AI News

A Living Benchmark for Information Retrieval from Electronic Health Records (arxiv.org)

Concurrent Split Learning Through Stable Client Clustering (arxiv.org)

Transcript-Supervised Post-Training of Generative Speech Enhancement on Real Recordings via Reinforce Adjoint Matching (arxiv.org)

SciWalker: Synthesizing Scientific Coding Problems with Operator Graphs and Execution Feedback (arxiv.org)

Improving Calibration of Black-Box Radiology AI Using Test-Time Augmentation (arxiv.org)

MF-SCBO : Multi-fidelity Scalable Constrained Bayesian Optimization (arxiv.org)

Error- and Prediction-Driven Motor Learning in the Cortico-Cerebellar Loop (arxiv.org)

CrossScale-GLIO: Topology-Preserving Vision-Language Alignment of MRI and Whole-Slide Histopathology for Diffuse Glioma (arxiv.org)

Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior (arxiv.org)

KathDB-FAO: Synthesized Query Plans in a Multimodal DBMS (arxiv.org)

An Explainable DistilBERT-BiLSTM-Attention Framework for Binary and Multi-Class Hate Speech Detection (arxiv.org)

Temporal Learning for End-Effector Position Estimation under Aerodynamic Disturbances in Aerial Continuum Manipulation (arxiv.org)

Technical Manual for Toolkit for Confidence-Corpus Consistency via Fine-Tuning on a Fabricated Corpus (arxiv.org)

Broadening Uncertainty Estimation for Audio Question Answering Across Methods, Formats, and Inputs (arxiv.org)

Robots That Take Initiative: A Framework for Building and Evaluating Proactive Robots (arxiv.org)

On the Effectiveness of Kernel-Level Evidence for Agent Security (arxiv.org)

Calibrated Decision Models for Autonomous Penetration-Testing Harnesses: JEV and Laya as System One Decision Layers for LLM-Driven Pentest Agents (arxiv.org)

Post-Training Leaves Behavioral Shadows on Unrelated Decisions (arxiv.org)

SARFusion: Scene-Aware Routing Fusion for Robust Camera-LiDAR 3D Object Detection (arxiv.org)

TOLA: Text-aware One-Step Latent Adaptation for Diffusion-based Text Image Super-Resolution (arxiv.org)

No More Free Lunch: Corpus Task Complexity Matters as Corpora Grow (arxiv.org)

Hyperbolic Multimodal Continual Learning: A Closest-Admissible Solution (arxiv.org)

A Corpus of Real Scam- and Spam-Call Conversations from an Active Voice-Agent Honeypot (arxiv.org)

ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds (arxiv.org)

Where LLM Graders Succeed and Break: Evidence from Two Computer-Science Exams (arxiv.org)

ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts (arxiv.org)

Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure (arxiv.org)

Dual-Frontier: When Can an Agent Trust Its World Model? (arxiv.org)

Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction (arxiv.org)

DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documents (arxiv.org)

Graph-Based Inference and Topology-Aware Multi-Agent Reinforcement Learning for Large-Scale Railway Network Management (arxiv.org)

Beyond Compression: Training Latent Representations for Stable Long-Horizon Rollout in Neural Surrogate Solvers (arxiv.org)

Minimally Invasive Steering of Language Models (arxiv.org)

PoEM: Predicting RL Outcomes from Existing Policies (arxiv.org)

To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech (arxiv.org)

Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning (arxiv.org)

CaliPPer: quantifying, predicting and improving AI model performance for binding prediction (arxiv.org)

Design and Evaluation of LLM Chaining-Based Task Planning for General Purpose Service Robots (arxiv.org)

RADAR: Readiness for AI Discovery and Agentic Reach (arxiv.org)

Hybrid Variational Quantum-Classical Framework with Adaptive Weighting and Efficiency Assessment (arxiv.org)

Algebraic Expressivity Certificates for Shallow Polynomial Neural Networks (arxiv.org)

An Exposition of GPT Astra's Proof of Lower Bound on DP Continual Counting (arxiv.org)

IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis (arxiv.org)

AIR: Analytic Imbalance Rectifier for Continual Learning (arxiv.org)

Task-Resolved Fisher Spectroscopy for Quantum Reservoir Computing (arxiv.org)

The kernel of graph indices for vector search (arxiv.org)

What About Rails? (jardo.dev)

Jev and System One Models: Calibration Beats Accuracy (www.kartikpansuriya.com)

Wand (www.producthunt.com)

Jango (www.producthunt.com)