14 papers
InsightChain: Optimized Chain-of-Insight Analytics for LLM-driven Data Visualization
Hanya Sun, Chen Zhang, Sheng Liang +2
Large language models (LLMs) are increasingly used for automated data visualization, yet existing approaches often frame visualization generation as a single-step mapping from user…
AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs
Sheng Liang, Yongyue Zhang, Nathanael Brian +4
Agentic LLM pipelines face escalating inference costs as context accumulates across retrieval, tool use, and multi-turn interactions. To control latency, deployments routinely comp…
Large Language Models as Amortized Pareto-Front Generators for Constrained Bi-Objective Convex Optimization
Peipei Xu, SiYuan Ma, Yaohua Liu +4
Generating feasible Pareto fronts for constrained bi-objective continuous optimization is central to multi-criteria decision-making. Existing methods usually rely on iterative scal…
MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
Sheng Zhang, Junyi Li, Yingyi Zhang +7
Recent advances in large language models (LLMs) have scaled the potential for reasoning and agentic search, wherein models autonomously plan, retrieve, and reason over external kno…
Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery
Xiaopeng Li, Wenlin Zhang, Yingyi Zhang +6
Deep Research agents driven by LLMs have automated the scholarly discovery pipeline, from planning and query formulation to iterative web exploration. Yet they remain constrained b…
Kaczmarz Linear Attention
Jiaxuan Zou, Ruifeng Ren, Yong Liu
Long-context language modeling remains central to modern sequence modeling, but the quadratic cost of Transformer attention makes scaling computationally prohibitive. Linear recurr…
The Procrustean Bed of Time Series: The Optimization Bias in Point-wise Loss Functions
Rongyao Cai, Yuxi Wan, Kexin Zhang +6
Intuitively, a more deterministic time series should be easier to forecast. However, point-wise loss functions (e.g., MSE and MAE), serving as differentiable surrogates for the ide…
Query-Centric Graph Retrieval Augmented Generation
Yaxiong Wu, Jianyuan Bo, Yongyue Zhang +2
Graph-based retrieval-augmented generation (RAG) enriches large language models (LLMs) with external knowledge for long-context understanding and multi-hop reasoning, but existing…
SGMem: Sentence Graph Memory for Long-Term Conversational Agents
Yaxiong Wu, Yongyue Zhang, Sheng Liang +1
Long-term conversational agents require effective memory management to handle dialogue histories that exceed the context window of large language models (LLMs). Existing methods ba…
CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering
Hang Lv, Sheng Liang, Hao Wang +6
Personalization has become crucial for adapting models to the diverse and evolving needs of users across cultural, temporal, and contextual dimensions. While existing methods often…
Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent
Haocheng Yu, Yaxiong Wu, Hao Wang +6
Interactive recommendation is a typical information-seeking task that allows users to interactively express their needs through natural language and obtain personalized recommendat…
Schema as Parameterized Tools for Universal Information Extraction
Sheng Liang, Yongyue Zhang, Yaxiong Wu +2
Universal information extraction (UIE) primarily employs an extractive generation approach with large language models (LLMs), typically outputting structured information based on p…
Effective and Efficient Schema-aware Information Extraction Using On-Device Large Language Models
Zhihao Wen, Sheng Liang, Yaxiong Wu +2
Information extraction (IE) plays a crucial role in natural language processing (NLP) by converting unstructured text into structured knowledge. Deploying computationally intensive…
Adaptive Schema-aware Event Extraction with Retrieval-Augmented Generation
Sheng Liang, Hang Lv, Zhihao Wen +4
Event extraction (EE) is a fundamental task in natural language processing (NLP) that involves identifying and extracting event information from unstructured text. Effective EE in…