-
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
Paper • 2507.02768 • Published • 18 -
STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models
Paper • 2507.15375 • Published • 29 -
SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models
Paper • 2510.06917 • Published • 33 -
Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
Paper • 2411.05361 • Published • 2
Ke-Han Lu
kehanlu
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
1 day ago
Awesome papers from 臺大李宏毅 (Hung-yi Lee)
updated
a collection
1 day ago
Awesome papers from 臺大李宏毅 (Hung-yi Lee)
updated
a collection
1 day ago
Awesome papers from 臺大李宏毅 (Hung-yi Lee)
Organizations
-
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
Paper • 2507.02768 • Published • 18 -
STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models
Paper • 2507.15375 • Published • 29 -
SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models
Paper • 2510.06917 • Published • 33 -
Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
Paper • 2411.05361 • Published • 2
models
9
kehanlu/9ae0a8ac-400a-440c-8a37-0358433875e1
Updated
kehanlu/my-cool-model
Updated
kehanlu/llama-3.2-8B-Instruct
Text Generation
•
8B
•
Updated
•
699
•
•
1
kehanlu/9285ae1c-5889-474e-b9f3-823d0eda4e21
Updated
kehanlu/share
Updated
kehanlu/llm32
Text Generation
•
10B
•
Updated
•
1
kehanlu/mandarin-wav2vec2-fairseq
Updated
kehanlu/mandarin-wav2vec2
Feature Extraction
•
Updated
•
30
kehanlu/mandarin-wav2vec2-aishell1
Automatic Speech Recognition
•
Updated
•
24
•
2