Test-time Verification via Optimal Transport: Coverage, ROC, & Sub-optimality
arXiv:2510.18982v1 Announce Type: new Abstract: While test-time scaling with verification has shown promise in improving the performance of large language…
C-SEO Bench: Does Conversational SEO Work?
arXiv:2506.11097v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are transforming search engines into Conversational Search Engines (CSE). Consequently, Search…
Learning from N-Tuple Data with M Positive Instances: Unbiased Risk Estimation and Theoretical Guarantees
arXiv:2510.18406v1 Announce Type: cross Abstract: Weakly supervised learning often operates with coarse aggregate signals rather than instance labels. We study…
When Intelligence Fails: An Empirical Study on Why LLMs Struggle with Password Cracking
arXiv:2510.17884v1 Announce Type: cross Abstract: The remarkable capabilities of Large Language Models (LLMs) in natural language understanding and generation have…
The Sherpa.ai Blind Vertical Federated Learning Paradigm to Minimize the Number of Communications
arXiv:2510.17901v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative decentralized training across multiple parties (nodes) while keeping raw data…
RAISE: A Unified Framework for Responsible AI Scoring and Evaluation
arXiv:2510.18559v1 Announce Type: cross Abstract: As AI systems enter high-stakes domains, evaluation must extend beyond predictive accuracy to include explainability,…
Does Capital Dream of Artificial Labour?
arXiv:2510.16042v1 Announce Type: cross Abstract: This paper investigates the concept of Labour as an expression of `timenergy’ – a fusion…
Curiosity-driven RL for symbolic equation solving
arXiv:2510.17022v1 Announce Type: cross Abstract: We explore if RL can be useful for symbolic mathematics. Previous work showed contrastive learning…
VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models
arXiv:2508.12081v2 Announce Type: replace-cross Abstract: This paper introduces VimoRAG, a novel video-based retrieval-augmented motion generation framework for motion large language…
Online automatic code generation for robot swarms: LLMs and self-organizing hierarchy
arXiv:2510.04774v2 Announce Type: replace-cross Abstract: Our recently introduced self-organizing nervous system (SoNS) provides robot swarms with 1) ease of behavior…