Intervention anchors and scientific verification in synthetic vascular predictive representations

Lingsen You et al.

#arXiv #cs.AI

BridgeGuard: Explicit Safety Drift for Diffusion-based Autonomous Driving

Zhenjun Qiu et al.

#arXiv #cs.AI

MedBenchAgent: Towards Systematic Automation of Medical VLM Benchmark Construction

Yulin Fu (Beijing University of Posts and Telecommunications) et al.

#arXiv #cs.AI

Harness Compilation: Which Decisions Should a Small Vision-Language Model Keep?

Minhao Fan et al.

#arXiv #cs.AI #cs.CV

Verification and Self-Improvement in Agentic AI: Foundations and Limits

Chien-Ping Lu

#arXiv #cs.AI #cs.CC

New paper proposes MetaOPD, a bilevel optimization framework that jointly trains a student model and a lightweight token-weighting network for on-policy distillation, removing the need for predefined signal-to-weight mappings in token…

#AI #MachineLearning #ArXiv
https://arxiv.org/abs/2610.11989

OnTrack: Real-Time Monitoring and Intervention in LLM Agent Trajectories via Streaming Structure-Aware Optimal Transport

Babak Barazandeh et al.

#arXiv #cs.AI #cs.CL #cs.CY #cs.LG

Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness

Saisab Sadhu, Shreeyans Arora, Pratinav Seth

#arXiv #cs.AI #cs.CL #cs.CY

One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails

Seyedarmin Azizi, Erfan Baghaei Potraghloo, Massoud Pedram

#arXiv #cs.AI

Instruction-Conditioned Electromagnetic Spectrum Understanding via Budget-Adaptive Signal Tokenization

Lei Zhai et al.

#arXiv #cs.AI #eess.SP

RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing

Ilya Lasy, Nora Yinuo Cai, Kola Ayonrinde

#arXiv #cs.AI #cs.CL #cs.LG

MultiWorldBench: Do Independently Controlled Views Describe One Shared World?

Zhangbo Xu et al.

#arXiv #cs.AI #cs.CV

Internalizer: Portable Context-to-Parameter Mapping for Very Large Language Models

Peter Devine et al.

#arXiv #cs.AI #cs.CL #cs.LG

A 3D Characterization Framework for Intelligent Sequential Decision Making

Sadig Gojayev, Carolina Fortuna

#arXiv #cs.AI

Why machines will still not rule the world

Jobst Landgrebe, Barry Smith

#arXiv #cs.AI

Equal Path Cost, Unequal Output Effects: Understanding Perturbation Propagation in Diffusion Models

Wei Guo et al.

#arXiv #cs.AI

When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization

Yanlong Zhao et al.

#arXiv #cs.AI #cs.LG #stat.ML

When Interfaces Speak: Data-Aware Generative UI Harness for Active Interaction

Xiaolong Li et al.

#arXiv #cs.AI

Learning How to Search for Plans with Exponentially Less Space

Dominik Drexler et al.

#arXiv #cs.AI

Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice

Jan-Peter Franke

#arXiv #cs.AI