AI News

READER: Robust Evidence-based Authorship Decoding via Extracted Representations (arxiv.org)

More Human or More AI? Visualizing Human-AI Collaboration Disclosures in Journalistic News Production (arxiv.org)

Accelerating NeurASP with vectorization and caching (arxiv.org)

$\tau$-Rec: A Verifiable Benchmark for Agentic Recommender Systems (arxiv.org)

AutoPDE: Reliable Agentic PDE Solving via Explicitly Represented Solver Strategies (arxiv.org)

The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment (arxiv.org)

When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models (arxiv.org)

Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents (arxiv.org)

LMT: A Bayesian Framework for Causal Discovery from Textual Alarm Records in Manufacturing Systems (arxiv.org)

Optuna Constrained Tree-Structured Parzen Estimator Is a Joint Density Generalization of c-TPE (arxiv.org)

SinkRec: Mitigating Semantic State Sink in Long Sequence Recommendation with Memory-Conditioned Gated Delta Networks (arxiv.org)

Toward Calibrated, Fair, and accurate Deepfake Detection (arxiv.org)

Hyperparameter Learning for Latent Factorization of Tensors for Representation Learning to Large-scale Dynamic Weighted Directed Network (arxiv.org)

One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA (arxiv.org)

ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning (arxiv.org)

HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning (arxiv.org)

Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algorithm (arxiv.org)

A complementary study on PlanGPT: Evaluation with defined Performance Metrics and comparison with a planner (arxiv.org)

FailureScope: Cross-Regime Behavioral Diagnosis of Language Model Weaknesses (arxiv.org)

Streaming Knowledge Compilation: Proactive Materiality-Scored Pinning for Time-Evolving LLM Wikis (arxiv.org)

Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs (arxiv.org)

Rotate2Think: Geometric Priming via Orthogonal Rotation to Improve Language Model Reasoning (arxiv.org)

PatchSTG: Scalable Spatiotemporal Graph Transformers for Traffic Forecasting on Irregular Sensor Networks (arxiv.org)

Blind denoising diffusion models and the blessings of dimensionality (arxiv.org)

Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access (arxiv.org)

Infinity-norm-based Input-to-State-Stable Long Short-Term Memory networks: a thermal systems perspective (arxiv.org)

Mixtures of Neural Operators Reduce Active Complexity in Operator Learning (arxiv.org)

Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss (arxiv.org)

Time series forecasting from partial observations via Non-negative Matrix Factorization (arxiv.org)

MAD: Manifold Attracted Diffusion (arxiv.org)

Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization (arxiv.org)

Latent Guided Sampling for Combinatorial Optimization (arxiv.org)

An $(\epsilon,\delta)$-accurate level set estimation with a stopping criterion (arxiv.org)

Interpretable deep convolutional model for nonlinear multivariate time series in complex systems (arxiv.org)

Data assimilation for subsurface flow using latent diffusion model parameterization: performance of ensemble-Kalman and Monte Carlo techniques (arxiv.org)

Conformal Prediction for Dyadic Regression Under Complex Missingness (arxiv.org)

Data-Driven Dynamic Assortment in Online Platforms: Learning about Two Sides (arxiv.org)

Flexible Kernels for Protein Property Prediction (arxiv.org)

Express Language Modeling (arxiv.org)

Conservation Laws from Data Symmetry in Neural Networks (arxiv.org)

SPACR: Single-Pass Adaptive Training of Uncertainty-Aware Conformal Regressors (arxiv.org)

Deterministic Denominator Design for Localized Tamed Stochastic-Gradient Langevin Dynamics (arxiv.org)

Limitations of Learning Tanh Neural Networks with Finite Precision (arxiv.org)

Robust Active Learning for Few-Shot Example Selection in Text-to-SQL (arxiv.org)

Mechanistic Analysis of Alignment Algorithms in Language Models (arxiv.org)

AuRA: Internalizing Audio Understanding into LLMs as LoRA (arxiv.org)

Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models (arxiv.org)

Data-Driven Runway and Taxiway Exits Prediction of Landing Aircraft: A Case Study at Hartsfield-Jackson Atlanta International Airport (arxiv.org)

Learning Doubly Sparse Explicitly Conditioned Transforms (arxiv.org)

Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning (arxiv.org)