arXiv AI
Jul 7
Adaptive Margin RLHF via Preference over Preferences
arXiv:2509. 22851v4 Announce Type: replace-cross Abstract: Margin-based optimization is fundamental to improving generalization and robustness in classification tasks.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jul 7
Attributing Emergence in Million-Agent Systems
arXiv:2605. 11404v2 Announce Type: replace Abstract: Large language models (LLMs) can simulate human-like reasoning and decision-making in individual agents.
arXiv AI
Jul 7
CausalGame: Benchmarking Causal Thinking of LLM Agents in Games
arXiv:2607. 04293v1 Announce Type: cross Abstract: Building AI Scientist agents with Large Language Models (LLMs) has recently attracted growing attention.
arXiv AI
Jul 7
Telescope: Improving Zero Shot Detection of LLM Generated Content By Measuring Token Repetition Probability
arXiv:2607. 04061v1 Announce Type: cross Abstract: Distinguishing Large Language Model (LLM) generated text from human writing is a critical and difficult challenge.
arXiv AI
Jul 7
HaorFloodAlert: A 72-Hour Machine Learning Early Warning System for Flash Floods in Bangladesh's Haor Wetlands
arXiv:2605. 20167v2 Announce Type: replace Abstract: Every spring, flash floods strike the haor wetlands of northeast Bangladesh just before the boro rice harvest, and one flood can erase a family's entire crop in days.
arXiv AI
Jul 7
Internal Pluralism and the Limits of Pairwise Comparisons
arXiv:2607. 02672v1 Announce Type: new Abstract: Local pairwise comparisons are a standard tool for learning how people want decision rules to work, e.
arXiv Machine Learning
Jul 7
Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networks
arXiv:2509. 14026v2 Announce Type: replace-cross Abstract: Variational quantum circuits (VQCs) are central to quantum machine learning, while recent progress in Kolmogorov-Arnold networks (KANs) highlights the power of learnable activation functions.
arXiv AI
Jul 7
When Aggregate Alignment Misleads: Auditing Policy Repair Without Per-State Expert Actions
arXiv:2607. 03386v1 Announce Type: new Abstract: Agentic AI systems are increasingly used to edit, refine, and repair decision policies, but evaluating these edits is difficult when per-state expert action labels are unavailable.
arXiv AI
Jul 7
Decentralized Aggregation of LLM Predictions via Wagering Mechanisms
arXiv:2607. 04389v1 Announce Type: new Abstract: It is increasingly common to aggregate predictions from multiple LLMs, each with domain expertise or access to private tools and data, to improve collective prediction performance.
arXiv AI
Jul 7
Double-Helix Active Geometry: LiDAR-Anchored Multi-View Depth with Selective Abstention
arXiv:2607. 02561v1 Announce Type: cross Abstract: Consumer depth sensors such as the LiDAR scanner on recent iPhones provide metric range, but their useful range is short and their returns are sparse.
arXiv AI
Jul 7
Additive Causal Construction for Transferable and Reconfigurable Cross-System Learning in Multi-Source Image Fusion
arXiv:2607. 02572v1 Announce Type: cross Abstract: In multi-source image fusion scenarios, heterogeneous inputs are typically driven by distinct generative mechanisms and can be viewed as a composition of multiple causal systems.
arXiv AI
Jul 7
The agent creates, we validate: A Lightweight Framework for Agentic Artifact Generation
arXiv:2607. 02615v1 Announce Type: cross Abstract: Generating structured artifacts with Large Language Models - e.
arXiv AI
Jul 7
CRRL: A Causality-Based Reinforcement Learning Framework for Autonomous System Recovery
arXiv:2607. 03177v1 Announce Type: cross Abstract: Traditional reinforcement learning (RL) for recovery in autonomous systems lacks causal understanding and generalizes poorly to novel failure scenarios.
arXiv AI
Jul 7
Agentic and Generative AI for Open-Source Intelligence and Cyber Investigations: Taxonomy, Evaluation, Challenges, and Future Directions
arXiv:2607. 03233v1 Announce Type: cross Abstract: The rapid growth of publicly available digital information has rendered manual open-source intelligence (OSINT) analysis insufficient for modern intelligence, cybersecurity, and cyber investigation.
arXiv AI
Jul 7
SNR-Adaptive Unified Diffusion for Multi-Task Medical Image Segmentation
arXiv:2607. 03103v1 Announce Type: cross Abstract: Clinical cardiac imaging pipelines currently deploy separate models for each dataset and modality, incurring redundant training costs and precluding knowledge sharing across anatomically related tasks.
arXiv AI
Jul 7
Criterion-Conditional In-Context Learning: Evaluating Criterion-Shift Adaptation in Vision-Language Models
arXiv:2607. 02575v1 Announce Type: cross Abstract: Vision-language models can perform new tasks without parameter updates through in-context learning (ICL), whose core mechanism is utilizing the support set for task induction.
arXiv Machine Learning
Jul 7
Towards a more realistic evaluation of machine learning models for bearing fault diagnosis
arXiv:2509. 22267v5 Announce Type: replace Abstract: Reliable detection of bearing faults is essential for maintaining the safety and operational efficiency of rotating machinery.
arXiv AI
Jul 7
Unbiased Alignment for Large Language Models with Noisy Preferences
arXiv:2607. 03248v1 Announce Type: cross Abstract: The alignment of large language models with human preferences is commonly achieved through Reinforcement Learning from Human Feedback or Direct Preference Optimization.
arXiv AI
Jul 7
OpenGlass: A Sensing-Computing Split Architecture for Local MLLM-Driven Real-Time Visual Assistance
arXiv:2607. 03213v1 Announce Type: cross Abstract: We present OpenGlass, an open-source, privacy-oriented, local-first system for low-latency multimodal visual assistance, with a primary focus on blind and low-vision users.
arXiv AI
Jul 7
Efficient Decentralized Multi-task Dataset Valuation via Model Merging
arXiv:2607. 03346v1 Announce Type: cross Abstract: Accurate and efficient dataset valuation is essential for enabling fair and transparent data marketplaces, especially when multiple contributors provide data for training multi-task models.