GITCO: Gated Inference-Time Context Optimization in TSFMs

Computer Science > Artificial Intelligence [Submitted on 3 Jun 2026] GITCO: Gated Inference-Time Context Optimization in TSFMs Manya Pandey, Dhruv Kumar, Murari Mandal, Saurabh Deshpande Patch-based Time Series Foundation Models (TSFMs) suffer from context poisoning: structurally anomalous patches capture disproportionate attention and silently degrade zero-shot forecast quality. We propose improving TSFM accuracy at inference time by optimizing the input context rather than modifying model weights. We present GITCO (Gated Inference-Time Context Optimization), a lightweight three-component framework: Gate, Router, and Critic that selectively identifies and suppresses harmful patches without any parameter updates. Evaluated on TimesFM 2.5 across 53 GIFT-Eval datasets under K-fold cross-validation, GITCO achieves an average +1.95% MASE reduction on TimesFM 2.5 while capturing 89.9% of the improvement upper bound. We introduce context sensitivity profiles as a new characterizable property of TSFMs: the mapping from time series meta-features to expected accuracy improvement under inference-time context intervention, shaped jointly by model architecture and the statistical structure of the data. Comments: ICML 2026 Workshop on Foundation Models for Structured Data Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.05332 [cs.AI]   (or arXiv:2606.05332v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.05332 Focus to learn more Submission history From: Manya Pandey [view email] [v1] Wed, 3 Jun 2026 18:17:40 UTC (329 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)