28 citations · 29 across the 23 of their papers we have counts for
14 papers · 1 filter
Not Too Hard, Not Too Easy: Learning from Intermediate States for LLM Structured Reasoning
Hongbo Chen, Guohua Lu, Ting Dang +1
A common principle of effective learning is to practice material that is neither already mastered nor too difficult to permit progress. We ask how to apply this principle to struct…
Listen Then Reason: Perception-Grounded Test-Time Reinforcement Learning for Large Audio-Language Models
Jiaheng Dong, Xiaofeng Yu, Jean Honorio +3
Large audio-language models (LALMs) are increasingly used for a broader range of audio reasoning tasks. These models typically incorporate audio representations into a large langua…
Flower Hub: A Reproducible Benchmarking Platform for Federated Learning in Simulation and Deployment
Yan Gao, Mohammad Naseri, Javier Fernandez-Marques +19
Federated learning (FL) has emerged as a key approach for training models across decentralized data, yet benchmarking in FL remains difficult to reproduce, compare, and extend. Exi…
Efficient Multimodal Clinical Question Answering for Pulmonary Embolism Risk Assessment
Xiangyuan Xue, Yang Yu, Yan Gao +5
Pulmonary embolism (PE) is a high risk cardiopulmonary condition whose management requires both timely diagnosis and reliable assessment of future clinical risk. Because PE care ro…
Pocket-Dentist: On-Device Dental Image Understanding via Efficient Multimodal Large Language Models
Kai Bian, Xucheng Guo, Bin Chen +4
Evaluations of dental vision-language models remain fragmented across datasets, task definitions and metrics, and often ignore their computational cost. This limits their widesprea…
VitalAgent: A Tool-Augmented Agent for Reactive and Proactive Physiological Monitoring over Wearable Health Data
Di Zhu, Yu Yvonne Wu, Hong Jia +3
Wearable devices enable continuous monitoring of physiological signals such as ECG and PPG, but existing mHealth systems are largely limited to task-specific prediction pipelines o…
HoRD: Robust Humanoid Control via History-Conditioned Reinforcement Learning and Online Distillation
Puyue Wang, Jiawei Hu, Yan Gao +7
Humanoid robots can suffer significant performance drops under small changes in dynamics, task specifications, or environment setup. We propose HoRD, a two-stage learning framework…
Edge-Cloud Collaborative Speech Emotion Captioning via Token-Level Speculative Decoding in Audio-Language Models
Xiangyuan Xue, Jiajun Lu, Yan Gao +3
Speech Emotion Captioning (SEC) leverages large audio-language models to generate rich, context-aware affective descriptions from speech. However, real-world deployment remains cha…
Disentangling Reasoning in Large Audio-Language Models for Ambiguous Emotion Prediction
Xiaofeng Yu, Jiaheng Dong, Jean Honorio +3
Speech emotion recognition plays an important role in various applications. However, most existing approaches predict a single emotion label, oversimplifying the inherently ambiguo…
Localizing and Editing Knowledge in Large Audio-Language Models
Sung Kyun Chung, Jiaheng Dong, Qiuchi Hu +3
Large Audio-Language Models (LALMs) have shown strong performance in speech understanding, making speech a natural interface for accessing factual information. Yet they are trained…
LQA: A Lightweight Quantized-Adaptive Framework for Vision-Language Models on the Edge
Xin Wang, Hong Jia, Hualin Zhou +4
Deploying Vision-Language Models (VLMs) on edge devices is challenged by resource constraints and performance degradation under distribution shifts. While test-time adaptation (TTA…
Rethinking Perplexity: Revealing the Impact of Input Length on Perplexity Evaluation in LLMs
Letian Cheng, Junyan Wang, Yan Gao +3
Perplexity is a widely adopted metric for assessing the predictive quality of large language models (LLMs) and often serves as a reference metric for downstream evaluations. Howeve…
Test-Time Adaptation for Speech Emotion Recognition
Jiaheng Dong, Hong Jia, Ting Dang
The practical utility of Speech Emotion Recognition (SER) systems is undermined by their fragility to domain shifts, such as speaker variability, the distinction between acted and…
AdaNODEs: Test Time Adaptation for Time Series Forecasting Using Neural ODEs
Ting Dang, Soumyajit Chatterjee, Hong Jia +3
Test time adaptation (TTA) has emerged as a promising solution to adapt pre-trained models to new, unseen data distributions using unlabeled target domain data. However, most TTA m…