6 citations · 13 across the 20 of their papers we have counts for
21 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.…
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…
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…
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…
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…
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…
Just Propagate: Unifying Matrix Factorization, Network Embedding, and LightGCN for Link Prediction
Haoxin Liu
Link prediction is a fundamental task in graph analysis. Despite the success of various graph-based machine learning models for link prediction, there lacks a general understanding…
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…
Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis
Haoxin Liu, Shangqing Xu, Zhiyuan Zhao +8
Time series data are ubiquitous across a wide range of real-world domains. While real-world time series analysis (TSA) requires human experts to integrate numerical series data wit…
LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting
Haoxin Liu, Zhiyuan Zhao, Jindong Wang +2
Time-series forecasting (TSF) finds broad applications in real-world scenarios. Prompting off-the-shelf Large Language Models (LLMs) demonstrates strong zero-shot TSF capabilities…
Performative Time-Series Forecasting
Zhiyuan Zhao, Haoxin Liu, Alexander Rodriguez +1
Time-series forecasting is a critical challenge in various domains and has witnessed substantial progress in recent years. Many real-life scenarios, such as public health, economic…
NICO++: Towards Better Benchmarking for Domain Generalization
Xingxuan Zhang, Yue He, Renzhe Xu +3
Despite the remarkable performance that modern deep neural networks have achieved on independent and identically distributed (I.I.D.) data, they can crash under distribution shifts…
Towards Unsupervised Domain Generalization
Xingxuan Zhang, Linjun Zhou, Renzhe Xu +3
Domain generalization (DG) aims to help models trained on a set of source domains generalize better on unseen target domains. The performances of current DG methods largely rely on…