6 citations · 12 across the 24 of their papers we have counts for
11 papers · 1 filter
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…