This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

While backpropagated gradients can predict human brain activity in the visual cortex, their spatial and temporal organization fundamentally diverges from the expected patterns of a biologically plausi…

The paper establishes the first theoretical framework for analyzing the learnability of Test-Time Adaptation (TTA) under non-stationary data streams by introducing Recovery Complexity, which quantifie…

The paper proposes Test-Time Training for Supervised Causal Learning (TTT-SCL), a novel framework that dynamically generates training data aligned with specific test instances to significantly improve…

This paper proposes a method to recover recoverability structure from failed traces of post-trained language models, enabling test-time routing and post-training analysis.

The paper analyzes backtracking dynamics in long reasoning traces to distinguish between useful self-correction and unproductive revision, finding that correct reasoning exhibits early, isolated repai…

The paper introduces TimeSage-MT, a comprehensive multi-turn benchmark designed to rigorously test an LLM agent's ability to perform complex, evolving time series analysis, revealing critical gaps in…

TIMEGATE introduces a resource-aware policy layer that manages continual ML adaptation by dynamically budgeting time and evaluation resources, achieving significant compute and energy savings without…

CaMBRAIN introduces a novel Mamba-based State Space Model (SSM) for real-time, continuous EEG inference, achieving state-of-the-art results with significantly higher throughput than existing methods.

The paper proposes a time-aware self-supervised learning framework using BYOL to improve Android malware detection robustness by accurately accounting for app release times.

SHARP proposes a novel sleep-based hierarchical replay framework to efficiently learn long-range non-stationary temporal patterns in streaming data, achieving improved context retention and predictive…

This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.

The paper proposes TimeGuard, a novel channel-wise pool training defense, to significantly improve the robustness of time series forecasting against backdoor attacks by addressing signal dilution and…

The paper proposes PG-RSSNN, a physics-guided recurrent state-space neural network that improves multi-step prediction stability and accuracy compared to both pure black-box and pure physics models, e…

The paper argues that long context windows are necessary for time series forecasting not just to capture long-range dependencies, but primarily to reduce uncertainty about the underlying data-generati…

The paper introduces QuITE, a plug-and-play embedding module that uses learnable query tokens to effectively embed irregular multivariate time series data into latent representations compatible with e…

The paper proposes BitTP, a lightweight bitlinear architecture that quantizes LLM-based trajectory predictors to 1.58-bit weights while keeping activations full-precision, enabling high-performance de…

The paper introduces Spike-PTSD, a novel, biologically inspired adversarial attack framework that successfully compromises the robustness of Spiking Neural Networks (SNNs) by modeling abnormal neural…

ChronosAD introduces a novel architecture that uses time series foundation models and a custom Temporal Block to achieve robust and highly accurate anomaly detection across diverse domains.

This paper synthesizes over 150 scattered studies and reports to provide the first comprehensive primer on post-training reasoning data, organizing the field around data objects, utility, construction…