Category
4,920 papers
The core proposal is to spike the training data by intentionally contaminating some test examples at known rates, which can then be used to calibrate predictors of model memorization which enable principled statistical correction of inflated test scores.
The Unlearning Depth Score (UDS), a metric that quantifies the mechanistic depth of unlearning via activation patching, is introduced, confirming the causal approach as the most reliable for unlearning evaluation.
FinCAD is proposed, an inference-time adaptation of Context-Aware Decoding that attenuates contributions from memorised historical outcomes without retraining and raises the subset-averaged in-sample/out-of-sample Spearman correlation on an eleven-model leaderboard.
The study demonstrates that leakage-aware, cycle-level, physics-guided machine learning can extend conventional gas-sensing analysis beyond single-response metrics while preserving physical interpretability.
Reach audiences
Advertise in front of researchers, engineers, and readers.
SciAtlas is presented, a shared, machine-actionable cross-disciplinary scholarly knowledge infrastructure that integrates evidential, conceptual, disciplinary, expertise, and normative layers under a shared schema and achieves a unified neuro-symbolic retrieval mechanism that grounds heterogeneous research objects, propagates relevance across the scholarly topology, and projects the resulting relevance field into the context required by each scientific workflow.
Focusing on the autonomous driving safety-critical case of pedestrian detection in the dark, it is shown how synthetic low-light samples can be used to better characterize the performance of a state-of-the-art object detection model as a function of the scene illumination.
Neural generative samplers for lattice field theory can be costly to train and evaluate. When they miss modes or assign them incorrect relative weights, biased observables do not reveal which collective variables are responsible. We project a trained flow-matching velocity onto vector fields built from lattice operators and Fourier modes. In two-dimensional lattice $\phi^4$ theory, the projection separates changes in the overall magnetization from the lowest nonzero-momentum fluctuations and guides an explicit invertible proposal that treats them separately. Allowing the amplitude of the lowest nonzero-momentum fluctuations to depend on the magnetization improves the overlap between the proposal and target distributions, while the same two-parameter modification at higher momenta gives smaller improvements. The Metropolis--Hastings correction defines a Markov chain with the target Boltzmann distribution as its stationary law, and the normalized proposal density yields finite-volume partition-function estimates consistent with an independent HMC calculation. At the larger tested volume, the overlap between the proposal and target distributions deteriorates substantially, limiting the range over which the same parameterization remains effective.
Self-Anchored Consensus (SAC), a fully decentralized filter-and-refine protocol in which agents iteratively exchange responses, locally evaluate and filter unreliable messages, and refine their own outputs, is proposed.
A transformer-based estimator is proposed to implicitly learn spatial patterns that channel-gain maps exhibit across environments, as dictated by the laws of physics and typical environmental characteristics, which enables CGME in new environments from significantly fewer measurements.
It is demonstrated that CoT encodes recoverable, token-level problem-solving information, offering new insight into how reasoning is represented and where it breaks down, suggesting complete reasoning chains are not always necessary.
This work introduces a generalizable large language model (LLM)-powered pipeline for automated extraction and structuring of materials data from unstructured scientific literature, using concrete materials as a representative and particularly challenging example.
This work establishes the existence of a symmetric, monotone pure-strategy equilibrium and shows that performance-based screening remains viable so long as evaluations retain a sufficient creative component, but collapses into an uninformative pooling equilibrium once AI capability grows large enough to crowd out creative effort.
Education Innovation
Machine Intelligence
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
General Science
GPT-Lab
· gpt-lab.eu
Sep 3, 2026
Adaptive AI agents can help make BIM data more machine-readable by navigating IFC models, interpreting inconsistent information, and mapping it to defined standards. In this blog, Alok Rawat shares findings from a real-world pilot in construction workflows. The post Adaptive AI Agents in Construction Workflows appeared first on GPT-Lab.
Climate & Sustainability
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
