Category
4,920 papers
This work demonstrates for the first time that mode connectivity between independently trained DDPM and NanoCLIP modes is discovered, and provides a novel perspective for understanding the geometric properties of the loss landscapes in modern generative and contrastive models.
By moving the analytical focus from terminal churn to earlier fund migration, the proposed approach provides a practical foundation for proactive, explainable, and economically informed client-retention decision support.
A simple, sequence-only pipeline can match and surpass leading methods by combining 330 interpretable sequence descriptors with TabPFN, a tabular foundation model that performs in-context prediction in a single forward pass without gradient-based training or hyperparameter search.
This paper proposes a trainable Neural Cellular Automata (NCA) based surrogate model for learning long time PDE dynamics that achieves the lowest long-horizon relative errors on the majority of the experiments.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work proposes a multi-domain generative domain mapping approach based on Star Generative Adversarial Networks (StarGAN) to improve fault detection on data-scarce wind turbines and proposes a proxy metric that detects poor performance at training time, despite an absence of anomalies.
LFPG-RL is developed and evaluated, which integrates link-flow propagation guidance (LFPG) into proximal policy optimization (PPO), and results support the contention that the method is a more efficient and accurate online OD demand calibration method compared to existing ones.
A dynamic explanation of how data statistics and architecture jointly shape token embeddings in language models is provided, and an implicit bias in the space of data statistics is revealed: training proceeds from simpler, low-order statistical relations toward increasingly complex, context-dependent ones.
Tail-Replay is presented, a prefix caching mechanism that enables unconstrained token-level prefix reuse in hybrid large language models and is evaluated on three Gated DeltaNet-based hybrid models using the LongBench and RULER benchmarks.
This work discovers that certain attention heads exhibit sequential consistency in their attention patterns, which can be persistently identified using a coefficient-of-variation-based algorithm, and proposes CateKV, a hybrid KV cache method that retains only critical token information for consistent heads, thereby reducing KV cache size and computational overhead.
BCPPO (Bachelier-Inspired Constrained Proximal Policy Optimization), a proximal policy optimization (PPO) method, supports a practical balance among reward, caution around cost predictions that vary across trained critics, and policy-only deployment.
CAESAR-LDAR is presented, an error-controlled multivariate learned compressor that augments a shared CAESAR-V backbone with two complementary mechanisms: a trainable orthogonal transform that reorganizes dependence across aligned latent channels, and a causal autoregressive hierarchical prior that captures local spatial structure left after transformation.
The threshold part of Question 4 of the COLT 2025 open problem "Data Selection for Regression Tasks" is resolved, and an erroneous claim circulating in a recent unrefereed preprint is correct.
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.
