activity
20212026
most citedTSI-Bench: Benchmarking Time Series Imputation

6 citations · 13 across the 20 of their papers we have counts for

collaborators
Showing 2026Show all

7 papers · 1 filter

cs.CL2026

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.…

cs.LG2026

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…

cs.LG2026

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…

cs.CL2026

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…

cs.LG2026

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…

cs.LG2026

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-…

cs.AI2026

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…