2 citations · 2 across the 17 of their papers we have counts for
18 papers
FlowCTS: On-policy Continuous Trajectory Supervision of Flow Models
Kaiyang Ye, Yuan Ge, Junxiang Zhang +8
While on-policy distillation (OPD) effectively addresses sparse rewards and exposure bias in large language model post-training, its extension to flow models remains underexplored.…
ToFu: A White-Box, Token-Efficient Agent Harness for Researchers
Junhao Ruan, Yuan Ge, Bei Li +7
Agentic coding tools present new opportunities to transform research workflows. The performance of agent systems built depends on both large language models (LLMs) and the harness…
DirectAudioEdit: Inversion-Free Text-Guided Audio Editing via Diffusion Prediction Contrast
Zhengkun Ge, Xiaoqian Liu, Haoran Zhang +5
Text-guided audio editing aims to modify the language-specified acoustic content while preserving edit-irrelevant source components. Existing training-free methods typically rely o…
On the Emotion Understanding of Synthesized Speech
Yuan Ge, Haishu Zhao, Aokai Hao +10
Emotion is a core paralinguistic feature in voice interaction. It is widely believed that emotion understanding models learn fundamental representations that transfer to synthesize…
StyleBench: Evaluating Speech Language Models on Conversational Speaking Style Control
Haishu Zhao, Aokai Hao, Yuan Ge +3
Speech language models (SLMs) have significantly extended the interactive capability of text-based Large Language Models (LLMs) by incorporating paralinguistic information. For mor…
When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning
Ruixiang Mao, Xiangnan Ma, Dan Chen +12
Test-Time Scaling has shown notable efficacy in addressing complex problems through scaling inference compute. However, within Large Audio-Language Models (LALMs), an unintuitive p…
VisualActBench: Can VLMs See and Act like a Human?
Daoan Zhang, Pai Liu, Xiaofei Zhou +6
Vision-Language Models (VLMs) have achieved impressive progress in perceiving and describing visual environments. However, their ability to proactively reason and act based solely…
M-CIF: Multi-Scale Alignment For CIF-Based Non-Autoregressive ASR
Ruixiang Mao, Xiangnan Ma, Qing Yang +7
The Continuous Integrate-and-Fire (CIF) mechanism provides effective alignment for non-autoregressive (NAR) speech recognition. This mechanism creates a smooth and monotonic mappin…
SUBQRAG: Sub-Question Driven Dynamic Graph RAG
Jiaoyang Li, Junhao Ruan, Shengwei Tang +5
Graph Retrieval-Augmented Generation (Graph RAG) effectively builds a knowledge graph (KG) to connect disparate facts across a large document corpus. However, this broad-view appro…
MTP-S2UT: Enhancing Speech-to-Speech Translation Quality with Multi-token Prediction
Jianjin Wang, Runsong Zhao, Xiaoqian Liu +6
Current direct speech-to-speech translation methods predominantly employ speech tokens as intermediate representations. However, a single speech token is not dense in semantics, so…
FLEXI: Benchmarking Full-duplex Human-LLM Speech Interaction
Yuan Ge, Saihan Chen, Jingqi Xiao +5
Full-Duplex Speech-to-Speech Large Language Models (LLMs) are foundational to natural human-computer interaction, enabling real-time spoken dialogue systems. However, benchmarking…
Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System
Yanfan Du, Jun Zhang, Bin Wang +6
Recent advances in speech large language models (SLMs) have improved speech recognition and translation in general domains, but accurately generating domain-specific terms or neolo…
SageLM: A Multi-aspect and Explainable Large Language Model for Speech Judgement
Yuan Ge, Junxiang Zhang, Xiaoqian Liu +10
Speech-to-Speech (S2S) Large Language Models (LLMs) are foundational to natural human-computer interaction, enabling end-to-end spoken dialogue systems. However, evaluating these m…
Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models
Kaiyan Chang, Yonghao Shi, Chenglong Wang +7
Test-Time Scaling (TTS) is a promising approach to progressively elicit the model's intelligence during inference. Recently, training-based TTS methods, such as continued reinforce…
A Modular-based Strategy for Mitigating Gradient Conflicts in Simultaneous Speech Translation
Xiaoqian Liu, Yangfan Du, Jianjin Wang +5
Simultaneous Speech Translation (SimulST) involves generating target language text while continuously processing streaming speech input, presenting significant real-time challenges…
NDP: Next Distribution Prediction as a More Broad Target
Junhao Ruan, Abudukeyumu Abudula, Xinyu Liu +7
Large language models (LLMs) trained on next-token prediction (NTP) paradigm have demonstrated powerful capabilities. However, the existing NTP paradigm contains several limitation…
RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners
Chi Hu, Yuan Ge, Xiangnan Ma +5
Large Language Models (LLMs) have achieved impressive performance across various reasoning tasks. However, even state-of-the-art LLMs such as ChatGPT are prone to logical errors du…
Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation
Yuan Ge, Yilun Liu, Chi Hu +10
With contributions from the open-source community, a vast amount of instruction tuning (IT) data has emerged. Given the significant resource allocation required for training and ev…