SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models
Paper
•
2510.06917
•
Published
•
34
Lijuan Wang
Lijuan
AI & ML interests
AGI
Recent Activity
upvoted
a
paper
19 days ago
SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models
authored
a paper
4 months ago
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual
Perception in VLMs
authored
a paper
7 months ago
SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual
Reasoning Self-Improvement
Organizations
upvoted
a
paper
19 days ago