10 papers
Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory
Qingcan Kang, Mingyang Liu, Shixiong Kai +5
Language agents depend on memory across interactions. However, the limited context windows of large language models (LLMs) and their inference costs constrain how much memory can b…
Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents
Qingcan Kang, Liu Mingyang, Shixiong Kai +3
Long-horizon language agents accumulate observations, reasoning traces, and retrieved facts exceeding context windows, making memory retention a fundamental resource-allocation pro…
EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling
Qingcan Kang, Mingyang Liu, Xiaojin Fu +3
Automating optimization modeling from natural language with large language models (LLMs) faces two key challenges. First, training corpora lack structural diversity. Second, data g…
On Temperature-Constrained Non-Deterministic Machine Translation: Potential and Evaluation
Weichuan Wang, Mingyang Liu, Linqi Song +1
In recent years, the non-deterministic properties of language models have garnered considerable attention and have shown a significant influence on real-world applications. However…
Enhancing Low-Rank Adaptation with Structured Nonlinear Transformations
Guanzhi Deng, Mingyang Liu, Dapeng Wu +2
Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning method for large language models. However, its linear nature limits expressiveness. We propose LoRAN,…
KLIPA: A Knowledge Graph and LLM-Driven QA Framework for IP Analysis
Guanzhi Deng, Yi Xie, Yu-Keung Ng +6
Effectively managing intellectual property is a significant challenge. Traditional methods for patent analysis depend on labor-intensive manual searches and rigid keyword matching.…
Activation-Guided Consensus Merging for Large Language Models
Yuxuan Yao, Shuqi Liu, Zehua Liu +6
Recent research has increasingly focused on reconciling the reasoning capabilities of System 2 with the efficiency of System 1. While existing training-based and prompt-based appro…
DiffETM: Diffusion Process Enhanced Embedded Topic Model
Wei Shao, Mingyang Liu, Linqi Song
The embedded topic model (ETM) is a widely used approach that assumes the sampled document-topic distribution conforms to the logistic normal distribution for easier optimization.…
Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling
Yuxuan Yao, Han Wu, Mingyang Liu +5
Large language models (LLMs) exhibit varying strengths and weaknesses across different tasks, prompting recent studies to explore the benefits of ensembling models to leverage thei…
Privacy in LLM-based Recommendation: Recent Advances and Future Directions
Sichun Luo, Wei Shao, Yuxuan Yao +9
Nowadays, large language models (LLMs) have been integrated with conventional recommendation models to improve recommendation performance. However, while most of the existing works…