Software Engineering Hacker News

Show HN: Meow – The 4th and final JavaScript runtime and toolchain

A new JavaScript runtime and toolchain called Meow is introduced, claiming to be the fourth and final runtime in the ecosystem.

Other Hacker News

The vibration of the pager has a sound all its own

A personal reflection or discussion on the distinct sensory experience and sound of a pager's vibration.

AI/ML arXiv cs.AI

Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR

Proposes geometry-preserving orthonormal initialization for LoRA in Reinforcement Learning with Verifiable Rewards (RLVR) to improve stability and performance.

AI/ML arXiv cs.AI

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

Introduces Medical Reasoning-aware Policy Optimization (MRPO), an RL algorithm that uses step-wise process rewards to mitigate cascading errors in medical multimodal reasoning.

AI/ML arXiv cs.AI

Real-Time Source-Free Object Detection

Presents RT-SFOD, a real-time source-free object detection method based on YOLOv10 that optimizes the speed-accuracy trade-off for autonomous systems.

AI/ML arXiv cs.AI

Bridging Local Observation and Global Simulation in Closed-Loop Traffic Modeling

Introduces CRAFT, a framework to align local observations with global simulations in closed-loop traffic modeling to reduce autonomous driving failures.

AI/ML arXiv cs.AI

Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models

Presents Z-1, an RL post-training framework using GRPO to improve the success rate of Vision-Language-Action (VLA) models in robotic manipulation.

AI/ML arXiv cs.AI

Belief Contraction in Dynamic Epistemic Logic

Explores belief contraction in Dynamic Epistemic Logic, introducing a mechanism defined on standard Kripke models to handle factual proposition contraction.

Software Engineering arXiv cs.AI

Modal CEGAR-tableaux with RECAR and resolution-based SAT-shortcuts

Investigates integrating SAT-shortcuts into CEGAR-tableaux using the KSP modal resolution prover, showing superior performance on large satisfiable problems.

AI/ML arXiv cs.AI

Better Understanding, Understanding Better

Proposes a comparative epistemic logic of understanding that uses level-indexed modalities to represent and compare degrees of understanding between agents.

AI/ML Hacker News

Senior SWE-Bench: open-source benchmark that assesses agents as senior engineers

Senior SWE-Bench is an open-source benchmark designed to evaluate the capabilities of AI agents in performing complex software engineering tasks typical of senior engineers.

Other Hacker News

Bring Back Crappy Forums

A discussion advocating for the return of simple, community-driven forums over modern, centralized social media platforms.

AI/ML arXiv cs.AI

Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models

Researchers evaluate Sparse Autoencoders (SAEs) for unlearning in diffusion models, finding that while SAEs are great for detection, direct latent intervention often causes visual artifacts.

AI/ML arXiv cs.AI

Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian

A study on cross-lingual relation extraction for Romanian using LLMs, highlighting that QLoRA fine-tuning significantly outperforms zero-shot prompting and outperforms small encoder models.

AI/ML arXiv cs.AI

Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue

Research indicates that Vision-Language Models (VLMs) tend to overestimate common ground in asymmetric dialogues, relying on static map cues rather than dialogue history.

AI/ML arXiv cs.AI

STEB: Style Text Embedding Benchmark

Introduction of STEB, an open-source benchmark for standardizing the evaluation of style text embeddings across various linguistic tasks and languages.

AI/ML arXiv cs.AI

FedXDS: Leveraging Model Attribution Methods to counteract Data Heterogeneity in Federated Learning

FedXDS leverages XAI-guided data sharing to combat data heterogeneity in federated learning, providing theoretical privacy guarantees and faster convergence.

AI/ML arXiv cs.AI

JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering

The JL1-CC&QA benchmark extends remote sensing change detection with change captioning and question answering to provide semantic understanding of land-cover changes.

Other arXiv cs.AI

A Technical Typology of AI Systems in Public Administration

The paper proposes a technical typology to categorize AI systems in public administration to improve accountability and procedural justice.

AI/ML arXiv cs.AI

CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield

CHERRY introduces compute-efficient language model training via selective supervision, depth compression with recurrent recovery, and a mixture of efficient experts.