4 citations · 7 across the 12 of their papers we have counts for
13 papers
PW-Pruning: Phase-Aware Expert Selection for Speech-Centric Omni-Modal Models
Junjie Cao, Fengping Tian, Wenjie Zhou +5
Sparse routing reduces per-token computation but leaves the full expert bank resident in memory. We study expert pruning for speech-centric omni-modal models, where pooling calibra…
What Matters for Aggressive Decoding-Time KV Eviction? Temporal Aggregation and Ranking Preservation
Bo Zeng, Yu Zhao, Yefeng Liu +3
Decoding-time KV cache compression research focuses heavily on designing better token scoring functions, while the temporal rule that aggregates scores across decode steps is often…
WnW: Waxing-and-Waning KV Cache for Long-Form Speech LLMs
Yiming Yao, Chenyang Lyu, Xuanfan Ni +4
Long-form audio inputs make the KV cache the dominant memory cost of speech LLMs. Prefill-only KV compression methods permanently discard audio KV positions once evicted, with no p…
Speech-XL: Towards Long-Form Speech Understanding in Large Speech Language Models
Haoqin Sun, Chenyang Lyu, Shiwan Zhao +5
Despite the growing success of Large Speech Language Models (LSLMs) in processing short-term acoustic signals, their extension to long-form audio understanding is severely bottlene…
LongSpeech: A Scalable Benchmark for Transcription, Translation and Understanding in Long Speech
Fei Yang, Xuanfan Ni, Renyi Yang +7
Recent advances in audio-language models have demonstrated remarkable success on short, segment-level speech tasks. However, real-world applications such as meeting transcription,…
Marco-ASR: A Principled and Metric-Driven Framework for Fine-Tuning Large-Scale ASR Models for Domain Adaptation
Xuanfan Ni, Fei Yang, Fengping Tian +6
Automatic Speech Recognition (ASR) models have achieved remarkable accuracy in general settings, yet their performance often degrades in domain-specific applications due to data mi…
Marco-Voice Technical Report
Fengping Tian, Chenyang Lyu, Xuanfan Ni +8
This paper presents a multifunctional speech synthesis system that integrates voice cloning and emotion control speech synthesis within a unified framework. The goal of this work i…
Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language Models
Bo Zeng, Chenyang Lyu, Sinuo Liu +14
Instruction-following capability has become a major ability to be evaluated for Large Language Models (LLMs). However, existing datasets, such as IFEval, are either predominantly m…
Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models
Huifeng Yin, Yu Zhao, Minghao Wu +9
Large Reasoning Models(LRMs) such as OpenAI o1 and DeepSeek-R1 have shown remarkable reasoning capabilities by scaling test-time compute and generating long Chain-of-Thought(CoT).…
ReFreeKV: Towards Threshold-Free KV Cache Compression
Xuanfan Ni, Liyan Xu, Chenyang Lyu +6
To reduce memory consumption during LLM inference, a handful of methods have been proposed for KV cache pruning. While these techniques can accomplish lossless memory reduction on…
A Systematic Evaluation of Large Language Models for Natural Language Generation Tasks
Xuanfan Ni, Piji Li
Recent efforts have evaluated large language models (LLMs) in areas such as commonsense reasoning, mathematical reasoning, and code generation. However, to the best of our knowledg…
XLBench: A Benchmark for Extremely Long Context Understanding with Long-range Dependencies
Xuanfan Ni, Hengyi Cai, Xiaochi Wei +3
Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks but are constrained by their small context window sizes. Various efforts have been propos…
Unified Text Structuralization with Instruction-tuned Language Models
Xuanfan Ni, Piji Li, Huayang Li
Text structuralization is one of the important fields of natural language processing (NLP) consists of information extraction (IE) and structure formalization. However, current stu…