Category
4,920 papers
PLC-DPO is proposed to robustly optimize preferences by routing each pair's training signal as a clean, flip, or tie case, which reframes noisy preference learning as actively correcting supervision direction and strength rather than merely filtering suspicious examples.
In this research, a novel framework is proposed for the SOH estimation, which employs a hybrid deep learning architecture of a concatenation of a Convolution Neural Network (CNN) and a Bidirectional Long Short-Term Memory (BiLSTM) Neural Network (NN) with the integration of Bayesian Optimization-based hyperparameter tuning for the network. Three different deep learning architectures are being evaluated: standalone recurrent models, CNN-RNN architectures and CNN-RNN combinations enhanced with intermediate Fully Connected (FC) layers. Among the three, the model with the intermediate FC layers demonstrated the highest predictive accuracy. A comprehensive feature engineering approach combines capacity (Q), voltage (V), Incremental Capacity Analysis (ICA), and Differential Voltage Analysis (DVA), with systematic evaluation of multiple combinations to identify the optimal input representation. To validate the proposed method, three publicly available datasets were utilized, ensuring reproducibility of the results, two from external sources and one developed by the author of this study using a unique experimental setup. The comparison study was performed using the Mean Absolute Error (MAE), the Root Mean Squared Error (RMSE) and the FLoating-point OPerations (FLOPs) as evaluation metrics.
It is explained how roleplay can produce compliance despite retained evidence of harm and identify a concrete target for future safeguards: maintaining the connection from harm recognition to refusal.
The AUC is shown to be non-collapsible because it decomposes into within- and cross-group AUC terms when subpopulations coexist, such that its overall value may fall outside the range of subgroup specific AUCs.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Q-Strata is proposed, a bi-level allocator that ranks within-block assignments with a cheap proxy and allocates across blocks with a model-level objective evaluated on the assembled quantized model, achieving lower WikiText2 perplexity than uniform-bitwidth GPTQ and the state-of-the-art MoE MPQ methods MxMoE and GEMQ in the low-bit regime.
PAC, a Progress-Augmented Advantage Curriculum for multi-task RL of LLMs that combines two task-level signals: advantage-derived learnability, which measures the magnitude of the policy update a task can induce, and recent reward gains, which show whether those updates have improved task performance.
This work proposes Neural Double Q-routing, which replaces destination-indexed tables with a shared state--action value network, and achieves the lowest mean completion time among all compared methods in the six 150- and 200-OHT settings, whereas Dijkstra remains best in the three 100-OHT settings.
This survey provides a structured entry point to tensorized language models and clarifies when parameter savings can plausibly translate into memory efficiency, computational efficiency, or interpretability, and introduces a metric for the compression-realization gap between theoretical memory reduction and measured system-level speedup.
Anytime-valid methods proposed for dependent data should be accompanied by null-calibration controls and mechanism traces, and Huber-style gating of the filter's own updates cuts isolated-spike degradation by an order of magnitude with no dataset specific tuning.
Topo^2, a measurement framework that makes deep networks causally separable, measurable, and law-governed, and turns"memorization" from an ill-defined capacity into a measurable, separable, invertible topological layer.
ToxLens is introduced, a reproducible multi-task graph-learning framework for 11 toxicity endpoints spanning Ames mutagenicity, acute oral toxicity, hERG inhibition, and Tox21 nuclear-receptor and stress-response assays and reveals substantial endpoint-specific variation in set efficiency and discrimination and calibration improved with similarity to the training domain.
This work introduces credit-addressable reasoning, in which the semantic units exposed during inference also define where learning compares alternatives and assigns credit, and instantiates Code-CoT, which retains the diagram, represents visual relations as line-addressable executable code, and organizes reasoning into typed events.
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.
