-224-vision-only
Image-to-Text • Updated • 14 • 1 -
UCSC-VLAA/openvision2-vit-giant-patch14-224-vision-only
Image-to-Text • Updated • 14 • 1 -
UCSC-VLAA/openvision2-vit-large-patch14-224-vision-only
Image-to-Text • Updated • 77 • 1 -
UCSC-VLAA/openvision2-vit-large-patch14-336-vision-only
Image-to-Text • Updated • 27 • 1
-
UCSC-VLAA/openvision-vit-tiny-patch16-224
Image Feature Extraction • Updated • 7 -
UCSC-VLAA/openvision-vit-tiny-patch8-224
Image Feature Extraction • Updated • 13 -
UCSC-VLAA/openvision-vit-tiny-patch16-384
Image Feature Extraction • Updated • 12 -
UCSC-VLAA/openvision-vit-tiny-patch8-160
Image Feature Extraction • Updated
-
UCSC-VLAA/MedReason-8B
Question Answering • 8B • Updated • 785 • 15 -
UCSC-VLAA/MedReason-Mistral
Question Answering • 266k • Updated • 13 -
UCSC-VLAA/MedReason
Viewer • Updated • 32.7k • 986 • 87 -
MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
Paper • 2504.00993 • Published • 3
-
UCSC-VLAA/ViT-bigG-14-CLIPA-datacomp1B
Zero-Shot Image Classification • Updated • 31 • 4 -
UCSC-VLAA/ViT-bigG-14-CLIPA-336-datacomp1B
Zero-Shot Image Classification • Updated • 92 • 4 -
UCSC-VLAA/ViT-L-14-CLIPA-336-datacomp1B
Zero-Shot Image Classification • Updated • 199 • 2 -
UCSC-VLAA/ViT-L-14-CLIPA-datacomp1B
Zero-Shot Image Classification • Updated • 233 • 3
-
UCSC-VLAA/ClinSeek-35B-A3B
Text Generation • 35B • Updated • 61 • 3 -
UCSC-VLAA/ClinSeek-Bench
Viewer • Updated • 2.79k • 177 • 2 -
UCSC-VLAA/ClinSeek-Evaluation-Results
Preview • Updated • 59 -
ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
Paper • 2605.20176 • Published • 12
Staged post-training along the perception → reasoning capability axis. Models, datasets, paper. ICML 2026.
-
UCSC-VLAA/VLM-CapCurriculum-Qwen3-VL-8B-Staged
Image-Text-to-Text • 9B • Updated • 13 -
UCSC-VLAA/VLM-CapCurriculum-Qwen2.5-VL-7B-Staged
Image-Text-to-Text • 8B • Updated • 5 -
UCSC-VLAA/VLM-CapCurriculum-InternVL3-8B-Staged
Image-Text-to-Text • 8B • Updated • 8 -
UCSC-VLAA/VLM-CapCurriculum-InternVL3.5-8B-Staged
Image-Text-to-Text • 9B • Updated • 14
A Family of Unified Visual Encoder with Unified Visual Representation.
-
UCSC-VLAA/openvision2-vit-huge-patch14-224-vision-only
Image-to-Text • Updated • 14 • 1 -
UCSC-VLAA/openvision2-vit-giant-patch14-224-vision-only
Image-to-Text • Updated • 14 • 1 -
UCSC-VLAA/openvision2-vit-large-patch14-224-vision-only
Image-to-Text • Updated • 77 • 1 -
UCSC-VLAA/openvision2-vit-large-patch14-336-vision-only
Image-to-Text • Updated • 27 • 1
-
UCSC-VLAA/gpt-image-edit-training
Image-to-Image • Updated • 26 -
UCSC-VLAA/GPT-Image-Edit-1.5M
Viewer • Updated • 2.78M • 5.6k • 89 -
GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset
Paper • 2507.21033 • Published • 23 -
UCSC-VLAA/gpt-image-edit-benchmark-results
Viewer • Updated • 1.21k • 44 • 1
-
UCSC-VLAA/openvision-vit-tiny-patch16-224
Image Feature Extraction • Updated • 7 -
UCSC-VLAA/openvision-vit-tiny-patch8-224
Image Feature Extraction • Updated • 13 -
UCSC-VLAA/openvision-vit-tiny-patch16-384
Image Feature Extraction • Updated • 12 -
UCSC-VLAA/openvision-vit-tiny-patch8-160
Image Feature Extraction • Updated
-
UCSC-VLAA/MedVLThinker-3B-SFT_m23k
Image-Text-to-Text • 4B • Updated • 9 -
UCSC-VLAA/MedVLThinker-3B-SFT_PMC
Image-Text-to-Text • 4B • Updated • 16 -
UCSC-VLAA/MedVLThinker-7B-SFT_m23k
Image-Text-to-Text • 8B • Updated • 33 -
UCSC-VLAA/MedVLThinker-3B-SFT_m23k-RL_PMC
Image-Text-to-Text • 4B • Updated • 10 • 1
-
UCSC-VLAA/VLAA-Thinker-Qwen2.5VL-3B
Image-Text-to-Text • 4B • Updated • 829 • 5 -
UCSC-VLAA/VLAA-Thinker-Qwen2.5VL-7B
Image-Text-to-Text • 8B • Updated • 778 • 2 -
UCSC-VLAA/VLAA-Thinker-Qwen2VL-2B
Image-Text-to-Text • 2B • Updated • 670 • 1 -
UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B
Image-Text-to-Text • 8B • Updated • 610
-
UCSC-VLAA/MedReason-8B
Question Answering • 8B • Updated • 785 • 15 -
UCSC-VLAA/MedReason-Mistral
Question Answering • 266k • Updated • 13 -
UCSC-VLAA/MedReason
Viewer • Updated • 32.7k • 986 • 87 -
MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
Paper • 2504.00993 • Published • 3
-
UCSC-VLAA/m1-7B-1K
Question Answering • 8B • Updated • 41 • 1 -
m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models
Paper • 2504.00869 • Published • 11 -
UCSC-VLAA/m1-32B-1K
Question Answering • 33B • Updated • 15 -
UCSC-VLAA/m1-7B-23K
Question Answering • 8B • Updated • 292
CLIPS
-
UCSC-VLAA/ViT-bigG-14-CLIPA-datacomp1B
Zero-Shot Image Classification • Updated • 31 • 4 -
UCSC-VLAA/ViT-bigG-14-CLIPA-336-datacomp1B
Zero-Shot Image Classification • Updated • 92 • 4 -
UCSC-VLAA/ViT-L-14-CLIPA-336-datacomp1B
Zero-Shot Image Classification • Updated • 199 • 2 -
UCSC-VLAA/ViT-L-14-CLIPA-datacomp1B
Zero-Shot Image Classification • Updated • 233 • 3