兴趣爱好
- LLMs and Agentic AI
- Time Series Analysis
- Recommender Systems
- AI for Science
最新
- From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization
- ScholarSum: Student-Teacher Abstractive Summarization via Knowledge Graph Reasoning and Reflective Refinement
- Re^3: Relevance & Recency Retrieval for Mitigating Temporal Hallucination
- CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting
- Fewer Battles, More Gain: An Information-Efficient Framework for Arena-based LLM Evaluation
- GeoMind: An Agentic Workflow for Lithology Classification with Reasoned Tool Invocation
- Visual Autoregressive Modeling for Instruction-Guided Image Editing
- StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
- A Comprehensive Survey of the LLM-Based Agent: The Contextual Cognition Perspective
- BLADE: A Behavior-Level Data Augmentation Framework with Dual Fusion Modeling for Multi-Behavior Sequential Recommendation
- From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation
- Can Slow-thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting
- TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning
- TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoders
- Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecasting
- CoGenCast: A Coupled Autoregressive-Flow Generative Framework for Time Series Forecasting
- MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning
- Position: Beyond Model-Centric Prediction — Agentic Time Series Forecasting
- InstructTime++: Time Series Classification with Multimodal Language Modeling via Implicit Feature Enhancement
- PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization
- Hierarchical multimodal llms with semantic space alignment for enhanced time series classification
- Global Structure-aware and Feature-augmented Graph Neural Network for Heterophilic Graphs
- Improving Time Series Forecasting via Instance-aware Post-hoc Revision
- STaR: Towards Cognitive Table Reasoning via Slow-Thinking Large Language Models
- A Hybrid Multi-Factor Framework for Dynamic Intraoperative Hypotension Prediction
- Conditional Denoising Meets Polynomial Modeling: A Flexible Decoupled Framework for Time Series Forecasting
- Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner
- Towards Automatic Sampling of User Behaviors for Sequential Recommender Systems
- Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study
- TableTime: Reformulating Time Series Classification as Zero-Shot Table Understanding via LLMs
- AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting
- Towards Context-aware Reasoning-enhanced Generative Searching in E-commerce
- PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature
- MemWeaver: A Hierarchical Memory from Textual Interactive Behaviors for Personalized Generation
- Tag-augmented Dual-target Cross-domain Recommendation
- Preference Trajectory Modeling via Flow Matching for Sequential Recommendation
- Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs
- am-ELO: A Stable Framework for Arena-based LLM Evaluation
- HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation
- TimeDART: A Diffusion Autoregressive Transformer for Self-supervised Time Series Representation
- Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables
- Are LLMs Stable Formal Logic Translators in Logical Reasoning Across Linguistically Diversified Texts?
- ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis
- A Comprehensive Survey of Time Series Forecasting: Concepts, Challenges, and Future Directions
- A Survey on Table Mining with Large Language Models: Challenges, Advancements and Prospects
- A Survey on Knowledge-Oriented Retrieval-Augmented Generation
- Cross-Domain Pre-training with Language Models for Transferable Time Series Representations
- InstrucTime: Advancing Time Series Classification with Multimodal Language Modeling
- Learning the Dynamics in Sequential Recommendation by Exploiting Real-time Information
- Revisiting the Solution of Meta KDD Cup 2024: CRAG
- TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback
- Empowering Sequential Recommender Systems from Mixture of Collaborative Signals and Semantic Relatedness
- Learning Recommender Systems with Soft Target: A Decoupled Perspective
- Reformulating Sequential Recommendation: Learning Dynamic User Interest with Content-enriched Language Modeling
- Unlocking the Potential of Large Language Models for Explainable Recommendations
- Towards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform
- Advancing Time Series Classification with Multimodal Language Modeling
- Learning Transferable Time Series Classifier with Cross-Domain Pre-training from Language Model
- Exploring Adapter-based Transfer Learning for Recommender Systems
- Generative Pretrained Hierarchical Transformer for Time Series Forecasting
- Adaptive Normalization for Non-stationary Time Series Forecasting: A Temporal Slice Perspective
- A General Tail Item Representation Enhancement Framework for Sequential Recommender Systems
- FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification
- ShapeWordNet: An Interpretable Shapelet Neural Network for Physiological Signal Classification
- One Person, One Model - Learning Compound Router for Sequential Recommendation
- Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification
- Nested Named Entity Recognition from Medical Texts: A Multi-task Learning Approach
- Collaborative List-and-Pairwise Filtering from Implicit Feedback
- Towards Automatic Designing of Deep Hybrid Network Architecture for Sequential Recommendation
- Learning Transferrable User Representations with Sequential Behaviors via Contrastive Pre-training
- LawyerPAN: A Proficiency Assessment Network for Trial Lawyers
- Learning Recommender Systems with Implicit Feedback via Soft Target Enhancement
- NeurJudge: A Circumstance-aware Neural Framework for Legal Judgment Prediction
- Alpha-Beta Sampling for Pairwise Ranking in One-Class Collaborative Filtering