9 citations · 26 across the 18 of their papers we have counts for
25 papers
Why Constrained Updates Still Forget: A Functional-Path Analysis of Continual SFT
Qingsen Ma, Dianyun Wang, Jiahong Liu +1
Supervised fine-tuning adapts language models to specialized tasks but can disrupt previously acquired behavior. Existing approaches constrain parameters, gradients, or replay obje…
Parametric Session States Recover Retrieval Intent without Replaying History
Qingsen Ma, Dianyun Wang, Jiahong Liu +1
Long-running assistants often interpret follow-up requests whose referents, constraints, and active goals were established many turns earlier. The central challenge is therefore no…
: Unifying Scale-Specific Structures and Prototype Decomposition for Spatial-Temporal Forecasting
Chengyang Zhou, Zijian Zhang, Hao Miao +5
Spatial-temporal forecasting is pivotal for intelligent urban management yet remains challenging due to the intricate coupling of spatial dynamics and temporal non-stationarity. Ex…
Hyperbolic Multimodal Continual Learning: A Closest-Admissible Solution
Jiahong Liu, Ming Shen, Xiaohao Liu +4
Existing continual-learning methods protect parameters, replayed examples, or Euclidean feature subspaces. When applied to hyperbolic multimodal models, they do not explicitly pres…
Memory Has Geometry: Non-Uniform Geometric Memory for Long-Horizon Personalized AI
Jiahong Liu, Wenhao Yu, Zexuan Qiu +2
Long-term memory is becoming a core substrate for personalized AI, yet most systems still represent personalization as discrete records in a largely static latent space, accessed u…
FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space
Jiahong Liu, Ram Samarth B B, Xinyu Fu +4
Federated learning enables privacy-preserving collaborative training, but highly heterogeneous client data remain challenging, especially in graph federated learning where clients…
Hyperbolic Multimodal Continual Learning
Jiahong Liu, Ming Shen, Xiaohao Liu +4
Hyperbolic geometry has recently emerged as a powerful representation space for multimodal learning, as it naturally captures hierarchical semantic structure across modalities. Des…
SemaCDR: LLM-Powered Transferable Semantics for Cross-Domain Sequential Recommendation
Chunxu Zhang, Shanqiang Huang, Zijian Zhang +5
Cross-domain recommendation (CDR) addresses the data sparsity and cold-start problems in the target domain by leveraging knowledge from data-rich source domains. However, existing…
Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning
Wenhao Yu, Shaohang Wei, Jiahong Liu +5
Token-level reweighting is a simple yet effective mechanism for controlling supervised fine-tuning, but common indicators are largely one-dimensional: the ground-truth probability…
UrbanMoE: A Sparse Multi-Modal Mixture-of-Experts Framework for Multi-Task Urban Region Profiling
Pingping Liu, Jiamiao Liu, Zijian Zhang +5
Urban region profiling, the task of characterizing geographical areas, is crucial for urban planning and resource allocation. However, existing research in this domain faces two si…
Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs
Zixing Song, Irwin King
The emergent reasoning capabilities of Large Language Models (LLMs) offer a transformative paradigm for analyzing text-attributed graphs. While instruction tuning is the prevailing…
Scalable Dielectric Tensor Predictions for Inorganic Materials using Equivariant Graph Neural Networks
Haowei Hua, Chen Liang, Ding Pan +4
Accurate prediction of dielectric tensors is essential for accelerating the discovery of next-generation inorganic dielectric materials. Existing machine learning approaches, such…
Towards Practical Automatic Piano Reduction using BERT with Semi-supervised Learning
Wan Ki Wong, Ka Ho To, Chuck-jee Chau +3
In this study, we present a novel automatic piano reduction method with semi-supervised machine learning. Piano reduction is an important music transformation process, which helps…
Implicit Reasoning in Large Language Models: A Comprehensive Survey
Jindong Li, Yali Fu, Li Fan +6
Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks. Reasoning with LLMs is central to solving multi-step problems and complex decisio…
Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey
Jindong Li, Yali Fu, Jiahong Liu +5
The rapid advancement of large language models (LLMs) has intensified the need for effective mechanisms to transform continuous multimodal data into discrete representations suitab…
Towards Geometry Problem Solving in the Large Model Era: A Survey
Yurui Zhao, Xiang Wang, Jiahong Liu +2
Geometry problem solving (GPS) represents a critical frontier in artificial intelligence, with profound applications in education, computer-aided design, and computational graphics…
Efficient Identity and Position Graph Embedding via Spectral-Based Random Feature Aggregation
Meng Qin, Jiahong Liu, Irwin King
Graph neural networks (GNNs), which capture graph structures via a feature aggregation mechanism following the graph embedding framework, have demonstrated a powerful ability to su…
CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey
Jindong Li, Yongguang Li, Yali Fu +4
As machine learning evolves, domain generalization (DG) and domain adaptation (DA) have become crucial for improving model robustness across diverse environments. Contrastive Langu…
Position: Beyond Euclidean -- Foundation Models Should Embrace Non-Euclidean Geometries
Neil He, Jiahong Liu, Buze Zhang +6
In the era of foundation models and Large Language Models (LLMs), Euclidean space has been the de facto geometric setting for machine learning architectures. However, recent litera…
Towards Detecting Persuasion on Social Media: From Model Development to Insights on Persuasion Strategies
Elyas Meguellati, Stefano Civelli, Pietro Bernardelle +3
Political advertising plays a pivotal role in shaping public opinion and influencing electoral outcomes, often through subtle persuasive techniques embedded in broader propaganda s…
A Survey of Personalized Large Language Models: Progress and Future Directions
Jiahong Liu, Zexuan Qiu, Zhongyang Li +7
Large Language Models (LLMs) excel in handling general knowledge tasks, yet they struggle with user-specific personalization, such as understanding individual emotions, writing sty…
Low-Rank Adaptation for Foundation Models: A Comprehensive Review
Menglin Yang, Jialin Chen, Jinkai Tao +9
The rapid advancement of foundation modelslarge-scale neural networks trained on diverse, extensive datasetshas revolutionized artificial intelligence, enabling unprecedented advan…
Hyperbolic Fine-Tuning for Large Language Models
Menglin Yang, Ram Samarth B B, Aosong Feng +4
Large language models (LLMs) have demonstrated remarkable performance across various tasks. However, it remains an open question whether the default Euclidean space is the most sui…
HC-GLAD: Dual Hyperbolic Contrastive Learning for Unsupervised Graph-Level Anomaly Detection
Yali Fu, Jindong Li, Jiahong Liu +3
Unsupervised graph-level anomaly detection (UGAD) has garnered increasing attention in recent years due to its significance. Most existing methods that rely on traditional GNNs mai…