shawn's picture

3

shawn

ares0728

AI & ML interests

None yet

Recent Activity

published a model 2 minutes ago

ares0728/qwen3-vl-8b-900

updated a model about 1 hour ago

ares0728/qwen3-vl-8b-800

published a model about 2 hours ago

ares0728/qwen3-vl-8b-800

View all activity

Organizations

None yet

upvoted a paper 3 months ago

ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping

Paper • 2510.08457 • Published Oct 9 • 12

upvoted a collection 3 months ago

ARES

🌴ARES is an open-source framework for adaptive multimodal reasoning, using difficulty-aware training and entropy-shaped policy optimization. • 5 items • Updated Oct 12 • 2

upvoted a paper 7 months ago

Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning

Paper • 2506.04207 • Published Jun 4 • 48