AI/ML arXiv cs.AI

A Comparative Study on Affective Cues in Text Embeddings Across Psychological Emotion Theories

Comparative study on how well modern text encoders capture psychological emotion theories at word and sentence levels.

Cybersecurity arXiv cs.AI

From Tool Connection to Execution Control: Benchmarking Security Invariants in MCP-Style Agent Runtimes

Proposal of the Handle-Capability Protocol (HCP) to add an execution-control layer to MCP-style agent runtimes for improved security invariants.

Software Engineering arXiv cs.AI

Diff-Based Code Corruption using LLMs for Large-Scale Bugfix Benchmarking

Introduction of MegaBugFix, a large-scale benchmark of 12,629 buggy Python programs created via LLM-generated diffs for bugfixing evaluation.

AI/ML arXiv cs.AI

AB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question Answering

AB-RAG, a training-free framework that adaptively decides the retrieval budget for RAG systems based on confidence estimates.

Tech Business/VC The Verge

Meta is adding ridiculous ‘rate limits’ and a soft paywall to its smart glasses

Meta is introducing monthly rate limits on AI features for its smart glasses, requiring a paid subscription for extended use.

AI/ML arXiv cs.AI

Modification-Considering Value Learning for Reward Hacking Mitigation in RL

Researchers propose Modification-Considering Value Learning (MCVL) to mitigate reward hacking in reinforcement learning by filtering transitions that decrease a bootstrapped-return estimator.

AI/ML arXiv cs.AI

RGLD: Randomized Global-Local Density Estimation for Tabular Anomaly Detection

RGLD is a new randomized global-local density estimator designed for efficient unsupervised tabular anomaly detection, outperforming deep detectors in speed and accuracy.

AI/ML arXiv cs.AI

Evidence-Based Text-Conditioned 3D CT Synthesis for Ovarian Cancer

OvESyn is a framework for text-conditioned 3D CT synthesis for ovarian cancer, enabling the generation of synthetic medical imaging cohorts without original radiology reports.

AI/ML arXiv cs.AI

Compositional Dynamics in Learning and Mechanics

This paper presents a compositional setting where gradient-based learning and Hamiltonian mechanics are treated as functorial semantics using an operad of smooth adaptive arrangements.

AI/ML arXiv cs.AI

Fine-Tuning General-Purpose Large Language Models for Agricultural Applications:A Reproducible Framework and Evaluation Protocol Based on Qwen3-8B

The authors introduce AgriTune-R, a reproducible framework for adapting general-purpose LLMs (specifically Qwen3-8B) to specialized agricultural applications.

AI/ML arXiv cs.AI

Arbitrary Reduction of Validation Error for AI Decision Tests using Homomorphic AI and Repetition Codes

The paper describes HbHAI (Hash-based Homomorphic AI), which allows processing encrypted data with native AI algorithms while reducing computation time and energy footprint.

AI/ML arXiv cs.AI

Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation

An empirical study on reward-free code alignment (DPO and BoNBoN) reveals that aligning pretrained models yields larger improvements than aligning already finetuned models.

AI/ML arXiv cs.AI

BERTomelo: Your Portuguese Encoder Best Friend

BERTomelo is a new monolingual Portuguese encoder based on ModernBERT, trained on a massive corpus to outperform previous Portuguese-specific models.

AI/ML arXiv cs.AI

Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis

A new framework for weather video synthesis uses semantics, physics-informed dynamics, and scene geometry to generate realistic adverse weather effects for video editors.

Software Engineering Hacker News

Google copybara: moving code between repositories

Google's Copybara is a tool for moving code between repositories while maintaining history and handling transformations.

AI/ML Hacker News

Anthropic to restoring access to Claude Fable 5 and Mythos 5 from tomorrow

Anthropic is restoring access to Claude Fable 5 and Mythos 5 models.

AI/ML Hacker News

Claude Fable 5 export control lifted

Export controls on Claude Fable 5 have been lifted.

AI/ML arXiv cs.AI

Exploring the Value of Diverse LLM Explanations in Introductory Programming

Research indicates that providing students with diverse LLM-generated explanations for programming exercises improves understanding and accuracy.

AI/ML arXiv cs.AI

A Task-Driven and Quality-Assured Agent Framework for SAR Data Generation

SAGA is a new agent framework designed for reliable and quality-assured synthetic aperture radar (SAR) data generation and augmentation.

AI/ML arXiv cs.AI

Latent Bridges for Multi-Table Question Answering

GRAB is a new pipeline that uses a graph encoder and latent bridges to improve multi-table question answering for LLMs without freezing the LLM itself.