182 citations · 264 across the 32 of their papers we have counts for
38 papers
When Protection Overrides Consequences: Understanding Protection Mode in Large Language Model Decision-Making
Yuanfan Li, Junyi Chen, Qi Zhou +3
Frontier language models excel at complex tasks yet may prioritize protection over larger physical consequences in simple, urgent decisions. GPT-5.6 Sol, for example, moves a girl…
Approximation in Contrastive Representation Learning
Yuanfan Li, Zihan Zhang, Yiming Ying +1
Contrastive representation learning (CRL) is a fundamental paradigm for learning transferable representations. Recent work identifies its population target as the pointwise mutual…
Beyond Generator-Specific Shortcuts: Open-World AI-Generated Video Detection via Adversarial Training
Qi Zhou, Yuanfan Li, Huiqi Deng +2
AI-generated video (AIGV) detection is increasingly important for mitigating misinformation, impersonation, and other malicious uses of synthetic media, yet existing detectors ofte…
MemFuse: Multi-Source Memory Fusion from Fragmented Observations
Chao Li, Yuanfa Li, Wenhao Wu +3
Long-term memory is essential for agents that operate across extended interactions, yet existing memory systems and benchmarks predominantly focus on single-source textual historie…
SEE: Structure-aware Exploring & Exploiting for Long-horizon GUI Agent Trajectory Synthesis
Zhuohang Fan, Beichen Zhang, Yuanfa Li +4
Graphical User Interface (GUI) agents powered by vision-language models hold promise for automating real-world mobile tasks. However, progress is limited by the lack of high-covera…
Mi-Memory: A Lifecycle Memory Framework for Personal AI
Xule Liu, Hanlin Teng, Chao Li +15
Personal AI is moving beyond chat-only interaction toward continuous services that span phones, cars, homes, wearables, cameras, and tools. In this setting, memory cannot remain a…
Xiaomi-GUI-0 Technical Report
Wanxia Cao, Chengzhen Duan, Pei Fu +29
Graphical user interface (GUI) agents build on vision-language models to complete user tasks end-to-end in real applications through interface actions such as tapping, swiping, tex…
SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training
Zhongyu He, Yuanfan Li, Fei Huang +9
Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or persistent skill retrieval at…
Enhancing LLM Medical Coding with Structured External Knowledge
Yidong Gan, David D. Nguyen, Yang Lin +4
Accurate medical coding requires consulting authoritative resources such as the ICD tabular list and coding guidelines. Existing LLM-based automated methods largely rely on LLMs' i…
Statistical Consistency and Generalization of Contrastive Representation Learning
Yuanfan Li, Xiyuan Wei, Tianbao Yang +1
Contrastive representation learning (CRL) underpins many modern foundation models. Despite recent theoretical progress, existing analyses suffer from several key limitations: (i) t…
Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
Muquan Li, Yingyi Ma, Yihong Huang +5
Dataset distillation (DD) compresses a large training set into a small synthetic set for efficient training, but most DD methods optimize only clean accuracy and leave robustness u…
Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification
Yuanfan Li, Yunwen Lei, Zheng-Chu Guo +1
Recent advances have significantly improved our understanding of the generalization performance of gradient descent (GD) methods in deep neural networks. A natural and fundamental…
MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
Tuan-Luc Huynh, Thuy-Trang Vu, Weiqing Wang +4
Continually updating model-based indexes in generative retrieval with new documents remains challenging, as full retraining is computationally expensive and impractical under resou…
Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models
Linhao Luo, Zicheng Zhao, Gholamreza Haffari +3
Large language models (LLMs) have demonstrated impressive reasoning abilities, but they still struggle with faithful reasoning due to knowledge gaps and hallucinations. To address…
Survey and Taxonomy: The Role of Data-Centric AI in Transformer-Based Time Series Forecasting
Jingjing Xu, Caesar Wu, Yuan-Fang Li +2
Alongside the continuous process of improving AI performance through the development of more sophisticated models, researchers have also focused their attention to the emerging con…
Decompose, Enrich, and Extract! Schema-aware Event Extraction using LLMs
Fatemeh Shiri, Van Nguyen, Farhad Moghimifar +3
Large Language Models (LLMs) demonstrate significant capabilities in processing natural language data, promising efficient knowledge extraction from diverse textual sources to enha…
PromptDSI: Prompt-based Rehearsal-free Continual Learning for Document Retrieval
Tuan-Luc Huynh, Thuy-Trang Vu, Weiqing Wang +5
Differentiable Search Index (DSI) utilizes pre-trained language models to perform indexing and document retrieval via end-to-end learning without relying on external indexes. Howev…
VersiCode: Towards Version-controllable Code Generation
Tongtong Wu, Weigang Wu, Xingyu Wang +7
Large Language Models (LLMs) have made tremendous strides in code generation, but existing research fails to account for the dynamic nature of software development, marked by frequ…
Augmented CARDS: A machine learning approach to identifying triggers of climate change misinformation on Twitter
Cristian Rojas, Frank Algra-Maschio, Mark Andrejevic +3
Misinformation about climate change poses a significant threat to societal well-being, prompting the urgent need for effective mitigation strategies. However, the rapid proliferati…
MMGRec: Multimodal Generative Recommendation with Transformer Model
Han Liu, Yinwei Wei, Xuemeng Song +3
Multimodal recommendation aims to recommend user-preferred candidates based on her/his historically interacted items and associated multimodal information. Previous studies commonl…
Double Mixture: Towards Continual Event Detection from Speech
Jingqi Kang, Tongtong Wu, Jinming Zhao +6
Speech event detection is crucial for multimedia retrieval, involving the tagging of both semantic and acoustic events. Traditional ASR systems often overlook the interplay between…
HeGTa: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table Understanding
Rihui Jin, Yu Li, Guilin Qi +7
Table understanding (TU) has achieved promising advancements, but it faces the challenges of the scarcity of manually labeled tables and the presence of complex table structures.To…
Modelling Political Coalition Negotiations Using LLM-based Agents
Farhad Moghimifar, Yuan-Fang Li, Robert Thomson +1
Coalition negotiations are a cornerstone of parliamentary democracies, characterised by complex interactions and strategic communications among political parties. Despite its signi…
Continual Learning for Large Language Models: A Survey
Tongtong Wu, Linhao Luo, Yuan-Fang Li +3
Large language models (LLMs) are not amenable to frequent re-training, due to high training costs arising from their massive scale. However, updates are necessary to endow LLMs wit…