AI/ML arXiv cs.AI

Crossing-Free Probabilistic K-Line Forecasts Without Retraining

KQSP is proposed as a training-free method to resolve quantile and K-line crossing inconsistencies in probabilistic financial forecasting.

AI/ML arXiv cs.AI

FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning

FedTopo introduces relation-level topology sharing to enable federated learning across clients with heterogeneous model architectures.

Tech Business/VC Hacker News

Tasklet (YC P26) Is Hiring a Customer Success Engineer

Tasklet is hiring a Customer Success Engineer.

Cybersecurity Hacker News

How A Gang of Thieves Pulled Off a Multimillion-Dollar Data Center Heist

A detailed account of a multi-million dollar heist targeting a data center.

Tech Business/VC TechCrunch

Repeat founder Ryan Williams raises $10M seed for an AI startup for private credit managers

Ryan Williams has raised $10M in seed funding for Ellis AI, a startup focused on AI for private credit managers.

Other The Verge

This tattoo is permanent, pain-free, and might soon come in the mail

A report on a new, painless permanent tattoo technology that uses AI-inspired imagery.

Other The Verge

Apple TV’s Cape Fear remake turns it into a paranoid tech thriller

Apple TV's remake of Cape Fear is described as a paranoid tech thriller reflecting modern technological distrust.

AI/ML arXiv cs.AI

Multimodal fusion of visual and morphometric features for avian bone classification

A proof-of-concept multimodal framework using CNNs and morphometric features to classify avian bone remains in zooarchaeology.

AI/ML arXiv cs.AI

An Attention-Based Framework for Alzheimers Disease Classification Using Resting-State fMRI

An attention-based deep learning framework using Transformers to classify Alzheimer's disease from resting-state fMRI data.

AI/ML arXiv cs.AI

Phoneme- vs. Character-Level Targets and Selective State-Space Models for Intracortical Brain-to-Text

A study comparing GRU and Mamba-based decoders for intracortical brain-to-text translation using phonetic and character targets.

AI/ML arXiv cs.AI

Searching for Robust Augmentations to Improve Out-of-Domain Generalization in Dermoscopic Skin Cancer Classification

Research on using robust data augmentations to improve the out-of-domain generalization of dermoscopic skin cancer classifiers.

Open Source arXiv cs.AI

MediaWiki Code2Code Search: Neural Retrieval for the Semantic Discovery of Open-Source Software Entities

MediaWiki Code2Code Search is a neural retrieval system for semantic code discovery across MediaWiki repositories using FAISS IVF-PQ indexing.

Cybersecurity arXiv cs.AI

Physically Real-time Infrared Attack against Optical Flow Estimation Networks

Researchers developed a real-time physical attack on Optical Flow Estimation Networks using infrared lights to compromise autonomous driving and motion detection systems.

AI/ML arXiv cs.AI

Constitutional Midtraining: Content Presence Drives Alignment Gains

A study introduces constitutional midtraining, integrating principled values-based content into the training process of 120B scale models to improve alignment durability.

Cybersecurity arXiv cs.AI

Graph Is the Verifier: Agentic Reinforcement Learning for Interprocedural Vulnerability Detection

VulAgentRL is a new agentic reinforcement learning framework that uses Code Property Graphs to detect interprocedural vulnerabilities in software.

AI/ML arXiv cs.AI

Scientific Knowledge Discovery in the Age of Large Language Models

A survey paper examines the application of generative LLMs for scientific knowledge discovery, specifically literature retrieval and screening.

AI/ML arXiv cs.AI

Efficient Heteroscedastic Bayesian Optimization for Risk-Aware AutoRL

ERAHBO is proposed as a risk-aware Bayesian Optimization method to efficiently tune hyperparameters in stochastic reinforcement learning environments.

AI/ML arXiv cs.AI

MPEcho: A Melody and Phoneme-Aware Generative Framework for Controllable Cover Song Generation

MPEcho is a generative framework for controllable cover song generation that uses a new transcription model, Phonsa, to improve lyric accuracy.

AI/ML arXiv cs.AI

Automated Multilabel Mpox Research Classification with Explainable Transformer Models

A research project uses BERT and SHAP to automate the multilabel classification of Mpox research articles for better public health organization.

AI/ML arXiv cs.AI

FARI: Robust One-Step Inversion for Watermarking in Diffusion Models

FARI introduces a one-step inversion framework for faster and more robust watermarking in diffusion models via adversarial LoRA fine-tuning.