AI News

Lost in the Flow with Code Talkers: Unveiling the Instruction-Tuning Tax of Large Language Models in Code Tasks (arxiv.org)

Online Learning with Recency: Algorithms for Sliding-window Streaming Multi-armed Bandits (arxiv.org)

BioVid: Autoregressive Video Generation with Biological Behavior Semantic Comprehension (arxiv.org)

TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation (arxiv.org)

The Need for Neural ISP in the Small-Pixel Era: How Shrinking Pixels Push Optics to the Limit and Neural Restoration Pushes Back (arxiv.org)

A Hierarchical Feature Engineering Framework for Automated Classification of Phonotraumatic and Non-Phonotraumatic Vocal Hyperfunction (arxiv.org)

Hardware-aware Low-latency Quantum Compilation with Data-driven Lightweight Error Detection for Early Fault-Tolerant Systems (arxiv.org)

Need We Teach Foundation Models What is a Generative Image? Gradient-Free Generative Artifact Detection via Analytic Spectral Adaptation (arxiv.org)

Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems (arxiv.org)

Latent Diffusion Policy: Shaping Latent Spaces for Diffusion-Based Robotic Manipulation (arxiv.org)

FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuning (arxiv.org)

Reconstructing Synthetic SDO/AIA 193 A EUV Images from He I 10830 A Observations with Diffusion Model Translator (arxiv.org)

What neurosurgeons need to see: synthetic intra-operative MRI from ultrasound for brain-shift compensation in brain tumour surgery (arxiv.org)

QDS-SNN: Energy-efficient Quantum Deeply-Supervised Spiking Neural Network Algorithm for Traffic Sign Recognition (arxiv.org)

SC3: The Multi-Solvent Solubility Challenge and Benchmark (arxiv.org)

Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation (arxiv.org)

SHIELD-IDS: Structurally Heterogeneous Ensemble with Integrated Layered Defense for Intrusion Detection Systems (arxiv.org)

A Unifying Lens on Reward Uncertainty in RLHF (arxiv.org)

OnlyDense: Reduced-Order Modeling for Lagrangian simulation (arxiv.org)

Stage-1 Controls the Entropy Regime, Not the Outcome (arxiv.org)

Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets (arxiv.org)

HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning (arxiv.org)

Auditable Graph-Guided Root Cause Analysis for Kubernetes Incidents (arxiv.org)

RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks (arxiv.org)

From `May' to `Is': Certainty Distortion in Language Model Rewriting (arxiv.org)

POISE: Position-Aware Undetectable Skill Injection on LLM Agents (arxiv.org)

Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation (arxiv.org)

Decoupling Semantics and Logic: A Training-Free Coarse-to-Fine Pipeline for Video Retrieval-Augmented Generation (arxiv.org)

Larch: Learned Query Optimization for Semantic Predicates (arxiv.org)

Decoy-Calibrated Failure Audits for Language Models (arxiv.org)

DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity (arxiv.org)

TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs (arxiv.org)

Structural Grid Descriptors Predict Within-Task Solver Success on ARC-AGI (arxiv.org)

LEAF: A Learning-Enabled ADMM Framework for Accelerated Convex Optimization (arxiv.org)

Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models (arxiv.org)

Transforming Police-Car Swerving for Mitigating Isolated Stop-and-Go Traffic Waves: A Practice-Oriented Jam-Absorption Driving Strategy (arxiv.org)

A Comparative Study of Student Perspectives on Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics (arxiv.org)

DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs (arxiv.org)

How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs (arxiv.org)

One if by Land, Two if by Sea, Three if by Four Seas, and More to Come -- Values of Perception, Prediction, Communication, and Common Sense in Decision Making (arxiv.org)

A large-scale nanocrystal database with aligned synthesis and properties enabling generative inverse design (arxiv.org)

Mitigating Diffusion Model Hallucinations with Dynamic Guidance (arxiv.org)

Quantum feature-map learning with reduced resource overhead (arxiv.org)

Cryptographic Backdoor for Neural Networks: Boon and Bane (arxiv.org)

A Survey on Deep Multi-Task Learning in Connected Autonomous Vehicles (arxiv.org)

Improving User Experience with Personalized Review Ranking and Summarization (arxiv.org)

Vision-Based Early Fault Diagnosis and Self-Recovery for Strawberry Harvesting Robots (arxiv.org)

Exploring the Effect of Basis Rotation on NQS Performance (arxiv.org)

Collaborative Edge-to-Server Inference for Vision-Language Models (arxiv.org)

Unambiguous Representations in Neural Networks: An Information-Theoretic Approach to Intentionality (arxiv.org)