arXiv AI
Jul 28
Moral Hazard in Multi-Agent Language Models
arXiv:2607. 23982v1 Announce Type: cross Abstract: Cooperation can fail when socially valuable effort is costly, weakly observable, and mainly benefits others.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv Machine Learning
Jul 28
Gradient-Free Continual Learning
arXiv:2504. 01219v2 Announce Type: replace Abstract: Neural networks are notorious for forgetting old skills when taught new ones - a problem known as catastrophic forgetting.
arXiv Machine Learning
Jul 28
Covariance-Boosted Gaussian Processes for Spatiotemporal Irregularities
arXiv:2607. 23018v1 Announce Type: cross Abstract: Nonstationary Gaussian process (GP) models are powerful tools for capturing input-dependent variability by adapting to observed data.
arXiv Machine Learning
Jul 28
Continuous surrogates versus threshold Boolean networks for modeling Arabidopsis ISR gene regulation
arXiv:2607. 23289v1 Announce Type: cross Abstract: Gene regulatory network modeling often requires balancing predictive accuracy and mechanistic interpretability.
arXiv AI
Jul 28
Not Forgotten: Implementation and Evaluation of a Personalized Episodic Memory for the Humanoid Robot Head Kim
arXiv:2607. 24190v1 Announce Type: cross Abstract: Social robots that rely on large language models for conversation are unable to retain information across sessions.
arXiv Machine Learning
Jul 28
Trustworthy Medical Segmentation: Uncertainty-Aware U-Net Evaluation Under Clinical Image Degradation
arXiv:2607. 22727v1 Announce Type: cross Abstract: Medical image segmentation models often report high benchmark accuracy under ideal imaging conditions, yet their failures under clinical degradation can be quiet: sensor noise, patient motion, low- resolution acquisition, and contrast variability may all alter model behavior without producing an obvious warning.
arXiv Machine Learning
Jul 28
Diffusion-Guided Search via Exponential Tilting (DiffTilt): An Application to Falsification of Safety-Critical Systems
arXiv:2607. 23134v1 Announce Type: new Abstract: Discovering rare safety-critical failures in autonomous and cyber-physical systems is a fundamental challenge in verification and validation.
arXiv Machine Learning
Jul 28
Visual Token Compression Enhances Robustness of MLLMs
arXiv:2607. 22716v1 Announce Type: cross Abstract: In this paper, we show for the first time that visual token pruning enhances the robustness of Multimodal Large Language Models (MLLMs), mitigating vulnerabilities such as jailbreak attacks and hallucinations.
arXiv Machine Learning
Jul 28
Generalization bounds and sample complexity for remaining useful life prediction from complete degradation trajectories
arXiv:2607. 23454v1 Announce Type: new Abstract: Data-driven remaining useful life (RUL) prediction requires complete degradation trajectories for training, yet such run-to-failure data are scarce and expensive.
arXiv AI
Jul 28
MPR-CiteG: Enhancing RAG with Multi-Portfolio Retrieval and Citation-Grounded Generation
arXiv:2607. 22706v1 Announce Type: new Abstract: This paper presents the MPR-CiteG framework, which achieved second place in the ScienceON AI Challenge by addressing two fundamental challenges in generative AI: inefficient retrieval and the absence of source verification.
arXiv AI
Jul 28
StanceBench: A Benchmark for Audio LLM-Based Interpersonal Stance Evaluation from Speech
arXiv:2607. 22658v1 Announce Type: new Abstract: Speech-to-speech dialogue models increasingly depend on prosody and interactional nuance to convey social intent, yet benchmarks for these cues remain limited.
arXiv Machine Learning
Jul 28
Nearly Tight Bounds for Cross-Learning Contextual Bandits with Graphical Feedback
arXiv:2502. 04678v2 Announce Type: replace Abstract: Repeated first-price auctions are contextual decision problems with censored but reusable feedback: after submitting a bid, a learner can infer the outcomes of related bids and evaluate them under different private values.
arXiv AI
Jul 28
Obliviate: Efficient Unlearning in Recommender Systems
arXiv:2607. 22665v1 Announce Type: new Abstract: Machine unlearning is becoming increasingly critical in the context of data privacy regulations, particularly for recommendation systems that are directly trained on user interaction data.
arXiv AI
Jul 28
Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects
arXiv:2607. 24645v1 Announce Type: cross Abstract: The wide-scale use of sparse autoencoders (SAEs) as interpretability tools is limited by inconsistent links between SAE features and model behavior.
arXiv AI
Jul 28
Online Fair Division with Budget Constraints
arXiv:2607. 23310v1 Announce Type: cross Abstract: We study an online variant of discrete fair division under generalized assignment budget constraints.
arXiv AI
Jul 28
Continual Knowledge Consolidation LORA for Domain Incremental Learning
arXiv:2510. 16077v2 Announce Type: replace-cross Abstract: Domain Incremental Learning (DIL) is a sub-branch of continual learning that aims to address the never-ending arrival of new domains without catastrophic forgetting.
arXiv AI
Jul 28
False Prophets: On the Security of World Models in Agentic Systems
arXiv:2607. 23147v1 Announce Type: cross Abstract: Large language models now power autonomous agents capable of complex, multi-step tasks in different environments.
arXiv AI
Jul 28
Exact and Asymptotically Complete Robust Verifications of Neural Networks via Ising Solvers
arXiv:2603. 00408v2 Announce Type: replace-cross Abstract: We present an Ising-compatible framework for formal neural-network robustness verification under bounded input perturbations.
arXiv AI
Jul 28
From "Help" to Helpful: A Hierarchical Assessment of LLMs in Mental e-Health Applications
arXiv:2602. 18443v2 Announce Type: replace-cross Abstract: Psychosocial online counselling frequently encounters generic subject lines that impede efficient case prioritisation.
arXiv AI
Jul 28
PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics Alignment
arXiv:2508. 05132v3 Announce Type: replace-cross Abstract: As medical LLMs transition to clinical deployment, assessing their ethical reasoning capability becomes critical.