Leveraging unlabelled data for generalizable neural population decoding
MOJO framework enables unsupervised pretraining for spike-tokenized neural decoders via masked autoencoders, improving brain-computer interface generalization.
Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
MOJO framework enables unsupervised pretraining for spike-tokenized neural decoders via masked autoencoders, improving brain-computer interface generalization.
SPyCE co-evolves reusable skills and policies for multimodal agents, distilling visual reasoning trajectories to improve generalization across tasks.
Dark matter search using Neural Spline Flows on CMS Run 2015D data in mono-Z channels, reducing 40 kinematic observables to 37-dim feature vector.
Neural-symbolic framework for automatic generation of multimodal analytic geometry problems, addressing precision gaps in diagram generation for math reasoning.
A group of 26 former Meta employees is suing the company over claims that it used AI tools to unfairly target workers on leave with layoffs, as reported earlier by Reuters. In the lawsuit, the employees allege Meta determined which workers to dismiss based on performance data…
In this paper, we study Reinforcement Learning in Parametrized Action Markov Decision Processes (PAMDP), where each decision consists of a symbolic action and numerical parameters. In such settings Reinforcement Learning algorithms typically determine parameters with one-shot…
Stochastic-process models are, as a rule, far easier to simulate than to condition. Non-linear observations, non-Gaussian likelihoods, black-box information, and global constraints all induce intractable conditional laws, requiring bespoke, model-specific constructions. We…
EEC explainer reveals mechanisms of emergent collective behaviors in multi-agent RL for robot swarms despite black-box neural policies.
ANGLE framework applies generative learning for non-parametric distributional regression on circular/angular data in computer vision and biology.
Study examines how iterative AI agent interaction creates neuroplastic conditioning loops, reshaping human cognitive patterns through high-frequency feedback cycles.
ESFP benchmark measures whether LLMs distinguish and coherently shift between neutral attribution and self-stance epistemic registers in contested claims.
Neuro-symbolic approach integrates MaxSAT constraint reasoning into vision-language models to enforce logical consistency in Sudoku solving.
Theoretical framework proposing atomic compression and compositional reuse as foundations for scalable intelligence across cognitive, biological, and computational systems.
Prequential coding compresses training trajectories to discover model simplicity independent of parameter count, advancing compression theory for neural networks.
Input-aware dynamic backdoor attack transfers classical adversarial trigger patterns to quantum neural networks, evading fixed-pattern defenses.
Hybrid NAS framework combining Transformer RL controller with Artificial Bee Colony for efficient architecture search on consumer hardware.
IAAN method for inference-time neuron identification in audio encoders to improve fine-grained speech attribute perception in LALMs.
NeuralActuator: neural model capturing low-cost servo nonlinearities (friction, hysteresis, backlash) for improved sim-to-real robot control.
Automated red-teaming system discovers reusable vulnerability patterns in production LLM agents (Claude Code, Codex) operating on untrusted content.
Graph neural network with multi-scale features for accelerating fluid dynamics simulations in complex geometries.
Apple's self-driving car program never really got off the ground, but it may have been what made the company's chips the powerful AI performers they are. Early in the development of the self-driving platform, Apple realized that it would need powerful on-device AI processing…
Topological neural network (PHINN-EEG) for dream-state EEG classification using persistent homology; niche neuroscience application.
Fine-tuned SHuBERT-ByT5 model for real-time sentence-level sign language translation achieving BLEU 15.9 on test set.
Digital Services Act may force Meta to make big changes on its platforms.
Researchers demonstrate cryptographically-undetectable backdoors in neural networks that enable adversarial examples while evading white-box detection.
Shared Selective Persistent Memory architecture for agentic LLM systems retains reusable task specifications, schemas, and tool configs across multi-turn sessions.
Analysis of representational variance in language models shows token-level context dominates (79-91%) over category structure (4-12%) across 14 models, challenging neural collapse theory.
Deutsche Telekom deploys OpenAI models across customer service, employee workflows, and network operations as part of AI-native telco strategy.
OpenAI's Fidji Simo is departing her full-time role as the company's AGI chief and is transitioning to being a "part-time advisor," she said on X. The news follows Simo's original announcement in April that she would take a few weeks of medical leave due to a neuroimmune…
SLORR introduces a stateless in-training low-rank regularization framework for neural network compression without architecture modification.