Tootfinder

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
Tomek Korbak, Mikita Balesni, Elizabeth Barnes, Yoshua Bengio, Joe Benton, Joseph Bloom, Mark Chen, Alan Cooney, Allan Dafoe, Anca Dragan, Scott Emmons, Owain Evans, David Farhi, Ryan Greenblatt, Dan Hendrycks, Marius Hobbhahn, Evan Hubinger, Geoffrey Irving, Erik Jenner, Daniel Kokotajlo, Victoria Krakovna, Shane Legg, David Lindner, David Luan, Aleksander M\k{a}dry, Julian Michael, Neel Nanda, Dave Orr, Jaku…

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known AI oversight methods, CoT monitoring is imperfect and allows some misbehavior to go unnoticed. Nevertheless, it shows promise and we recommend further research into CoT monitorability and investment in CoT monitoring alongside existing safety methods. Because CoT monitorability may be fragile, we recommend that frontie…

Been volunteering with @… and @… since January.
We are in the Toronto Star today!
Thanks @…

ICPR SPONSORED TWO DAY MULTIDISCIPLINARY INTERNATIONAL SEMINAR ON EXPLORING THE PHILOSOPHY OF YOGA: THE PURSUIT OF HEALTH, HAPPINESS, HARMONY AND BEYOND
https://ift.tt/j1JM3nr
updated: Monday, July 7, 2025 - 2:17pmfull name / name of organization: ICPR AND DEPARTMENT OF…
via Input 4 RELCFP

The year 2038 will be "interesting".
At 03:14:07 UTC on 19 January 2038 we will hit what may be the real Y2K problem.
And will the US exist as a single nation-state in the year 2038? (I have serious doubts.)

LLM-Driven Self-Refinement for Embodied Drone Task Planning
Deyu Zhang, Xicheng Zhang, Jiahao Li, Tingting Long, Xunhua Dai, Yongjian Fu, Jinrui Zhang, Ju Ren, Yaoxue Zhang
https://arxiv.org/abs/2508.15501

LLM-Driven Self-Refinement for Embodied Drone Task Planning
We introduce SRDrone, a novel system designed for self-refinement task planning in industrial-grade embodied drones. SRDrone incorporates two key technical contributions: First, it employs a continuous state evaluation methodology to robustly and accurately determine task outcomes and provide explanatory feedback. This approach supersedes conventional reliance on single-frame final-state assessment for continuous, dynamic drone operations. Second, SRDrone implements a hierarchical Behavior Tree…

Data-driven optimized high-order WENO schemes with low-dissipation and low-dispersion
Jinrui Zhou, Yiqi Gu, Song Jiang, Hua Shen, Liwei Xu, Guanyu Zhou
https://arxiv.org/abs/2508.13190

Data-driven optimized high-order WENO schemes with low-dissipation and low-dispersion
Classical high-order weighted essentially non-oscillatory (WENO) schemes are designed to achieve optimal convergence order for smooth solutions and to maintain non-oscillatory behaviors for discontinuities. However, their spectral properties are not optimal, which limits the ability to capture high-frequency waves and small-scale features. In this paper, we propose a data-driven optimized method to improve the spectral properties of the WENO schemes. By analyzing the approximate dispersion rela…

Prompt-aware of Frame Sampling for Efficient Text-Video Retrieval
Deyu Zhang, Tingting Long, Jinrui Zhang, Ligeng Chen, Ju Ren, Yaoxue Zhang
https://arxiv.org/abs/2507.15491

Prompt-aware of Frame Sampling for Efficient Text-Video Retrieval
Enabling efficient text-video retrieval on edge-end devices is critical for real-world applications. Yet, existing methods face a critical challenge in balancing accuracy and computational efficiency: uniform frame sampling methods ensure content coverage but incur prohibitive computational costs, while salient-frame sampling methods reduce overhead but suffer from query-agnostic frame selection that biases retrieval results. To address this, we propose ProCLIP, a user-centric framework that ac…