AI News

Sample-Size Scaling of the African Languages NLI Evaluation (arxiv.org)

Trans GAN-WT: A Feature Extraction and Interactive Learning-Based Anomaly Detection Model for Wind Turbine Time Series Data (arxiv.org)

Easy-to-Use Shielding for Reinforcement Learning (arxiv.org)

Learning Temporal Causal Structure via Smooth Differentiable Optimization (arxiv.org)

AI Model Extraction Attacks: Bypassing Single-Client Assumptions in Defenses (arxiv.org)

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation (arxiv.org)

A Single-Loop Bilevel Deep Learning Method for Optimal Control of Obstacle Problems (arxiv.org)

The Unsampled Truth: Psychometrics in SLMs Measure Prompt Artifacts, Not Psychological Constructs (arxiv.org)

Dynamic Short Convolutions Improve Transformers (arxiv.org)

Rethinking Neural Width for Alternating Current Optimal Power Flow Proxies (arxiv.org)

Assessing and Mitigating Miscalibration in LLM-Based Social Science Measurement (arxiv.org)

Pretraining Language Models on Historical Text (arxiv.org)

Typhoon: Towards an Effective Task-Specific Masking Strategy for Pre-trained Language Models (arxiv.org)

PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization (arxiv.org)

Contrastive Neural Algorithmic Reasoning for Graph Coloring (arxiv.org)

FFR: Forward-Forward Learning for Regression (arxiv.org)

A Factorized Low-Rank RNN Framework for Uncovering Independent Neural Latent Dynamics and Connectivity (arxiv.org)

Suboptimality bounds for trace-bounded SDPs enable a faster and scalable low-rank SDP solver SDPLR+ (arxiv.org)

Glass Box at Orbit: A Constitutional AI Verification Framework for Trustworthy Autonomous CubeSat Intelligence (arxiv.org)

Discovering autonomous quantum error correction via deep reinforcement learning (arxiv.org)

MAdam: Metric-Aware Multi-Objective Adam (arxiv.org)

Speech Emotion Recognition using Attention-based LSTM-Network with Residual Connection (arxiv.org)

Patcher: Post-Hoc Patching of Backdoored Large Language Models (arxiv.org)

Towards Blind Lens Aberration Correction via Large LensLib Pre-training and Discrete Degradation Priors (arxiv.org)

AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse (arxiv.org)

SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation (arxiv.org)

Echelon: Auditable Aggregate-Only Language-Model Adaptation Across Privacy Boundaries (arxiv.org)

Leveraging BART to Assess CS1 C++ Programming Assignments using Rubric-based Criteria (arxiv.org)

Enhanced Renewable Energy Forecasting using Context-Aware Conformal Prediction (arxiv.org)

High-Precision APT Malware Attribution with Out-of-Scope Resilience (arxiv.org)

WRIT: Write-Read Intensive Trajectory Synthesis for Multi-Turn User-Facing Agents (arxiv.org)

Calibrating Urban Traffic Simulation from Sparse Road Observations via Genetic Optimization (arxiv.org)

Text-attributed Graph Condensation via Text Selection and Attribute Matching (arxiv.org)

FORGE: Multi-Agent Graduated Exploitation and Detection Engineering (arxiv.org)

Strongly Polynomial Time Complexity of Policy Iteration for $L_\infty$ Robust MDPs (arxiv.org)

BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents (arxiv.org)

WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation (arxiv.org)

Testing LLM Arithmetic Reasoning Generalization with Automatic Numeric-Remapping Attacks (arxiv.org)

SCOPE: Real-Time Natural Language Camera Agent at the Edge (arxiv.org)

Re-Evaluating Continual Learning with Few-Shot Adaptation (arxiv.org)

A Hybrid Approach For Malware Classification Using Secondary Features Fusion (arxiv.org)

Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression (arxiv.org)

P\textsuperscript{2}-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization (arxiv.org)

Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference (arxiv.org)

PURGE: Projected Unlearning via Retain-Guided Erasure (arxiv.org)

Auditing Engagement Incentives in the Kidfluencer Ecosystem: A Multimodal Weak Supervision Approach (arxiv.org)

A Scoping Review of the Ethical Perspectives on Anthropomorphising Large Language Model-Based Conversational Agents (arxiv.org)

q0: Primitives for Hyper-Epoch Pretraining (arxiv.org)

Signed Spiking Neuron Enabled by an Orthogonal-Easy-Axis Magnetic Tunnel Junction (arxiv.org)

NeuroArmor: Safe-Variant-Guided Representation Consistency for Selective Re-Anchoring in Jailbreak Defense (arxiv.org)