collaborators

7 papers

eess.AS2026

Compress the Cache, Not the Speech Embedding: KV Compression for Efficient Speech LLMs

Ke-Han Lu, Keqi Deng, Ruchao Fan +2

Speech large language models (Speech LLMs) typically encode speech into sequences far longer than text, creating a major efficiency bottleneck during autoregressive decoding. A com…

cs.CL2026

Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving

Ruchao Fan, Yiming Wang, Rui Zhao +10

Speech-LLM integration has shown promising results by leveraging extensive textual pretraining, yet its specific benefits for automatic speech recognition (ASR) remain unclear. We…

cs.AI2026

Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization

Jiawei Kong, Hao Fang, Shunxiang Liao +5

Multimodal Large Reasoning Models introduce the reasoning paradigm, demonstrating strong capabilities on complex vision-language tasks. However, they still suffer from severe hallu…

cs.CL2026

UNIQUE: Universal Top-k Sparse Attention for Training-free Inference and Sparsity-aware Training

Keqi Deng, Shaoshi Ling, Ruchao Fan +1

Long-context inference in large language models (LLMs) is bottlenecked by the linear growth of the self-attention key-value (KV) cache. Top-k sparse attention alleviates this by lo…

cs.CL2026

Speech LLMs are Contextual Reasoning Transcribers

Keqi Deng, Ruchao Fan, Bo Ren +2

Despite extensions to speech inputs, effectively leveraging the rich knowledge and contextual understanding of large language models (LLMs) in automatic speech recognition (ASR) re…

eess.AS2025

Train Short, Infer Long: Speech-LLM Enables Zero-Shot Streamable Joint ASR and Diarization on Long Audio

Mohan Shi, Xiong Xiao, Ruchao Fan +2

Joint automatic speech recognition (ASR) and speaker diarization aim to answer the question "who spoke what" in multi-speaker scenarios. In this paper, we present an end-to-end spe…