Paper-Conference

From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization
PDF
ScholarSum: Student-Teacher Abstractive Summarization via Knowledge Graph Reasoning and Reflective Refinement
Re^3: Relevance & Recency Retrieval for Mitigating Temporal Hallucination
Fewer Battles, More Gain: An Information-Efficient Framework for Arena-based LLM Evaluation
Arena-based evaluation has become a key method for assessing large language models (LLMs) through head-to-head model comparisons, …
引用
Visual Autoregressive Modeling for Instruction-Guided Image Editing
Recent advances in diffusion models have brought remarkable visual fidelity to instruction-guided image editing. However, their global …
引用
BLADE: A Behavior-Level Data Augmentation Framework with Dual Fusion Modeling for Multi-Behavior Sequential Recommendation
Multi-behavior sequential recommendation aims to capture users’ dynamic interests by modeling diverse types of user interactions …
引用 DOI
From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation
Logical reasoning is a core challenge in natural language understanding and a fundamental capability of artificial intelligence, …
引用 DOI
Can Slow-thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting
Time series forecasting (TSF) traditionally relies on fast-thinking paradigms that map historical observations directly to future …
引用 DOI
TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning
Table reasoning requires models to jointly perform comprehensive semantic understanding and precise numerical operations. Although …
引用 DOI
TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoders
Enhancing the expressive capacity of deep learning-based time series models with self-supervised pre-training has become …
引用 DOI