54 papers screened · since 2026-07-07 · updated July 14, 2026
The core problem is auditing black-box conditional quantile forecasters with non-i.i.d. losses. The novel mechanism is a distribution-free and game-theoretic testing framework that focuses on contextual bets linear in the features. The head… Not a direct fit, but it's a higher-signal entry from the past week in Statistical Machine Learning.
arXiv:2607.11653v1 ↗The novel mechanism is Deep Gaussian Processes over DAGs, which places priors over functions to tackle these challenges. Not a direct fit, but it's a higher-signal entry from the past week in Statistical Machine Learning.
arXiv:2607.09645v1 ↗Time series forecasting models struggle with diverse temporal dynamics, GatedLinear proposes a lightweight framework that adaptively routes complementary linear bases using a Tri-Factorized Fusion Gate, achieving state-of-the-art accurac… Not a direct fit, but it's a higher-signal entry from the past week in Machine Learning.
arXiv:2607.09537v1 ↗The novel mechanism is an incentive-compatible auction mechanism for dynamically allocating tasks to expert models and tools. Not a direct fit, but it's a higher-signal entry from the past week in Artificial Intelligence.
arXiv:2607.09600v1 ↗The core problem is the lack of control over AI agents' evolution, the novel mechanism is the introduction of the logos pluggable layer for self-evolution and governance, the headline empirical result is the ability to compile heterogene… Not a direct fit, but it's a higher-signal entry from the past week in Artificial Intelligence.
arXiv:2607.10878v1 ↗The novel mechanism is the use of invariant manifolds to capture the learning dynamics of attention models. Not a direct fit, but it's a higher-signal entry from the past week in Machine Learning.
arXiv:2607.11875v1 ↗The core problem is modeling chemical kinetics in turbulent reacting flows, which is addressed by a novel entropy-constrained machine learning framework that incorporates the second law of thermodynamics as a training constraint, achievi… Not a direct fit, but it's a higher-signal entry from the past week in Machine Learning.
arXiv:2607.09582v1 ↗The novel mechanism is an exact instrument for measuring how a trained model uses these modes, based on a per-(layer, channel, window) Gram tensor. Not a direct fit, but it's a higher-signal entry from the past week in Machine Learning.
arXiv:2607.11796v1 ↗The Semantic Pareto-DQN proposes a multi-objective reinforcement learning framework that synthesizes transaction features into natural-language narratives. Not a direct fit, but it's a higher-signal entry from the past week in Machine Learning.
arXiv:2607.09641v1 ↗The novel mechanism is Latent Memory Palace (LMP), which formulates reasoning as variational inference with an autoregressive latent distribution. Not a direct fit, but it's a higher-signal entry from the past week in Machine Learning.
arXiv:2607.08724v1 ↗Evaluating vision-language models for safety-critical incidents in autonomous driving is challenging, AUTOPILOT-VQA addresses this gap with an incident-centric visual question answering benchmark, the dataset covers diverse safety-releva… Not a direct fit, but it's a higher-signal entry from the past week in Artificial Intelligence.
arXiv:2607.08745v1 ↗The novel mechanism is the use of activation space analysis to identify bias directions. Not a direct fit, but it's a higher-signal entry from the past week in Machine Learning.
arXiv:2607.11871v1 ↗We built Datadog's brief from a public sketch of what they do. Field Watch tunes to your actual roadmap and rivals — daily-fresh, delivered to your whole team.