AI News

Are Prompt Optimizers Blind? Cross-Modal Visual Feedback for Automatic Prompt Optimization (arxiv.org)

Procedural Content Generation via Generative Artificial Intelligence (arxiv.org)

Robustness and Cybersecurity in the EU Artificial Intelligence Act (arxiv.org)

Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting (arxiv.org)

Obliviate: Efficient Unlearning in Recommender Systems (arxiv.org)

Anticipatory Risk-Guided Reinforcement Learning for Safe Flight Through Dynamic Clutter (arxiv.org)

Asymmetric Hierarchical Anchoring for Robust Audio-Visual Cross-Modal Generalization (arxiv.org)

DSTFView: Multi-View Cloud-Edge Workload Forecasting with Dual-Input Spatio-Temporal-Frequency Modeling (arxiv.org)

Hallucination Rates in Language Generation (arxiv.org)

DualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Field Theory (arxiv.org)

ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding (arxiv.org)

The Visual Bottleneck: Sparse-Frame Adaptation of MLLMs for Joint Spatial-Temporal Video Grounding (arxiv.org)

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

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

Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers (arxiv.org)

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

Learning switched non-linear dynamical systems from a single trajectory (arxiv.org)

Exact Evaluation of the Accuracy of Diffusion Models for Inverse Problems with Gaussian Data Distributions (arxiv.org)

Simulating Tenant Responses to Energy Policy Interventions with Transaction-Cost-Aware LLM Age (arxiv.org)

SIREN: Towards End-to-End Extreme-Weather Early Warning with Experience-Grounded LLM Agents (arxiv.org)

In-Context Learning as Implicit Policy Gradient (arxiv.org)

ParasGB: A Graph Benchmark Suite for Parasitic Estimation on AMS Circuits (arxiv.org)

What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features (arxiv.org)

Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining (arxiv.org)

False Prophets: On the Security of World Models in Agentic Systems (arxiv.org)

PRESTO: Prefix-Aligned Tree Drafting for Diffusion Speculative Decoding (arxiv.org)

STAIF: A Stage-wise Optimization for Complex Instruction Following (arxiv.org)

Bayesian Complete-Pooling in Cross-Subject Classification for Motor Imagery Electroencephalogram (arxiv.org)

CHS-SQL: A Text-to-SQL approach based on Confidence-Guided Heuristic Search Schema Linking process (arxiv.org)

LEDOM: Reverse Language Model (arxiv.org)

Fashion-3DLR: A Controllable 3D Garment Generation Using Pairwise Fashion Elements for Intelligent Design (arxiv.org)

EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability (arxiv.org)

EventOD: Event-Aware OD Flow Generation via LLM-Guided Semantic Modulation (arxiv.org)

A Cyclic Adaptation-Generalization Framework with Uncertainty-Guided Self-Paced Learning for Long-Term Brain-Machine Interfaces (arxiv.org)

A Simple, Optimal and Efficient Algorithm for Online Exp-Concave Optimization (arxiv.org)

DeepLook: Deeper Thinking with Lookahead (arxiv.org)

CC-AOS: Cost- and Horizon-Conditioned Amortized Backward Induction for Finite-Horizon Optimal Stopping (arxiv.org)

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

Exploring Budgeted Image Classification with Content-Sensitive Resource Allocation (arxiv.org)

Capacity-Aware Deep Learning for Generalizable Traffic Volume Estimation Across Links and Cities (arxiv.org)

Creative Integration: A Decidable Criterion of Creativity (arxiv.org)

LLM-based Source Code Compression via Thresholded Symbol Ranking (arxiv.org)

Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement (arxiv.org)

GOTS: Greedy Orthogonal Token Selection for High-Resolution Vision-Language Models (arxiv.org)

Masked Distillation: Internalizing the Chain-of-Thought in Language Models (arxiv.org)

Cortex: Compact Behavior Cloning for Quake with Frozen Visual Features (arxiv.org)

Plato-Bio: verification-first biological novelty screening with temporal rediscovery and structural benchmarks (arxiv.org)

AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Use (arxiv.org)

CAPT: A Multi-task Continuous Autoregressive Transformer enabling Cross-dataset and Cross-species Transfer for Calcium Population Dynamics (arxiv.org)

When Low CER is Not Enough: An Analysis of Hallucinations in Vision-Language OCR Systems on Historical Uruguayan Documents (arxiv.org)