AI News

A Systematic Study of Small Language Models on Abstract Reasoning Tasks (arxiv.org)

REViT-v2: Hierarchical Windowed Roto-reflection Equivariant ViT for Equivariant Feature Extraction (arxiv.org)

CETUS: How Far Do Representations Trained on Earth Transfer to Cassini SAR of Titan? (arxiv.org)

Two Vectors Replace In-Context Demos: Structured Task Adaptation via Embeddings (arxiv.org)

MobileVISTA: Generative Data Augmentation for Pose Generalization in Mobile Manipulation (arxiv.org)

Deep Defence on Wheels: A Dual Intrusion Detection System Architecture for Comprehensive In-Vehicle Network Security (arxiv.org)

RA-MoWE: Workflow-Affinity Embeddings for Query Clustering and Agentic Workflow Generation (arxiv.org)

Seeing the Invisible: Physics-Guided Visual Prompting for Temperature- and Radiation-Aware VLA Navigation (arxiv.org)

OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception (arxiv.org)

EnGRICH: Enhancing Generative Reward Modeling with Critiques from Humans (arxiv.org)

When Agent Context Goes Stale: Incoherence in Volatile Agent Context (arxiv.org)

A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies (arxiv.org)

SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models (arxiv.org)

Artifact removal improves electrodermal waveforms but not downstream classification in a virtual-reality balance task (arxiv.org)

SkillFormer: Skill-Decomposed Adaptation for Audio Language Models (arxiv.org)

AccentCL: Robust Accent Classification with Incremental Expansion (arxiv.org)

Identity-Conditioned Score Fusion for Open-Set Person Re-Identification (arxiv.org)

Evaluating Behavioral Context for Interpretable IAM Policy Risk Scoring in Cloud Environments (arxiv.org)

Agentic AI with Structured CoT for Enhancing AI's Spatial Intelligence: Visualization and Reasoning of Rotation (arxiv.org)

SpikeMoE: Brain-Inspired Competitive Routing for Flexible Spiking Mixture-of-Experts (arxiv.org)

Recurrent Looped Transformer (arxiv.org)

Modeling Latent Disturbances for Robust Decision-Making in World Models (arxiv.org)

ReSolve: Reusing Candidate Reasoning through Selective Generative Moderation (arxiv.org)

Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions (arxiv.org)

Probabilistic Counterfactual Inference for Discrete Outcomes in Gaussian-Process Causal Models (arxiv.org)

Advantage of Entangled Learning Rules in Quantum Measurement Class Learning (arxiv.org)

A Single-Loop, Constant-Batch First-Order Penalty Method for Stochastic Bilevel Optimization (arxiv.org)

What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization (arxiv.org)

Hybrid Cross-Modal Attention Network for Early Breast Cancer Detection in Low-Resource Clinical Settings (arxiv.org)

Rethinking Knowledge Retrieval for Generation: A Survey on RAG Architectures and Applications (arxiv.org)

JudgeProfile: Understanding and Steering Subjectivity in LLM Judges (arxiv.org)

A Validated Dataset and Benchmark for Coherent Multi-Diagram SysML Models (arxiv.org)

Anchor and Adapt: Asymmetric Prompt Adaptation for Few-Shot Industrial Anomaly Detection (arxiv.org)

An overview of machine learning-enhanced iterative methods for systems of linear and nonlinear equations (arxiv.org)

GeneICL: A Tabular Foundation Model for Bulk Transcriptomics (arxiv.org)

Optimal and Efficient Online Inverse Optimization (arxiv.org)

On the Computational Tractability of Robust Bandits (arxiv.org)

Learning Disentangled Representations with Quantum Variational Autoencoders (arxiv.org)

Interleaved Projected Gradient Descent for Safe Imitation Learning (arxiv.org)

Evaluating Inference Compute for Generative AI: A Framework for Enterprise Workloads (arxiv.org)

Dynamical low-rank equilibrium computation for stochastic games between advanced persistent threats and moving target defense (arxiv.org)

Linear Bandits under Exact Sliding-Window Constraints (arxiv.org)

Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness (arxiv.org)

MINDSET: Energy-based Schema Evolution for Long Conversational Agent Memory (arxiv.org)

Adaptive Power Sampling for LLM Reasoning (arxiv.org)

How Much Evidence Should a Coding Agent's Self-Correction Carry? Adaptive Dirichlet Evidence for Self-Distillation (arxiv.org)

Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation (arxiv.org)

AssemState: Manual and Physical-State-Guided Reasoning for Zero-shot Furniture Assembly (arxiv.org)

APEX: Active Protection at Execution Boundaries for LLM Agents (arxiv.org)

On Color Alignment in VAE Latent Spaces and Its Applications (arxiv.org)