Scholar
Keqi Deng
Google Scholar ID: zJTbptgAAAAJ
University of Cambridge
Speech processing
Translation
Large language model
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
632
H-index
12
i10-index
14
Publications
20
Co-authors
0
Contact
No contact links provided.
Publications
10 items
Compress the Cache, Not the Speech Embedding: KV Compression for Efficient Speech LLMs
2026
Cited
0
Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving
2026
Cited
0
OpenSTBench: Beyond Semantic Evaluation for Speech Translation
2026
Cited
0
UNIQUE: Universal Top-k Sparse Attention for Training-free Inference and Sparsity-aware Training
2026
Cited
0
Speech LLMs are Contextual Reasoning Transcribers
2026
Cited
0
MCAT: Scaling Many-to-Many Speech-to-Text Translation with MLLMs to 70 Languages
2025
Cited
0
Multi-head Temporal Latent Attention
2025
Cited
0
SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation
2025
Cited
0
Load more
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
