AI News

Multi-Modal Machine Learning for Breast Cancer Recurrence Prediction (arxiv.org)

Generating Rectifiable Measures through Neural Networks (arxiv.org)

Speedrunning Tabular Foundation Model Pretraining (arxiv.org)

PURGE: Projected Unlearning via Retain-Guided Erasure (arxiv.org)

Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation (arxiv.org)

Set-Preserving Calibration from Conformal P-Values to E-Values (arxiv.org)

From Script to Semantics: Prompting Strategies for African NLI (arxiv.org)

Building Reliable Long-Form Generation via Hallucination Rejection Sampling (arxiv.org)

Estimating Bidirectional Causal Effects with Large Scale Online Kernel Learning (arxiv.org)

Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs (arxiv.org)

Optimal and exact recovery on the general nonuniform Hypergraph Stochastic Block Model (arxiv.org)

Hierarchies of Calibration: Classification meets Regression (arxiv.org)

TiWeaver: Unified Temporal Dynamics Modeling via Contextual Patching (arxiv.org)

Signed Spiking Neuron Enabled by an Orthogonal-Easy-Axis Magnetic Tunnel Junction (arxiv.org)

Explainable Forecasting of Scientific Breakthroughs from Concept Network Dynamics (arxiv.org)

RogueMerge: Robust and Unified Attacks against LLM Model Merging (arxiv.org)

Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation (arxiv.org)

A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs (arxiv.org)

Patcher: Post-Hoc Patching of Backdoored Large Language Models (arxiv.org)

Combining Statistical Features and Deep Encodings for Rehearsal-Based Class-Incremental Time Series Classification (arxiv.org)

TreeFlash: Parallel AR-Approximation for Faster Speculative Decoding (arxiv.org)

ConTraIRL: Factorized Contrastive Abstractions for Transferable IRL (arxiv.org)

Echelon: Auditable Aggregate-Only Language-Model Adaptation Across Privacy Boundaries (arxiv.org)

Analytical Evaluation of DCA Convergence Properties for Minimizing Prediction Functions of Gaussian RBF Support Vector Regression (arxiv.org)

Hand Trajectory Fusion for Egocentric Natural Language Query Grounding (arxiv.org)

Speech Emotion Recognition using Attention-based LSTM-Network with Residual Connection (arxiv.org)

COD10K-C: Benchmarking Robustness of Camouflaged Object Detection Under Natural Image Corruptions (arxiv.org)

Reproducibility is the New Copyleft: Defining AGI-oriented Reproducible Builds (arxiv.org)

PerchRL: Vision-Based Agile Perching on Inclined Platforms under Rapid and Irregular Motion (arxiv.org)

Dynamic Short Convolutions Improve Transformers (arxiv.org)

SCOPE: Real-Time Natural Language Camera Agent at the Edge (arxiv.org)

Partial recovery and weak consistency in the non-uniform hypergraph Stochastic Block Model (arxiv.org)

FlowGuard: Flow Matching for Identity-Independent Detection of Data-Free Model Stealing Attacks on Energy System Intrusion Detection Systems (arxiv.org)

The DeepSpeak-Agentic Dataset (arxiv.org)

From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models (arxiv.org)

Greed is Good: A Unifying Perspective on Guided Generation (arxiv.org)

NeuroArmor: Safe-Variant-Guided Representation Consistency for Selective Re-Anchoring in Jailbreak Defense (arxiv.org)

Calibrating Urban Traffic Simulation from Sparse Road Observations via Genetic Optimization (arxiv.org)

Contrastive Neural Algorithmic Reasoning for Graph Coloring (arxiv.org)

Auditing Engagement Incentives in the Kidfluencer Ecosystem: A Multimodal Weak Supervision Approach (arxiv.org)

Laplacian Representations for Decision-Time Planning (arxiv.org)

EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents (arxiv.org)

Leveraging BART to Assess CS1 C++ Programming Assignments using Rubric-based Criteria (arxiv.org)

A Geometric Lens on Physics-Aligned Data Compression (arxiv.org)

Privacy-Robust Incrementality Measurement for Advertising Systems under Signal Loss (arxiv.org)

P\textsuperscript{2}-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization (arxiv.org)

A Robust Optimization Approach to Sparse Principal Component Analysis (arxiv.org)

Tailoring Strictly Proper Scoring Rules for Downstream Tasks: An Application to Causal Inference (arxiv.org)

Markov chain Monte Carlo without evaluating the target: an auxiliary variable approach (arxiv.org)

Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering (arxiv.org)