AI News

Accelerating Transfer-Learning-Based Autotuning with Predictive LLVM IR Performance Ranking (arxiv.org)

Delegating Authorization to Misaligned Agents: Coalitional Alignment and Safe Control (arxiv.org)

Projection-Free Multi-level Algorithms for Stochastic Constrained Compositional Optimization (arxiv.org)

Circuit-MLLM: Topological Logic-Guided Latent-Space Visual Reasoning for Circuit Schematic Understanding (arxiv.org)

Through the Eyes of the Beholder: Biometric and Demographic Conditioning for Multimodal Sexism Detection (arxiv.org)

Convergence Analysis of Sequential Federated Learning on Heterogeneous Data (arxiv.org)

A Game-Theoretic Framework for Incentive-Compatible AI training Under Renewable-Energy Constraints (arxiv.org)

Artificial entrepreneurial cognition: Locating and causally steering an opportunity recognition dial inside large language models (LLMs) (arxiv.org)

Improving the Last-Iterate Guarantees of Anytime Algorithms for Stochastic Monotone Variational Inequalities (arxiv.org)

S3-Tracker: Self-Supervised Surgical Tissue Tracking With Contrastive Random Walks (arxiv.org)

HQARRF: Hierarchical Q-learning and Force-aware Routing for Multi-Charger Scheduling in Wireless Rechargeable Sensor Networks (arxiv.org)

CyclOT: Learning Quadratic Optimal Transport Maps via Synchronized Forward-Backward Interpolants (arxiv.org)

Generation of Custom Solvers in Rust for Convex Optimization (arxiv.org)

Physically Typed and Geometry-Aware Representations for Earth Foundation Models (arxiv.org)

From Network Inequality to Network Fairness: A Perspective on Responsible Decision-Making (arxiv.org)

Parameter Estimation of Ringdown Quasinormal Modes with Autoencoder (arxiv.org)

VGFM: Expressive Robot Policies via Dense Value Guidance in Flow Matching (arxiv.org)

Towards Anticipatory Databases Through Shared Data and Workload Semantics (arxiv.org)

What Input Resolution Is Required for Bird Species Identification, and What Is Its Latency Cost on an Edge Device? A Study of 14 Input Resolutions and Six Architectures with On-Device Measurements (arxiv.org)

Joint Optimization for Federated Learning and Transmission over Unreliable Wireless Networks with Heterogeneous Data (arxiv.org)

AI Assisted Workflow Optimization and Automation (arxiv.org)

Partition-Aware Scheduling for Mobile Heterogeneous Inference Co-Execution (arxiv.org)

3D Gait-Based Autism Classification Using Attention-Enhanced Deep Learning with Cross-Fold Statistical Stability Analysis (arxiv.org)

When Faster VLA Deployment Changes Closed-Loop Behavior: Task Success-Latency Analysis of SmolVLA Across PyTorch and ONNX Variants (arxiv.org)

Not All Duplicates Are Coordination: Generic vs. Non-Generic Duplicate Campaigns in Information Operations (arxiv.org)

EI-DDLGN: Efficient Encrypted Inference with Deep Differentiable Logic Gate Networks under TFHE (arxiv.org)

BOOST: Concurrent Access to Host Memory and HBM to Accelerate LLM Inference (arxiv.org)

Mirror, Mirror on the Wall: Prompt Echoing in Small Instruct Language Models (arxiv.org)

Syn2Logic: End-to-End Neuromorphic Design Automation (arxiv.org)

A Few Pages of Markdown: Committed AI Configuration and Lower Quality Cost after Coding-Agent Adoption (arxiv.org)

IWC-Bench: Evaluating Web Application Generation from a Software Testing Perspective (arxiv.org)

Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs (arxiv.org)

End-to-End Cell Detection via Instance-aware Graph Modeling (arxiv.org)

Dynamic Semantic Compression for Efficient Latent-Space Inference in Large Language Models (arxiv.org)

Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation (arxiv.org)

Planning in the Backbone: DiffAdapterVLA for Native Continuous Trajectory Generation with Driving VLMs (arxiv.org)

Math for AI safety: an invitation for mathematicians (arxiv.org)

Pre-PEFT Probing: Weight Statistics and Perturbation Robustness for Layer Selection in VLM Vision Encoders (arxiv.org)

Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception (arxiv.org)

Failure-Guided Co-Evolution of Prompts and Training Data (arxiv.org)

TEAR: Table Extraction with Attribute Recommendation from Texts via Large Language Models (arxiv.org)

Interpreting hierarchical organisation of speaker embeddings (arxiv.org)

EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse (arxiv.org)

PACE: Progressive Angular-to-Norm Contrastive Embedding (arxiv.org)

AdaVSkip: Adaptive Visual Token Skipping Across Layers For Efficient MLLMs Inference (arxiv.org)

MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup (arxiv.org)

DepthBenchCAD: When Does Deeper Auditing Yield More Reliable Conclusions? (arxiv.org)

Legislating World-Model-Based Planning with Legal Reasoning (arxiv.org)

Physics Informed Neural Network model for the dynamical study of Abdominal Aortic Aneurysm (arxiv.org)

ChatGPT Images 2.5 in the Wild: A Launch-Period Dataset and Detector Evaluation (arxiv.org)