2 citations · 8 across the 17 of their papers we have counts for
15 papers · 1 filter
Tabby: An Open Pretraining Recipe for Time Series Foundation Models
Shifeng Xie, Bahaeddine Abdessalem, Zehao Xiao +9
In this report, we release Tabby, a long context probabilistic time series foundation model, together with a complete and open recipe of how it was built. Tabby adopts an encoder-o…
FlowTSFM: Turning Encoder Depth into Quantile Transport
Bahaeddine Abdessalem, Shifeng Xie, Zehao Xiao +6
Encoder-based time series foundation models (TSFMs) typically rely on deep stacks of independently parameterized Transformer layers, where only the final forecast is supervised and…
Post-Training in Time Series Foundation Models: A Unifying Framework
Shifeng Xie, Ambroise Odonnat, Zehao Xiao +7
Time series foundation models (TSFMs) have emerged as general-purpose models for time series analysis, but pretraining alone is often insufficient for reliable downstream deploymen…
The Red Queen Gödel Machine: Co-Evolving Agents and Their Evaluators
Alex Iacob, Andrej Jovanović, William F. Shen +12
Self-improving agents are state-of-the-art on agentic coding benchmarks, yet their search methods assume a stationary evaluation criterion. This ignores a central feature of evolut…
Vision Transformer Finetuning Benefits from Non-Smooth Components
Ambroise Odonnat, Laetitia Chapel, Romain Tavenard +1
The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness. However, its role in t…
Optimal Self-Consistency for Efficient Reasoning with Large Language Models
Austin Feng, Marius Alonso, Ambroise Odonnat +2
Self-consistency (SC) is a widely used test-time inference technique for improving performance in chain-of-thought reasoning. It consists of generating multiple responses, or ``sam…
Provable Benefits of In-Tool Learning for Large Language Models
Sam Houliston, Ambroise Odonnat, Charles Arnal +1
Tool-augmented language models, equipped with retrieval, memory, or external APIs, are reshaping AI, yet their theoretical advantages remain underexplored. In this paper, we addres…
CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data
Shifeng Xie, Vasilii Feofanov, Ambroise Odonnat +7
Time series foundation models (TSFMs) have recently gained significant attention due to their strong zero-shot capabilities and widespread real-world applications. Such models typi…
Easing Optimization Paths: a Circuit Perspective
Ambroise Odonnat, Wassim Bouaziz, Vivien Cabannes
Gradient descent is the method of choice for training large artificial intelligence systems. As these systems become larger, a better understanding of the mechanisms behind gradien…
A Mechanistic Study of Transformers Training Dynamics
Ambroise Odonnat, Wassim Bouaziz, Vivien Cabannes
Large-scale pretraining of transformers has been central to the success of foundation models. However, the scale of those models limits our understanding of the mechanisms at play…
SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities
Yanis Lalou, Théo Gnassounou, Antoine Collas +6
Unsupervised Domain Adaptation (DA) consists of adapting a model trained on a labeled source domain to perform well on an unlabeled target domain with some data distribution shift.…
MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
Renchunzi Xie, Ambroise Odonnat, Vasilii Feofanov +3
Leveraging the models' outputs, specifically the logits, is a common approach to estimating the test accuracy of a pre-trained neural network on out-of-distribution (OOD) samples w…
SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention
Romain Ilbert, Ambroise Odonnat, Vasilii Feofanov +4
Transformer-based architectures achieved breakthrough performance in natural language processing and computer vision, yet they remain inferior to simpler linear baselines in multiv…
Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift
Renchunzi Xie, Ambroise Odonnat, Vasilii Feofanov +3
Estimating the test performance of a model, possibly under distribution shift, without having access to the ground-truth labels is a challenging, yet very important problem for the…
Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias
Ambroise Odonnat, Vasilii Feofanov, Ievgen Redko
Self-training is a well-known approach for semi-supervised learning. It consists of iteratively assigning pseudo-labels to unlabeled data for which the model is confident and treat…