6 citations · 12 across the 24 of their papers we have counts for
28 papers
Beyond State Capacity: Why Retrieval Breaks in Mamba
Nir Yarden, Amit Ben-Artzy, Roy Schwartz
Mamba models underperform Transformers on in-context retrieval. This gap is usually attributed to Mamba's fixed-size recurrent state, which loses information as the context grows.…
From Knowledge Access to Source Learning: Developing Source-Specific Competence
Lucheng Fu, Kejing Xia, Yiyang Wang +10
Large language model (LLM) agents increasingly rely on persistent external sources to solve sequences of knowledge-intensive tasks. Existing methods improve how source content is a…
Rethinking Multimodal Time-Series Forecasting Evaluation
Haoxin Liu, Yichen Zhou, Rajat Sen +2
We introduce a new context-enriched, multimodal time series forecasting benchmark, TimesX. TimesX contains a wide selection of high-quality real-world time series with diverse doma…
Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting
Haoxin Liu, Yichen Zhou, Rajat Sen +2
Time-Series Foundation Models (TSFMs) excel at zero-shot unimodal forecasting using numerical data, but unlike LLMs they cannot consume multimodal, non-numerical context that often…
UniSD: Towards a Unified Self-Distillation Framework for Large Language Models
Yiqiao Jin, Yiyang Wang, Lucheng Fu +7
Self-distillation (SD) offers a promising path for adapting large language models (LLMs) without relying on stronger external teachers. However, SD in autoregressive LLMs remains c…
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
Lucheng Fu, Ye Yu, Yiyang Wang +4
Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints. Many recent prompt optimization methods iteratively rew…
Seeking Universal Shot Language Understanding Solutions
Haoxin Liu, Harshavardhan Kamarthi, Zhiyuan Zhao +2
Shot language understanding (SLU) is crucial for cinematic analysis but remains challenging due to its diverse cinematographic dimensions and subjective expert judgment. While visi…
Hierarchical Industrial Demand Forecasting with Temporal and Uncertainty Explanations
Harshavardhan Kamarthi, Shangqing Xu, Xinjie Tong +4
Hierarchical time-series forecasting is essential for demand prediction across various industries. While machine learning models have obtained significant accuracy and scalability…
In-context Pre-trained Time-Series Foundation Models adapt to Unseen Tasks
Shangqing Xu, Harshavardhan Kamarthi, Haoxin Liu +1
Time-series foundation models (TSFMs) have demonstrated strong generalization capabilities across diverse datasets and tasks. However, existing foundation models are typically pre-…
FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains
Jiashuo Liu, Siyuan Chen, Zaiyuan Wang +38
Building upon FutureX, which established a live benchmark for general-purpose future prediction, this report introduces FutureX-Pro, including FutureX-Finance, FutureX-Retail, Futu…
AHA: Scalable Alternative History Analysis for Operational Timeseries Applications
Harshavardhan Kamarthi, Harshil Shah, Henry Milner +4
Many operational systems collect high-dimensional timeseries data about users/systems on key performance metrics. For instance, ISPs, content distribution networks, and video deliv…
Modular Deep-Learning-Based Early Warning System for Deadly Heatwave Prediction
Shangqing Xu, Zhiyuan Zhao, Megha Sharma +4
Severe heatwaves in urban areas significantly threaten public health, calling for establishing early warning strategies. Despite predicting occurrence of heatwaves and attributing…
Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift
Zhiyuan Zhao, Haoxin Liu, B. Aditya Prakash
Time-series forecasting finds broad applications in real-world scenarios. Due to the dynamic nature of time series data, it is important for time-series forecasting models to handl…
Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE
Guancheng Wan, Lucheng Fu, Haoxin Liu +10
The performance of Large Language Models (LLMs) hinges on carefully engineered prompts. However, prevailing prompt optimization methods, ranging from heuristic edits and reinforcem…
TAT: Temporal-Aligned Transformer for Multi-Horizon Peak Demand Forecasting
Zhiyuan Zhao, Sitan Yang, Kin G. Olivares +5
Multi-horizon time series forecasting has many practical applications such as demand forecasting. Accurate demand prediction is critical to help make buying and inventory decisions…
Improving Epidemic Analyses with Privacy-Preserving Integration of Sensitive Data
Zihan Guan, Zhiyuan Zhao, Fengwei Tian +5
Epidemic analyses increasingly rely on heterogeneous datasets, many of which are sensitive and require strong privacy protection. Although differential privacy (DP) has become a st…
TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectiveness
Zhiyuan Zhao, Juntong Ni, Shangqing Xu +3
Time-series forecasting is an essential task with wide real-world applications across domains. While recent advances in deep learning have enabled time-series forecasting models wi…
Evaluating System 1 vs. 2 Reasoning Approaches for Zero-Shot Time Series Forecasting: A Benchmark and Insights
Haoxin Liu, Zhiyuan Zhao, Shiduo Li +1
Reasoning ability is crucial for solving challenging tasks. With the advancement of foundation models, such as the emergence of large language models (LLMs), a wide range of reason…
How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook
Haoxin Liu, Harshavardhan Kamarthi, Zhiyuan Zhao +6
Time series analysis (TSA) is a longstanding research topic in the data mining community and has wide real-world significance. Compared to "richer" modalities such as language and…
A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization
Haoxin Liu, Chenghao Liu, B. Aditya Prakash
Large language models (LLMs), with demonstrated reasoning abilities across multiple domains, are largely underexplored for time-series reasoning (TsR), which is ubiquitous in the r…
Large Scale Hierarchical Industrial Demand Time-Series Forecasting incorporating Sparsity
Harshavardhan Kamarthi, Aditya B. Sasanur, Xinjie Tong +4
Hierarchical time-series forecasting (HTSF) is an important problem for many real-world business applications where the goal is to simultaneously forecast multiple time-series that…
Learning Graph Structures and Uncertainty for Accurate and Calibrated Time-series Forecasting
Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodriguez +2
Multi-variate time series forecasting is an important problem with a wide range of applications. Recent works model the relations between time-series as graphs and have shown that…
Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning
Haoxin Liu, Harshavardhan Kamarthi, Lingkai Kong +3
Time-series forecasting (TSF) finds broad applications in real-world scenarios. Due to the dynamic nature of time-series data, it is crucial to equip TSF models with out-of-distrib…
TSI-Bench: Benchmarking Time Series Imputation
Wenjie Du, Jun Wang, Linglong Qian +12
Effective imputation is a crucial preprocessing step for time series analysis. Despite the development of numerous deep learning algorithms for time series imputation, the communit…