The Archive

Technique to mitigate shortcut learning in transformer-based spoken English proficiency assessment systems.

Pick-to-Learn methodology applied to hyperparameter calibration for Model Predictive Control in aircraft flight planning.

Official estimates Google and Apple likely made millions in nudify app fees.

Physics-informed U-Net for 10–90 min precipitation nowcasting using multi-variable radar data in high-resolution settings.

HCIG framework uses hierarchical cross-modal graph networks to detect sarcasm and cyberbullying via text-visual incongruity.

JoyNexus: multi-tenant post-training service for Vision-Language-Action models with efficient GPU resource pooling.

Frontier LLMs fail at exact string copying due to positional encoding bias; 2D-RoPE organizes text as 2D grid to fix.

Tutorial and survey on agentic AI for 5G/6G networks covering reasoning, planning, multi-agent coordination, and standardization.

Spatial normalization technique for cross-domain retinal OCT layer segmentation in clinical neurodegenerative disease analysis.

Model merging (TIES, RAM+) matches jointly trained multi-task RL on Qwen3-8B AppWorld agent benchmark; geometry analysis explains parity.

New benchmark evaluates frontier LLMs on real analytical knowledge work—synthesizing information, judgment under uncertainty, strategic thinking—beyond factual recall and coding.

Methods for gene regulatory network inference from genome-wide data using deep probabilistic models with uncertainty quantification.

Loopie: MoE Transformer models (20B and 6B parameters) that outperform vanilla scaling by efficiently looping under fixed compute budgets.

DELUGE: multimodal deep learning system for continental-scale daily pluvial flood damage prediction at 1km resolution using foundation model embeddings.

Patreon is strengthening its defenses against AI scraping by working with Cloudflare to block bots that train AI models on creators’ content without permission. The move marks a shift away from relying on websites using robots.txt alone to actively block unauthorized AI training.

SciForge: AI-native multimodal workbench for scientific discovery with agent-accessible services for code, datasets, workflow execution, and paper management.

Tabular foundation model for pre-fault dynamic security assessment in power systems using in-context learning to reduce labeling and improve contingency generalization.

Quantum elastic weight consolidation: QFI-based regularization to mitigate catastrophic forgetting in variational quantum classifiers on sequential tasks.

DRL trading system for Bitcoin/Tesla using policy gradient and Q-learning with LLaMA 3.2 sentiment analysis and technical indicators.

Google DeepMind introduces Gemini 3.5 Flash Cyber, a specialized model for vulnerability detection and patching.

Constrained Hebbian learning rule supports efficient neural representation under biological synaptic and metabolic constraints.

BERT-based dialogue state tracking with candidate attention for scalable task-oriented dialogue systems with zero-shot domain transfer.

Study of memory retrieval evaluation methodology for systems handling evolving records, comparing flat vs. structured revision tracking approaches.

DPNeXt decoder improves Vision Foundation Model efficiency for multi-task dense prediction in robotics perception systems.

Empirical evaluation finds LLM watermarking methods fail forensic standards required by EU AI Act and California SB 942.

RL-based control method for low-voltage grid congestion management under noisy observations and model mismatch.

BayesPO formulates prompt optimization as Bayesian posterior sampling over discrete tokens using parallel-tempered MCMC.

CanonicalPhys improves remote photoplethysmography robustness to head pose variation using canonical-space priors.

Opinion piece arguing for independent AI certification mechanisms to address market failure in rewarding trustworthy development.