Publications (36)
Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs
Feng Hong, Geng Yu, Yushi Ye +5
Diffusion Large Language Models (DLLMs) have emerged as a compelling alternative to Autoregressive models, designed for fast parallel generation. However, existing DLLMs are plague…
Learning to Instruct for Visual Instruction Tuning
Zhihan Zhou, Feng Hong, Jiaan Luo +5
We propose L2T, an advancement of visual instruction tuning (VIT). While VIT equips Multimodal LLMs (MLLMs) with promising multimodal capabilities, the current design choices for V…
Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems
Xuxin Cheng, Ke Zeng, Zhiquan Cao +65
Enhancing customer experience is essential for business success, particularly as service demands grow in scale and complexity. Generative artificial intelligence and Large Language…
Bag of Tricks for Long-Tailed Multi-Label Classification on Chest X-Rays
Feng Hong, Tianjie Dai, Jiangchao Yao +2
Clinical classification of chest radiography is particularly challenging for standard machine learning algorithms due to its inherent long-tailed and multi-label nature. However, f…
Unlocking air traffic flow prediction through microscopic aircraft-state modeling
Bin Wang, Anqi Liu, Jiangtao Zhao +8
Short-term air traffic flow prediction in terminal airspace is essential for proactive air traffic management. Existing approaches predominantly model traffic flow as aggregated ti…
A text-dependent speaker verification application framework based on Chinese numerical string corpus
Litong Zheng, Feng Hong, Weijie Xu
Researches indicate that text-dependent speaker verification (TD-SV) often outperforms text-independent verification (TI-SV) in short speech scenarios. However, collecting large-sc…
Machine Learning for Depression Screening and Intervention: an Original Circadian Rhythm Score-based Methodology
Bin Wang, Shuo Lian, Yuanyuan Hou +5
Depression screening from large-scale behavioral data is challenged by fragmented circadian indicators, limited interpretability, and the lack of intervention-oriented analysis. Ex…
Introducing the Brand New QiandaoEar22 Dataset for Specific Ship Identification Using Ship-Radiated Noise
Xiaoyang Du, Feng Hong
Target identification of ship-radiated noise is a crucial area in underwater target recognition. However, there is currently a lack of multi-target ship datasets that accurately re…
Evaluating Pavement Deterioration Rates Due to Flooding Events Using Explainable AI
Lidan Peng, Lu Gao, Feng Hong +1
Flooding can damage pavement infrastructure significantly, causing both immediate and long-term structural and functional issues. This research investigates how flooding events aff…
Long-Tailed Partial Label Learning via Dynamic Rebalancing
Feng Hong, Jiangchao Yao, Zhihan Zhou +2
Real-world data usually couples the label ambiguity and heavy imbalance, challenging the algorithmic robustness of partial label learning (PLL) and long-tailed learning (LT). The s…
Non-collective Calibrating Strategy for Time Series Forecasting
Bin Wang, Yongqi Han, Minbo Ma +4
Deep learning-based approaches have demonstrated significant advancements in time series forecasting. Despite these ongoing developments, the complex dynamics of time series make i…
A framework of text-dependent speaker verification for chinese numerical string corpus
Litong Zheng, Feng Hong, Weijie Xu +1
The Chinese numerical string corpus, serves as a valuable resource for speaker verification, particularly in financial transactions. Researches indicate that in short speech scenar…
Optimization-based Motion Planning for Autonomous Parking Considering Dynamic Obstacle: A Hierarchical Framework
Xuemin Chi, Zhitao Liu, Jihao Huang +2
This paper introduces a hierarchical framework that integrates graph search algorithms and model predictive control to facilitate efficient parking maneuvers for Autonomous Vehicle…
Cluster-Guided Unsupervised Domain Adaptation for Deep Speaker Embedding
Haiquan Mao, Feng Hong, Man-wai Mak
Recent studies have shown that pseudo labels can contribute to unsupervised domain adaptation (UDA) for speaker verification. Inspired by the self-training strategies that use an e…
DTMC-Based Analysis and Scheduling for Periodic Flows with Proactive HARQ
Haozhe Yi, Junyi Liu, Maolin Yang +5
Ultra-Reliable Low-Latency Communication (URLLC) requires strict reliability and latency guarantees for heterogeneous periodic traffic. Proactive HARQ improves resource efficiency…
From Time Series to State: Situation-Aware Modeling for Air Traffic Flow Prediction
Anqi Liu, Jiangtao Zhao, Guiyuan Jiang +3
Accurate air traffic prediction in the terminal airspace (TA) is pivotal for proactive air traffic management (ATM). However, existing data-driven approaches predominantly rely on…
UniChest: Conquer-and-Divide Pre-training for Multi-Source Chest X-Ray Classification
Tianjie Dai, Ruipeng Zhang, Feng Hong +3
Vision-Language Pre-training (VLP) that utilizes the multi-modal information to promote the training efficiency and effectiveness, has achieved great success in vision recognition…
Differential-informed Sample Selection Accelerates Multimodal Contrastive Learning
Zihua Zhao, Feng Hong, Mengxi Chen +5
The remarkable success of contrastive-learning-based multimodal models has been greatly driven by training on ever-larger datasets with expensive compute consumption. Sample select…
Diversified Batch Selection for Training Acceleration
Feng Hong, Yueming Lyu, Jiangchao Yao +3
The remarkable success of modern machine learning models on large datasets often demands extensive training time and resource consumption. To save cost, a prevalent research line,…
Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge
Gregory Holste, Yiliang Zhou, Song Wang +22
Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" $\unicode{x2013}$ there are a few common findings followed by many more rela…
Dual-granularity Sinkhorn Distillation for Enhanced Learning from Long-tailed Noisy Data
Feng Hong, Yu Huang, Zihua Zhao +5
Real-world datasets for deep learning frequently suffer from the co-occurring challenges of class imbalance and label noise, hindering model performance. While methods exist for ea…
Balanced Destruction-Reconstruction Dynamics for Memory-replay Class Incremental Learning
Yuhang Zhou, Jiangchao Yao, Feng Hong +2
Class incremental learning (CIL) aims to incrementally update a trained model with the new classes of samples (plasticity) while retaining previously learned ability (stability). T…
Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers
Fanqin Zeng, Feng Hong, Geng Yu +6
Diffusion Large Language Models (DLLMs) promise fast parallel generation, yet open-source DLLMs still face a severe quality-speed trade-off: accelerating decoding by revealing mult…
TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification
Haoyun Jiang, Junqi He, Feng Hong +8
Inference efficiency in Large Language Models (LLMs) is fundamentally limited by their serial, autoregressive generation, especially as reasoning becomes a key capability and respo…
Combating Representation Learning Disparity with Geometric Harmonization
Zhihan Zhou, Jiangchao Yao, Feng Hong +3
Self-supervised learning (SSL) as an effective paradigm of representation learning has achieved tremendous success on various curated datasets in diverse scenarios. Nevertheless, w…
Sophia: A Persistent Agent Framework of Artificial Life
Mingyang Sun, Feng Hong, Weinan Zhang
The development of LLMs has elevated AI agents from task-specific tools to long-lived, decision-making entities. Yet, most architectures remain static and reactive, tethered to man…
Long-tailed Recognition with Model Rebalancing
Jiaan Luo, Feng Hong, Qiang Hu +3
Long-tailed recognition is ubiquitous and challenging in deep learning and even in the downstream finetuning of foundation models, since the skew class distribution generally preve…
QiandaoEar22: A high quality noise dataset for identifying specific ship from multiple underwater acoustic targets using ship-radiated noise
Xiaoyang Du, Feng Hong
Target identification of ship-radiated noise is a crucial area in underwater target recognition. However, there is currently a lack of multi-target ship datasets that accurately re…
TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios
Yuanzhe Shen, Zisu Huang, Zhengyuan Wang +14
As LLM-based agents are deployed in increasingly complex real-world settings, existing benchmarks underrepresent key challenges such as enforcing global constraints, coordinating m…
Rejection Mixing: Fast Semantic Propagation of Mask Tokens for Efficient DLLM Inference
Yushi Ye, Feng Hong, Huangjie Zheng +4
Diffusion Large Language Models (DLLMs) promise fast non-autoregressive inference but suffer a severe quality-speed trade-off in parallel decoding. This stems from the ''combinator…
Search-Based Path Planning Algorithm for Autonomous Parking:Multi-Heuristic Hybrid A*
Jihao Huang, Zhitao Liu, Xuemin Chi +2
This paper proposed a novel method for autonomous parking. Autonomous parking has received a lot of attention because of its convenience, but due to the complex environment and the…
Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards
Yu Huang, Zihua Zhao, Zhaoxin Huan +9
The open-ended generation in LLMs usually requires multi-dimensional rubrics to adequately assess quality and guide the improvement of reinforcement learning. However, a critical d…
Personalized Deep Learning for Ventricular Arrhythmias Detection on Medical IoT Systems
Zhenge Jia, Zhepeng Wang, Feng Hong +3
Life-threatening ventricular arrhythmias (VA) are the leading cause of sudden cardiac death (SCD), which is the most significant cause of natural death in the US. The implantable c…
First Deep Learning Approach to Hammering Acoustics for Stem Stability Assessment in Total Hip Arthroplasty
Dongqi Zhu, Zhuwen Xu, Youyuan Chen +7
Audio event classification has recently emerged as a promising approach in medical applications. In total hip arthroplasty (THA), intra-operative hammering acoustics provide critic…
Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling
Ning Liao, Xiaoxing Wang, Zehao Lin +18
A large language model (LLM) with knowledge in both scientific and general tasks is the foundation of science general intelligence. However, directly continued pretraining an LLM u…
Deep Learning Framework for Infrastructure Maintenance: Crack Detection and High-Resolution Imaging of Infrastructure Surfaces
Nikhil M. Pawar, Jorge A. Prozzi, Feng Hong +1
Recently, there has been an impetus for the application of cutting-edge data collection platforms such as drones mounted with camera sensors for infrastructure asset management. Ho…