AI/ML arXiv cs.AI

Veriphi: Attack-Guided Neural Network Verification with Dataset-Dependent Training Methods

The Veriphi system provides GPU-accelerated neural network verification, demonstrating that the effectiveness of training methods is dependent on the dataset used.

AI/ML arXiv cs.AI

What Does the Weight Norm Control in Grokking? Logit-Scale Mediation under Cross-Entropy

Study reveals that the 'grokking' phenomenon in neural networks is primarily driven by logit scale rather than weight norm, contrary to previous assumptions.

AI/ML arXiv cs.AI

Structured Representation Learning with Locally Linear Embeddings and Adaptive Feature Fusion

A new reinforcement learning framework inspired by neuroscience uses locally linear embeddings and adaptive gating to improve learning efficiency.

AI/ML arXiv cs.AI

MagpieTTS-LF: Inference-Time Long-Form Speech Generation Without Training on Long-Form data

MagpieTTS-LF introduces an inference-time approach to generate coherent long-form speech without requiring retraining on long-form data.

AI/ML arXiv cs.AI

SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR

Research indicates that overtraining during SFT can lead to rank inversion and entropy collapse when using RLVR, specifically affecting models like Qwen2.5-Coder.

AI/ML arXiv cs.AI

Neural Phase Correlation

Introduction of a learned generalization of phase correlation that enables the discovery of transformations between observations in the Fourier domain.

AI/ML arXiv cs.AI

PSyGenTAB: A Privacy-Preserving Framework for Synthetic Clinical Tabular Data Generation via Constrained Optimization

PSyGenTAB is a privacy-preserving framework for generating synthetic clinical tabular data using constrained optimization to balance privacy and utility.

AI/ML arXiv cs.AI

As You Wish: Mission Planning with Formal Verification using LLMs in Precision Agriculture

A mission planning system for precision agriculture uses LLMs and linear temporal logic (LTL) to formally verify natural language mission specifications.

Homelab/Self-Hosting Hacker News

Smashed Toilet Phone Web Server

A project involving the creation of a web server hosted on a 'Smashed Toilet Phone'.

AI/ML arXiv cs.AI

From Specification to Execution: AI Assisted Scientific Workflow Management

Proposes an AI-assisted scientific workflow management approach using specification-driven generation and an LLM-based debugging agent integrated with Pegasus.

AI/ML arXiv cs.AI

CAOA -- Completion-Assisted Object-CAD Alignment

Introduces CAOA, a method for aligning CAD models to indoor RGB-D scans using point cloud completion and symmetry-aware relative pose estimation.

AI/ML arXiv cs.AI

Self-CTRL: Self-Consistency Training with Reinforcement Learning

Introduces Self-CTRL, a reinforcement learning method to improve consistency between a language model's self-explanations and its actual behavior.

Cybersecurity arXiv cs.AI

SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents

Presents SafeClawBench, a staged benchmark for evaluating security failures in tool-using LLM agents across various attack vectors.

AI/ML arXiv cs.AI

Guava: An Effective and Universal Harness for Embodied Manipulation

Proposes Guava, a harness framework for embodied tool use that enables compact open-source models to perform complex manipulation tasks.

AI/ML arXiv cs.AI

Redact or Keep? A Fully Local AI Cascade for Educational Dialogue De-Identification

Describes a fully local AI cascade framework for de-identifying PII in educational dialogues, outperforming commercial APIs on a single laptop.

AI/ML arXiv cs.AI

RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation

Details RankGraph-2, Meta's lifecycle co-design framework for billion-node graph learning in recommendation systems to optimize retrieval and serving.

AI/ML arXiv cs.AI

LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents

Introduces LLMZero, a system using LLM agents to automatically discover adaptive training strategies for reinforcement learning post-training.

AI/ML arXiv cs.AI

Learning-Based Decision Making for Combustion Phasing Control in Multi-Fuel CI Engines with Latent Fuel Reactivity Estimation

Proposes a GRU-guided RL framework for combustion phasing control in multi-fuel engines, managing latent fuel reactivity estimation.

Hardware/Chips arXiv cs.AI

Deep Learning-Driven Inverse Design of Doherty Power Amplifiers Using Pixelated Combiners and Dual-State Impedance Synthesis

Utilizes CNNs and genetic algorithms for the inverse design of high-efficiency Doherty power amplifiers using pixelated combiners.

Hardware/Chips arXiv cs.AI

Deep-Learning-Based Pixelated Microwave Filter Design and Characterization using Electro-Optical Electric-Field Measurements

Applies deep learning and genetic algorithms to automate the design and characterization of pixelated microwave filters.