AI News

Rarity-Gated Context Conditioning for Offline Imitation Learning-Based Maritime Anomaly Detection (arxiv.org)

Mining Architectural Quality Under Agentic AI Adoption: A Causal Study of Java Repositories (arxiv.org)

HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers (arxiv.org)

Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality (arxiv.org)

Different Layers, Different Manifolds: Module-Wise Weight-Space Geometry in Transformer Optimization (arxiv.org)

Humor Style Drives Laughter, Topic Shapes Acceptability: Evaluating Bilingual Personal and Political Robot-Delivered AI Jokes (arxiv.org)

Towards Personalized Federated Learning for Dysarthric Speech Recognition (arxiv.org)

ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm (arxiv.org)

Once-for-All: Scalable Simultaneous Forecasting via Equilibrium State Estimation (arxiv.org)

Decoding Insect Song: A Multitask Semisupervised Orthoptera Bioacoustic Classifier (arxiv.org)

ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling (arxiv.org)

Proprioceptive-visual correspondence enables self-other distinction in humanoid robots (arxiv.org)

Transformer-Guided Graph Attention for Direct Cardiac Mesh Reconstruction: A Structural Digital Twin Framework (arxiv.org)

Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models (arxiv.org)

Modern analog computing for solving differential and matrix equations (arxiv.org)

MemRefine: LLM-Guided Compression for Long-Term Agent Memory (arxiv.org)

NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning (arxiv.org)

Iterative Visual Thinking: Teaching Vision-Language Models Spatial Self-Correction through Visual Feedback (arxiv.org)

Cascade Classification of Dermoscopic Images of Skin Neoplasms with Controllable Sensitivity and External Clinical Validation (arxiv.org)

MiniPIC: Flexible Position-Independent Caching in <100LOC (arxiv.org)

Select and Improve: Understanding the Mechanics of Post-Training for Reasoning (arxiv.org)

NaturalFlow: Reducing Disruptive Pauses for Natural Speech Flow in Simultaneous Speech-to-Speech Translation (arxiv.org)

MP3: Multi-Period Pattern Pre-training forSpatio-Temporal Forecasting (arxiv.org)

Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents (arxiv.org)

Emotional regulation improves deep learning-based image classification (arxiv.org)

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems (arxiv.org)

"Is This Not Enough?": Asymmetries in Institutional Accountability and Collective Sensemaking in the Case of Canada's Algorithmic Visa Triage System (arxiv.org)

TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization (arxiv.org)

EA-WM: Event-Aware World Models with Task-Specification Grounding for Long-Horizon Manipulation (arxiv.org)

Fault Lines: Navigating Ethics and Responsible AI Where National Policy Meets Local Practice in Public Sector Transformation (arxiv.org)

TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment (arxiv.org)

SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models (arxiv.org)

Democracy in the Era of Artificial Intelligence (arxiv.org)

CausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts (arxiv.org)

scLLM-DSC: LLM-Knowledge Enhanced Cross-Modal Deep Structural Clustering for Single-Cell RNA Sequencing (arxiv.org)

A Machine Learning Framework for Real-Time Personalized Ergonomic Pose Analysis (arxiv.org)

Efficient, Robust, and Anti-Collusion Fingerprinting of Image Diffusion Models (arxiv.org)

An Embodied Simulation Platform, Benchmark, and Data-Efficient Augmentation Framework for Wet-Lab Robotics (arxiv.org)

Order Is Not Control (arxiv.org)

LoRA-Muon: Spectral Steepest Descent on the Low-Rank Manifold (arxiv.org)

MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems (arxiv.org)

G-Long: Graph-Enhanced Memory Management for Efficient Long-Term Dialogue Agents (arxiv.org)

Bounding Boxes as Goals: Language-Conditioned Grasping via Neuro-Symbolic Planning (arxiv.org)

PolicyGuard: Towards Test-time and Step-level Adversary Defense for Reinforcement Learning Agent (arxiv.org)

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement (arxiv.org)

Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming (arxiv.org)

Diffusion Transformer World-Action Model for AV Scene Prediction (arxiv.org)

JSCGC: Joint Source-Channel-Generation Coding for Wireless Generative Communications (arxiv.org)

TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models (arxiv.org)

OCOO-T : A Simple and Scalable Virtual Cell Model for Transcriptional Perturbation Response Prediction (arxiv.org)