arXiv:2511.13780v1 Announce Type: new Abstract: This paper presents a mathematical interpretation of self-attention by connecting it to distributional semantics principles. We show that self-attention emerges from projecting corpus-level co-occurrence statistics into sequence context. Starting from the co-occurrence matrix underlying GloVe…
arXiv:2511.12511v2 Announce Type: replace-cross Abstract: With growing concerns over image authenticity and digital safety, the field of AI-generated image (AIGI) detection has progressed rapidly. Yet, most AIGI detectors still struggle under real-world degradations, particularly motion blur, which frequently occurs in…
arXiv:2511.13787v1 Announce Type: new Abstract: In this paper, we explore the transferability of SSL by addressing two central questions: (i) what is the representation transferability of SSL, and (ii) how can we effectively model this transferability? Transferability is defined as…
arXiv:2511.14368v1 Announce Type: cross Abstract: While Large Vision Language Models (LVLMs) are increasingly deployed in real-world applications, their ability to interpret abstract visual inputs remains limited. Specifically, they struggle to comprehend hand-drawn sketches, a modality that offers an intuitive means…
arXiv:2511.13788v1 Announce Type: new Abstract: Large language models (LLMs) increasingly operate in multi-agent and safety-critical settings, raising open questions about how their vulnerabilities scale when models interact adversarially. This study examines whether larger models can systematically jailbreak smaller ones –…
arXiv:2511.14545v1 Announce Type: cross Abstract: Structural nested mean models (SNMMs) are a principled approach to estimate the treatment effects over time. A particular strength of SNMMs is to break the joint effect of treatment sequences over time into localized, time-specific…
arXiv:2511.13809v1 Announce Type: new Abstract: Understanding the decision of large deep learning models is a critical challenge for building transparent and trustworthy systems. Although the current post hoc explanation methods offer valuable insights into feature importance, they are inherently disconnected…
arXiv:2511.14651v1 Announce Type: cross Abstract: Recently developed applications in the field of machine learning and computational physics rely on automatic differentiation techniques, that require stable and efficient linear algebra gradient computations. This technical note provides a comprehensive and detailed discussion…
arXiv:2511.13841v1 Announce Type: new Abstract: Reinforcement learning(RL) post-training has become essential for aligning large language models (LLMs), yet its efficiency is increasingly constrained by the rollout phase, where long trajectories are generated token by token. We identify a major bottleneck:the…
The virtual VideoCAD tool could boost designers’ productivity and help train engineers learning computer-aided design.
