arXiv:2603.23315v1 Announce Type: cross Abstract: When providers update AI companions, users report grief, betrayal, and loss. A growing literature asks whether the norms governing personal relationships extend to these interactions. So what, if anything, is morally significant about them? I argue that human-AI companion interaction is a triadic structure in which the provider exercises constitutive […]
Robust Safety Monitoring of Language Models via Activation Watermarking
arXiv:2603.23171v1 Announce Type: cross Abstract: Large language models (LLMs) can be misused to reveal sensitive information, such as weapon-making instructions or writing malware. LLM providers rely on $emphmonitoring$ to detect and flag unsafe behavior during inference. An open security challenge is $emphadaptive$ adversaries who craft attacks that simultaneously (i) evade detection while (ii) eliciting unsafe […]
Planning over MAPF Agent Dependencies via Multi-Dependency PIBT
arXiv:2603.23405v1 Announce Type: cross Abstract: Modern Multi-Agent Path Finding (MAPF) algorithms must plan for hundreds to thousands of agents in congested environments within a second, requiring highly efficient algorithms. Priority Inheritance with Backtracking (PIBT) is a popular algorithm capable of effectively planning in such situations. However, PIBT is constrained by its rule-based planning procedure and […]
Leveraging LLMs and Social Media to Understand User Perception of Smartphone-Based Earthquake Early Warnings
arXiv:2603.23322v1 Announce Type: cross Abstract: Android’s Earthquake Alert (AEA) system provided timely early warnings to millions during the Mw 6.2 Marmara Ereglisi, T”urkiye earthquake on April 23, 2025. This event, the largest in the region in 25 years, served as a critical real-world test for smartphone-based Earthquake Early Warning (EEW) systems. The AEA system successfully […]
Thickness effects in the electromechanical stability of charged biological membranes
arXiv:2603.23477v1 Announce Type: cross Abstract: Understanding how electric fields destabilize biological membranes is important for electroporation-based technologies and bioelectronic interfaces. However, theoretical descriptions of this phenomenon remain fragmented. Existing theories treat either electrostatics in membranes of finite thickness or electrohydrodynamic flows at idealized zero-thickness interfaces, leaving unresolved a unified description that simultaneously incorporates finite membrane […]
SARE: Sample-wise Adaptive Reasoning for Training-free Fine-grained Visual Recognition
arXiv:2603.17729v2 Announce Type: replace-cross Abstract: Recent advances in Large Vision-Language Models (LVLMs) have enabled training-free Fine-Grained Visual Recognition (FGVR). However, effectively exploiting LVLMs for FGVR remains challenging due to the inherent visual ambiguity of subordinate-level categories. Existing methods predominantly adopt either retrieval-oriented or reasoning-oriented paradigms to tackle this challenge, but both are constrained by two […]
RealCQA-V2: A Diagnostic Benchmark for Structured Visual Entailment over Scientific Charts
arXiv:2410.22492v3 Announce Type: replace Abstract: Multimodal reasoning models often produce fluent answers supported by seemingly coherent rationales. Existing benchmarks evaluate only final-answer correctness. They do not support atomic visual entailment verification of intermediate steps, especially visual compositional logic. This limitation is especially acute in scientific chart understanding, where answers depend on deterministically grounded visual semantics […]
Can Graph Foundation Models Generalize Over Architecture?
arXiv:2603.22984v1 Announce Type: cross Abstract: Graph foundation models (GFMs) have recently attracted interest due to the promise of graph neural network (GNN) architectures that generalize zero-shot across graphs of arbitrary scales, feature dimensions, and domains. While existing work has demonstrated this ability empirically across diverse real-world benchmarks, these tasks share a crucial hidden limitation: they […]
Hybrid Stackelberg Game and Diffusion-based Auction for Two-tier Agentic AI Task Offloading in Internet of Agents
arXiv:2511.22076v2 Announce Type: replace Abstract: The Internet of Agents (IoA) is rapidly gaining prominence as a foundational architecture for interconnected intelligent systems, designed to facilitate seamless discovery, communication, and collaborative reasoning among a vast network of Artificial Intelligence (AI) agents. Powered by Large Language and Vision-Language Models, IoA enables the development of interactive, rational agents […]
Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs
arXiv:2603.22446v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvements remain unclear. We present a systematic empirical study of RLVR’s distributional effects organized around three main analyses: (1) token-level characterization of distributional shifts between base and RL models, […]
Early Discoveries of Algorithmist I: Promise of Provable Algorithm Synthesis at Scale
arXiv:2603.22363v1 Announce Type: cross Abstract: Designing algorithms with provable guarantees that also work well in practice remains difficult, requiring both mathematical reasoning and careful implementation. Existing approaches that bridge worst-case theory and empirical performance, such as beyond-worst-case analysis and data-driven algorithm selection, typically assume prior distributional knowledge or restrict attention to a fixed pool of […]
Three Creates All: You Only Sample 3 Steps
arXiv:2603.22375v1 Announce Type: cross Abstract: Diffusion models deliver high-fidelity generation but remain slow at inference time due to many sequential network evaluations. We find that standard timestep conditioning becomes a key bottleneck for few-step sampling. Motivated by layer-dependent denoising dynamics, we propose Multi-layer Time Embedding Optimization (MTEO), which freeze the pretrained diffusion backbone and distill […]