AI News

Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics (arxiv.org)

TaskFusion: Continual Anomaly Detection for Heterogeneous Tabular Data (arxiv.org)

Compatibility-Aware Dynamic Fine-Tuning for Large Language Models (arxiv.org)

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement (arxiv.org)

Frozen Multimodal Embeddings for Personality and Cognitive Ability Assessment in Asynchronous Video Interviews (arxiv.org)

Exploration Structure in LLM Agents for Multi-File Change Localization (arxiv.org)

Runtime Enforcement of Hybrid System Properties (arxiv.org)

ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward (arxiv.org)

Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models (arxiv.org)

A2SG:Adaptive and Asymmetric Surrogate Gradients for Training Deep Spiking Neural Networks (arxiv.org)

Physically Constrained Ensemble Gaussian Process Modelling for Expensive Quantum Systems with Heteroskedastic Noise (arxiv.org)

On the Limits of LLM-as-Judge for Scientific Novelty Assessment (arxiv.org)

"That's AI Slop, You Bot!" Studying Accusations, Evidence, and Credibility in Online Discourse Towards LLM-Generated Comments (arxiv.org)

Non-frontal face recognition using GANs and memristor-based classifiers (arxiv.org)

OpenMedReason: Scientific Reasoning Supervision for Medical Vision-Language Models (arxiv.org)

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application (arxiv.org)

MASK: Multi-Agent Semantic K-Scheduling for Risk-Sensitive 6G Robotics (arxiv.org)

My Chemical Harness: Evolutionary Molecular Design over Synthetic Pathways with Large Language Model Agents (arxiv.org)

Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite (arxiv.org)

Geometric bias in eigenspace perturbation under random heterogeneous noise (arxiv.org)

Multi-agent rendezvous in fluid flows via reinforcement learning (arxiv.org)

Massive Open-Vocabulary Keyword Spotting (arxiv.org)

Phi-Actor-Critic: Steering General-Sum Games to Pareto-Efficient Correlated Equilibria (arxiv.org)

Interpretable Neural Marked Statistics for Cosmological Inference (arxiv.org)

SPADE: Split-and-Delay Embeddings for Autoregressive High-Granularity Calorimeter Simulation (arxiv.org)

Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends (arxiv.org)

Making Foresight Actionable: Repurposing Representation Alignment in World Action Models (arxiv.org)

Adapting Prithvi-EO for Fallow Detection for Food-Water Nexus: ViT-Adapter Necks and Parameter-Efficient Backbone tuning of Geospatial Foundation Model (arxiv.org)

Rule Taxonomy and Evolution in AI IDEs: A Mining and Survey Study (arxiv.org)

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models (arxiv.org)

When Probing Accuracy Saturates, Fragility Resolves: A Complementary Metric for LLM Pre-Training Analysis (arxiv.org)

Small Experiments, Cheaper Decisions: A Case Study in Staged Promotion for Micro-Pretraining (arxiv.org)

A Scalable PyTorch Abstraction for Multi-GPU Gaussian Splatting (arxiv.org)

Spatially Masked Regression Reveals Local and Distributed Predictability in Electrophysiological Recordings (arxiv.org)

Toward Preference-aligned Large Language Models via Residual-based Model Steering (arxiv.org)

Geometric Metrics and LLMs: What They Measure and When They Work (arxiv.org)

Noise-Guided Transport for Imitation Learning (arxiv.org)

Certifiable Safe RLHF: Semantic Grounding and Fixed Penalty Constraint Optimization for Safer LLM Alignment (arxiv.org)

Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction (arxiv.org)

APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection (arxiv.org)

Density estimation for Hellinger via minimum-distance estimators: mixtures of Gaussians, log-concave, and more (arxiv.org)

Evaluating and Combating the Impact of Concept Drift on the Performance of Machine Learning-Based Phishing Detection Systems (arxiv.org)

Parameter-Efficient Adapter Tuning for Tabular-Image Multimodal Learning (arxiv.org)

FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI (arxiv.org)

Grounding Computer Use Agents on Human Demonstrations (arxiv.org)

Irresponsible AI: big tech's influence on AI research and associated impacts (arxiv.org)

Semantic search for 100M+ galaxy images using AI-generated captions (arxiv.org)

Towards Deep Learning Surrogate for the Forward Problem in Electrocardiology: A Scalable Alternative to Physics-Based Models (arxiv.org)

Improving Generalization and Data Efficiency with Diffusion in Offline Multi-agent RL (arxiv.org)

Unifying Learning Dynamics and Generalization in Transformers Scaling Law (arxiv.org)