AI News

Metamorphic Testing for Clinical ML Models: A Framework Proposal and Pilot Study (arxiv.org)

Uncertainty Modeling for Multi-Objective RTA Interception with Distillation Acceleration (arxiv.org)

Infinite-Precision Autoregressive Modeling for Vector Graphics and Layouts (arxiv.org)

NeurGO: Learning to Generate Elite Candidates for Meta-Black-Box Expensive Optimization (arxiv.org)

Characterizing Arbitrary Lindbladian Dynamics with a Few Pauli Measurements (arxiv.org)

Weighted Low-Rank Matrix Approximation: Acceleration and Applications (arxiv.org)

The Illusion of Secure LLM Code: Closing the Security Gap via Iterative Reprompting (arxiv.org)

BHARATI: Morphology-Aware Tokenizers for Classical Indian Languages with Subword Fertility Analysis (arxiv.org)

MixQuant: Adaptive Mixed-Precision Quantization for Large Language Models (arxiv.org)

Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models (arxiv.org)

IKS-Instruct: A 24,000-Example Multilingual Dataset for Teaching Language Models Indian Knowledge Systems (arxiv.org)

SpecAHD: Localize to Specialize for Automated Heuristic Design in Large-Scale Routing Problems (arxiv.org)

cMoLLM at Scale: Horizontal Scaling Laws for Mixture-of-LLMs (arxiv.org)

CALMRec: Causally Aligned Language Memory for Long-Horizon Recommendation (arxiv.org)

Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification (arxiv.org)

Quantum Safe-Set Bayesian Optimization for Quality Improvement in Fuselage Assembly (arxiv.org)

Multi-Agent Privacy Game in Federated Learning: A Unified Mean-Field View (arxiv.org)

Efficiency Matters in Autonomous Research (arxiv.org)

Reason-Mediated Behavioral Models for Auditing LLM Social Simulators (arxiv.org)

Bit-Accurate FPGA Evaluation of Learned Feature Gating in a Fixed-Point Fourier-Feature Automatic Modulation Classifier (arxiv.org)

PhononBench-MP40: a spectrum-resolved benchmark dataset for phonon stability (arxiv.org)

Online Fair Division with Budget Constraints (arxiv.org)

Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects (arxiv.org)

Verification-Notebook Learning for Source-Aware Multimodal Misinformation Detection (arxiv.org)

Multimodal Semantic-Probabilistic Objectness for Open World Object Detection (arxiv.org)

Queryable Self-Organizing Maps: A Database Abstraction for Topology-Driven Data Exploration (arxiv.org)

Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization (arxiv.org)

FusionML: Prefill, Not Decode - Mechanism and Boundaries of CPU+GPU Co-Execution on Unified-Memory Apple Silicon (arxiv.org)

Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows (arxiv.org)

CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents (arxiv.org)

Practical advantage beyond the quadratic speedup limit with fully-quantum walks (arxiv.org)

VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy (arxiv.org)

Efficient LLM-Generated Shuttling Compilers for Complex Trapped-Ion Architectures (arxiv.org)

Subject-Level Heterogeneity in EEG Motor Imagery Decoding: A Large-Scale Benchmark and Portfolio-Based Reduction of the Search Space (arxiv.org)

E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios (arxiv.org)

MMOE: Modernizing Diffusion Transformers with Efficient Expert Design (arxiv.org)

Benchmarking LLMs for Verilog Design Flows (arxiv.org)

Evaluating RAG for French immigration law: a benchmark and baseline study (arxiv.org)

ObsDriveBench: Benchmarking Multimodal Understanding under Adverse Weather with Observability Awareness (arxiv.org)

Separating Capability from Permission: A Governance Framework for Agentic AI Autonomy Levels (arxiv.org)

Can an Actor-Critic Optimization Framework Improve Analog Design? (arxiv.org)

When Can You Correct Distribution Drift in Temporal Graph Generation? A Sharpening--Drift Tension and an Impossibility for Observation-Based Correction (arxiv.org)

Discrepancy-Rounded Fair Bandits with Static and Time-Varying Exposure Floors (arxiv.org)

ARdena: Scenario-driven control of real-time LLM agents (arxiv.org)

Verbalized Particle Posterior: Bayesian Inference over Natural Language Hypotheses (arxiv.org)

MioFFAn: an Annotation Software for Formula Formalization with LLM Automation Capabilities (arxiv.org)

Beyond Error-vs-Discard Characteristic: Toward Stable and Reliable Evaluation for Face Image Quality Assessment (arxiv.org)

How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift (arxiv.org)

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis (arxiv.org)

Hallucination Rates in Language Generation (arxiv.org)