Publications (25)
Variance Reduction via Resampling and Experience Replay
Jiale Han, Xiaowu Dai, Yuhua Zhu
Experience replay is a foundational technique in reinforcement learning that enhances learning stability by storing past experiences in a replay buffer and reusing them during trai…
Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models
Shuhao Zhang, Yuli Chen, Jiale Han +2
Watermarking provides a critical safeguard for large language model (LLM) services by facilitating the detection of LLM-generated text. Correspondingly, stealing watermark algorith…
SimDiff: Depth Pruning via Similarity and Difference
Yuli Chen, Shuhao Zhang, Fanshen Meng +4
Depth pruning improves the deployment efficiency of large language models (LLMs) by identifying and removing redundant layers. A widely accepted standard for this identification pr…
Auto-bidding under Return-on-Spend Constraints with Uncertainty Quantification
Jiale Han, Chun Gan, Chengcheng Zhang +4
Auto-bidding systems are widely used in advertising to automatically determine bid values under constraints such as total budget and Return-on-Spend (RoS) targets. Existing works o…
Aethorix v1.0: An Integrated Scientific AI Agent for Scalable Inorganic Materials Innovation and Industrial Implementation
Yingjie Shi, Yiru Gong, Yiqun Su +3
Artificial Intelligence (AI) is redefining the frontiers of scientific domains, ranging from drug discovery to meteorological modeling, yet its integration within industrial manufa…
Incentivizing Truthful Language Models via Peer Elicitation Games
Baiting Chen, Tong Zhu, Jiale Han +3
Large Language Models (LLMs) have demonstrated strong generative capabilities but remain prone to inconsistencies and hallucinations. We introduce Peer Elicitation Games (PEG), a t…
Online Auction Design Using Distribution-Free Uncertainty Quantification with Applications to E-Commerce
Jiale Han, Xiaowu Dai
Online auction is a cornerstone of e-commerce, and a key challenge is designing incentive-compatible mechanisms that maximize expected revenue. Existing approaches often assume kno…
A Multi-view Landmark Representation Approach with Application to GNSS-Visual-Inertial Odometry
Tong Hua, Jiale Han, Wei Ouyang
Invariant Extended Kalman Filter (IEKF) has been a significant technique in vision-aided sensor fusion. However, it usually suffers from high computational burden when jointly opti…
Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering
Xu Wang, Shuai Zhao, Bo Cheng +5
Question Answering (QA) models over Knowledge Bases (KBs) are capable of providing more precise answers by utilizing relation information among entities. Although effective, most o…
DialogueAgents: A Hybrid Agent-Based Speech Synthesis Framework for Multi-Party Dialogue
Xiang Li, Duyi Pan, Hongru Xiao +5
Speech synthesis is crucial for human-computer interaction, enabling natural and intuitive communication. However, existing datasets involve high construction costs due to manual a…
A Robust Multi-Item Auction Design with Statistical Learning
Jiale Han, Xiaowu Dai
We propose a novel statistical learning method for multi-item auctions that incorporates credible intervals. Our approach employs nonparametric density estimation to estimate credi…
Generative Prompt Tuning for Relation Classification
Jiale Han, Shuai Zhao, Bo Cheng +2
Using prompts to explore the knowledge contained within pre-trained language models for downstream tasks has now become an active topic. Current prompt tuning methods mostly conver…
Mechanism Design for Quality-Preserving LLM Advertising
Jiale Han, Xiaowu Dai
Embedding advertisements into large language model (LLM) outputs introduces a fundamental tension: revenue optimization can distort content and degrade user experience. Existing ap…
Adapting General-Purpose Embedding Models to Private Datasets Using Keyword-based Retrieval
Yubai Wei, Jiale Han, Yi Yang
Text embedding models play a cornerstone role in AI applications, such as retrieval-augmented generation (RAG). While general-purpose text embedding models demonstrate strong perfo…
CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models
Xiang Li, Fan Bu, Ambuj Mehrish +4
Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), hold…
An Immediate Update Strategy of Multi-State Constraint Kalman Filter
Qingchao Zhang, Wei Ouyang, Jiale Han +3
The lightweight Multi-state Constraint Kalman Filter (MSCKF) has been well-known for its high efficiency, in which the delayed update has been usually adopted since its proposal. T…
HiMed: Incentivizing Hindi Reasoning in Medical LLMs
Dingfeng Jiang, Han Yan, Chenze Ma +12
Medical large language models hold promise for reducing healthcare disparities, yet Hindi remains severely underrepresented. While medical LLMs excel in high-resource languages, th…
CT-ESKF: A General Framework of Covariance Transformation-Based Error-State Kalman Filter
Jiale Han, Wei Ouyang, Maoran Zhu +1
Invariant extended Kalman filter (InEKF) possesses excellent trajectory-independent property and better consistency compared to conventional extended Kalman filter (EKF). However,…
DLP: Dynamic Layerwise Pruning in Large Language Models
Yuli Chen, Bo Cheng, Jiale Han +3
Pruning has recently been widely adopted to reduce the parameter scale and improve the inference efficiency of Large Language Models (LLMs). Mainstream pruning techniques often rel…
Exploring Task Difficulty for Few-Shot Relation Extraction
Jiale Han, Bo Cheng, Wei Lu
Few-shot relation extraction (FSRE) focuses on recognizing novel relations by learning with merely a handful of annotated instances. Meta-learning has been widely adopted for such…
Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction
Xiang Li, Jiabao Gao, Sipei Lin +5
The pursuit of human-like conversational agents has long been guided by the Turing test. For modern speech-to-speech (S2S) systems, a critical yet unanswered question is whether th…
RAG Meets Temporal Graphs: Time-Sensitive Modeling and Retrieval for Evolving Knowledge
Jiale Han, Austin Cheung, Yubai Wei +4
Knowledge is inherently time-sensitive and continuously evolves over time. Although current Retrieval-Augmented Generation (RAG) systems enrich LLMs with external knowledge, they l…
CEFW: A Comprehensive Evaluation Framework for Watermark in Large Language Models
Shuhao Zhang, Bo Cheng, Jiale Han +4
Text watermarking provides an effective solution for identifying synthetic text generated by large language models. However, existing techniques often focus on satisfying specific…
Making Pre-trained Language Models Better Continual Few-Shot Relation Extractors
Shengkun Ma, Jiale Han, Yi Liang +1
Continual Few-shot Relation Extraction (CFRE) is a practical problem that requires the model to continuously learn novel relations while avoiding forgetting old ones with few label…
HoneyImage: Verifiable, Harmless, and Stealthy Dataset Ownership Verification for Image Models
Zhihao Zhu, Jiale Han, Yi Yang
Image-based AI models are increasingly deployed across a wide range of domains, including healthcare, security, and consumer applications. However, many image datasets carry sensit…