AI/ML arXiv cs.AI

Latent graph encoding of multimodal neuroimaging features with generative AI architectures

Development of gMMVAE, a multimodal graph variational autoencoder for encoding neuroimaging features from MRI data.

AI/ML arXiv cs.AI

Ad Headline Generation using Self-Critical Masked Language Model

Proposes a programmatic solution for generating e-commerce ad headlines using Reinforcement Learning Policy gradient methods on Transformer-based Masked Language Models.

AI/ML arXiv cs.AI

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs

Introduces a training-free, gradient-based method for speech-to-text alignment that works across diverse ASR models, including speech LLMs.

AI/ML arXiv cs.AI

A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong

Presents a lightweight, game-agnostic recipe for training competitive RL agents for imperfect-information card games, released as a reusable package.

AI/ML arXiv cs.AI

GemNav: Discrete-Token Visual Robot Navigation using a Multimodal Large Language Model

Introduces GemNav, a data-efficient robot navigation policy that adapts a frozen MLLM using LoRA on the language tower without auxiliary visual encoders.

AI/ML arXiv cs.AI

ReMoDEx: A Local-to-Global Relevance-Based Model Decision Explainability Framework for large-Scale Image Datasets

Proposes ReMoDEx, a scalable framework for assessing model decision behavior in image classification to detect shortcut learning via relevance maps.

AI/ML arXiv cs.AI

Computing with Stochastic Oracles in AI-Augmented Computation

Studies the Stochastic-Oracle Turing Machine (SOTM) framework to model AI-augmented computation and analyze the impact of response reuse on performance.

AI/ML arXiv cs.AI

LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models

Introduces LoCA, a parameter-efficient fine-tuning framework that decouples channel and spatial adaptation for Vision Foundation Models.

AI/ML arXiv cs.AI

MADB: A Large-Scale Music Aesthetics Dataset with Professional and Multi-Dimensional Annotations

Introduces MADB, a large-scale dataset for music aesthetics assessment with professional multi-dimensional annotations.

AI/ML arXiv cs.AI

Imputation Meets Clustering: Exploiting Latent Subgroup Structure for Missing Data Recovery

Proposes CAGI, a framework that co-optimizes clustering and imputation to recover missing data by exploiting latent subgroup structures.

AI/ML arXiv cs.AI

Comprehensive Evaluation of Large Language Model Responses: A Multi-Factor Scoring System

Presents a multi-factor scoring system for the comprehensive evaluation of LLM responses, including accuracy, conciseness, and factual consistency.

Software Engineering Hacker News

Postgres rewritten in Rust, now passing 100% of the Postgres regression tests

A project has rewritten the PostgreSQL database engine in Rust, successfully passing 100% of the official regression tests.

Other Hacker News

How Donkey Kong Toppled Atari

An exploration of the historical competition between Donkey Kong and Atari during the early era of gaming.

Other Hacker News

I Built the Only 2026 WWII Jeep

A detailed account of building a replica of a rare 1942 WWII Jeep.

AI/ML arXiv cs.AI

SmartHomeSecure: Automated Detection and Repair of Smart Home Configuration Errors Using Large Language Models

SmartHomeSecure uses program analysis and constrained LLM generation to automatically detect and repair configuration errors in Home Assistant YAML files.

AI/ML arXiv cs.AI

AirPASS: Over-the-Air Federated Learning via Pinching Antenna Systems

AirPASS introduces an alternating optimization framework for over-the-air federated learning using pinching antenna systems to improve wireless device selection and beamforming.

AI/ML arXiv cs.AI

From Agentic to Autogenic Network Management for AI-Native 6G and Beyond: A Standards Perspective

A proposal for 'Autogenic' network management in 6G, enabling systems to self-program and evolve their own automation software using AI agents.

AI/ML arXiv cs.AI

Enhancing deep learning models for time series classification via knowledge distillation

Research on applying knowledge distillation to make deep learning models for time series classification more efficient for resource-limited environments.

AI/ML arXiv cs.AI

What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study

A study on predicting the correctness of Text-to-SQL queries, finding that LLM-based verification and ensembles outperform self-consistency and log-probability signals.

AI/ML arXiv cs.AI

A Multi-Analyst LLM Pipeline for Auditable Rule Discovery Across 68 Public Physiological Corpora

An LLM-driven pipeline for extracting and auditing rule shapes from 68 public physiological corpora to guide the design of contactless monitoring hardware.