AI News

Speed Limit for Information Acquisition in Stochastic Learning Dynamics (arxiv.org)

DRIFT: Removing Diffusion Watermarks by Deflecting the Generative Trajectory (arxiv.org)

Instance-wise Linearization of Neural Network for Model Interpretation (arxiv.org)

Optimal Slice-Adaptive Tuning of Hybrid Slice Sampling (arxiv.org)

A Transformer-Based Delta Expression Encoder for Psilocybin Transcriptional Response: Architecture, Representations, and Biological Validation (arxiv.org)

PocketVE: Stable and Property-Guided Structure-Based Drug Design with Variance-Exploding Diffusion (arxiv.org)

Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation (arxiv.org)

A Gradient-based yet Spike-Timing-Dependent Solution to the Feedback Learning Problem in Neural Microcircuits (arxiv.org)

MI-PEFT: Mixture-of-Experts Integrated Parameter-Efficient Fine-Tuning Protein Language Models Improves Acidophilic Proteins Classification (arxiv.org)

Bayesian Matrix-Valued Graphs for Context-Dependent Multivariate Relationships (arxiv.org)

A Quantitative Evaluation Framework for Temporal Explainability in Echocardiographic Video Segmentation (arxiv.org)

MamMA: A Mamba-Based Pedestrian Trajectory Prediction Algorithm Considering Occupancy Map and Pedestrian Awareness States (arxiv.org)

VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities (arxiv.org)

SolarBench: A global solar energy nowcasting benchmark (arxiv.org)

Segment Any Motion with Radar: Robust Multimodal Moving-Object Segmentation and Tracking (arxiv.org)

Omni Interaction Agent Technical Report (arxiv.org)

SQLMorph: Query Mutation and Fine-Grained Metrics for Text-to-SQL Evaluation (arxiv.org)

Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation (arxiv.org)

OntoKG-EQ: A provenance-grounded, competency-question-governed knowledge graph for auditable analyst querying (arxiv.org)

Hi-FLoop: Hierarchical State-Feedback Loops for Multi-Timescale World Modeling (arxiv.org)

Evidence-Grounded Retrieval for Investigation Hunt Lead Generation from CTI Reports (arxiv.org)

Silent Revision: Measuring Undisclosed Change in the Safety Frameworks of Frontier AI Developers (arxiv.org)

Kairos: A Dataset for Fine-Grained Video-Language Modeling over Space, Time, and Dynamics (arxiv.org)

CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling (arxiv.org)

BIFTA: Brain-Inspired Few-Shot Tactile Adaptation for Unknown Sensors (arxiv.org)

TriCCOT: Tri-part Convolutional Conformal Transformer for Onboard Space Object Detection (arxiv.org)

From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video (arxiv.org)

Neptune: An AI model for Global Ocean Subseasonal Prediction (arxiv.org)

Benchmark Scores Are Pipeline-Dependent: A Reliability Audit of Cybersecurity LLM Benchmarks (arxiv.org)

The Unreliable Progress Bar: Can LLM Agents Reliably Report Task Progress Throughout Execution? (arxiv.org)

Do New Attention Mechanisms Actually Fix Attention Sinks at Million-Token Context? (arxiv.org)

ModularPhaseNet: Finite-Cyclic Phase Geometry for Computable Semantic Hierarchy, Direction, and Context Consistency in Standard Transformers (arxiv.org)

Discovering Latent Groups for Robust Classification (arxiv.org)

VegSim: A Geospatial World Model for Scenario-Conditioned Vegetation Simulation (arxiv.org)

Counter-Swarm Doctrine: Containing Coordinated Agent Intrusions (arxiv.org)

Causal DAG Identification for Count Data via Poisson Thinning Structural Equation Models (arxiv.org)

GradeTrap: Authority Cues in Images Shift VLM Judgments Despite Explicit Instructions to Ignore Them (arxiv.org)

Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model (arxiv.org)

RoboCousin: Build Your Own Simulation Playground for Robust Bimanual Robotic Manipulation (arxiv.org)

Knowing Your Uncertainty -- On the application of LLM in social sciences (arxiv.org)

Unveiling Hidden Threats: Using Fractal Triggers to Boost Stealthiness of Distributed Backdoor Attacks in Federated Learning (arxiv.org)

PAN: A World Model for General, Actionable, and Long-Horizon World Simulation (arxiv.org)

Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs (arxiv.org)

Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and Navigation (arxiv.org)

Audio-Maestro: Enhancing Large Audio-Language Models with Tool-Augmented Reasoning (arxiv.org)

AudioFuse: Unified Spectral-Temporal Learning via a Hybrid ViT-1D CNN Architecture for Robust Phonocardiogram Classification (arxiv.org)

S$^3$F-Net: A Multi-Modal Approach to Medical Image Classification via Spatial-Spectral Summarizer Fusion Network (arxiv.org)

Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking (arxiv.org)

BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints (arxiv.org)

D3ARC: Time-Critical Distributed Disaster Detection for Asynchronous Cooperative Multi-Robot Systems (arxiv.org)