AI News

PACT: Learning Diverse Diagnostic Strategies via Privileged Synthesis and Branch Consensus (arxiv.org)

Report on CHIIR 2026 Workshop on Generative AI and Academic Search (GAI&AS) (arxiv.org)

From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing (arxiv.org)

SpectraLDS: Provable Distillation for Linear Dynamical Systems (arxiv.org)

Learning from flowsheets: A generative transformer model for autocompletion of flowsheets (arxiv.org)

Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models (arxiv.org)

Hybrid Robustness Verification for Spatio-Temporal Neural Networks (arxiv.org)

Adaptive directional gradients for parameterised quantum circuits (arxiv.org)

Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA (arxiv.org)

Towards End to End Motion Planning and Execution for Autonomous Underwater Vehicles Using Reinforcement Learning (arxiv.org)

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization (arxiv.org)

Predictive Coding with Bayesian Priors via Proximal Gradients (arxiv.org)

SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC) (arxiv.org)

On solving symmetric multi-type orthogonal non-negative matrix tri-factorization problem (arxiv.org)

Speaker-Invariant Representation Learning for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneck (arxiv.org)

Learning to Solve Generative ODEs Beyond the Linear Span (arxiv.org)

A Comparison of SSL-Based Feature Extractors and Back-End Classifiers for Spoofing Detection: A Multi-Corpus Training and Cross-Linguistic Analysis (arxiv.org)

TeamHerald@CHIPSAL 2026: Hate Speech Detection and Sentiment Analysis of Nepali Memes using Transformer-based Architectures and Ensemble Learning (arxiv.org)

Parameter Tuning with Generalization Guarantees for GPU-Accelerated Linear Programming (arxiv.org)

Bayesian Optimization of a Multi-Product Chemical Reactor Using Composite Models and Partial Physics Knowledge (arxiv.org)

Quantum Global Variational Learning for Quantum Error Correction (arxiv.org)

Convolutional Sparse Coding via the Locally Competitive Algorithm on Loihi 2 (arxiv.org)

A spectral audit framework reveals task-dependent aperiodic reliance across EEG and ECG deep learning (arxiv.org)

Structuring agentic AI for HPC code modernization (arxiv.org)

Lost in the Non-convex Loss Landscape: How to Fine-tune the Large Time Series Model? (arxiv.org)

Resource-aware Computation-Communication Overlap for multi-GPU ML Workloads (arxiv.org)

Titans-as-a-Layer: Test-Time Memory for Conversational Speech Emotion Recognition (arxiv.org)

Physics-Guided Dual Decoding and Spectral Supervision for Global 3D Hydrometeor Prediction (arxiv.org)

Real-time body pose non-verbal communication with a consistency-based reliability measure (arxiv.org)

PhysScene: A Scene Graph Dataset for Scientific Visual Reasoning in Physics Experiments (arxiv.org)

A Theoretical Analysis of Memory and Overfitting Phenomena in Stochastic Interpolation Models (arxiv.org)

Routine laboratory trajectories encode the onset of organ-level complications in cancer (arxiv.org)

Autonomous Aerial Manipulation via Contextual Contrastive Meta Reinforcement Learning (arxiv.org)

A Joint Finite-Sample Certificate for Adaptive Selective Conformal Risk Control (arxiv.org)

Inferring hidden forcing in a biological oscillator using Kolmogorov-Arnold networks (arxiv.org)

Conan-embedding-v3: Fusing Modality-Specific Models for Omni-Modal Embedding (arxiv.org)

Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents (arxiv.org)

Calibration of Structured Ignorance Certificates for Diagnosing Unknown Unknowns in Reasoning Models (arxiv.org)

EinSort: Sorting is All We Need for Tensorizing LLM (arxiv.org)

When Video Misreads: Closed-Loop Distillation of Reading Heuristics for Exploratory Manipulation Trace QA (arxiv.org)

GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation (arxiv.org)

ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policies (arxiv.org)

More Yap Less Meaning: Uncovering Self-Improvement Behavior in SLMs (arxiv.org)

Seeing is Believing: Aligning Prompt Rewriting with Visual Anchors for Text-to-Image Generation (arxiv.org)

Physically Consistent Null Space Alignment for Detection of Low-Magnitude False Data Injection Attacks (arxiv.org)

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior (arxiv.org)

Theoretical Foundations of Continual Learning via Drift-Plus-Penalty (arxiv.org)

How Much Capacity Does EEG Denoising Need? Ultra-Compact Networks reveal Benchmark Saturation and Metric-Utility Gap (arxiv.org)

Few-step Cofolding with All-Atom Flow Maps (arxiv.org)

Projecting the Emerging Mindset of SWE Agent by Launching a Wild Code Understanding Journey (arxiv.org)