马嘉祺

jiaqima1

AI & ML interests

None yet

Recent Activity

upvoted a paper 16 days ago

onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction

upvoted a paper 3 months ago

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

liked a model 9 months ago

stepfun-ai/Step3-VL-10B-Base

View all activity

Organizations

None yet

upvoted a paper 16 days ago

onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction

Paper • 2609.24983 • Published 18 days ago • 55

upvoted a paper 3 months ago

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

Paper • 2606.28322 • Published Jun 26 • 42

upvoted a collection 9 months ago

Step3-VL-10B

3 items • Updated Feb 2 • 36

upvoted 3 papers 9 months ago

STEP3-VL-10B Technical Report

Paper • 2601.09668 • Published Jan 14 • 197

BabyVision: Visual Reasoning Beyond Language

Paper • 2601.06521 • Published Jan 10 • 202

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning

Paper • 2601.05593 • Published Jan 9 • 87