John Chuang

Leonard Waldmann, Ando Shah, Yi Wang et al.

Earth observation (EO) data features diverse sensing platforms with varying spectral bands, spatial resolutions, and sensing modalities. While most prior work has constrained inputs to fixed sensors, a new class of any-sensor foundation models able to process arbitrary sensors has recently emerged. Contributing to this line of work, we propose Panopticon, an any-sensor foundation model built on the DINOv2 framework. We extend DINOv2 by (1) treating images of the same geolocation across sensors as natural augmentations, (2) subsampling channels to diversify spectral input, and (3) adding a cross attention over channels as a flexible patch embedding mechanism. By encoding the wavelength and modes of optical and synthetic aperture radar sensors, respectively, Panopticon can effectively process any combination of arbitrary channels. In extensive evaluations, we achieve state-of-the-art performance on GEO-Bench, especially on the widely-used Sentinel-1 and Sentinel-2 sensors, while out-competing other any-sensor models, as well as domain adapted fixed-sensor models on unique sensor configurations. Panopticon enables immediate generalization to both existing and future satellite platforms, advancing sensor-agnostic EO.

Marianne Chuang, Gabriel Chuang, Cheryl Chuang et al.

We study the use of large language models (LLMs) to both evaluate and greenwash corporate climate disclosures. First, we investigate the use of the LLM-as-a-Judge (LLMJ) methodology for scoring company-submitted reports on emissions reduction targets and progress. Second, we probe the behavior of an LLM when it is prompted to greenwash a response subject to accuracy and length constraints. Finally, we test the robustness of the LLMJ methodology against responses that may be greenwashed using an LLM. We find that two LLMJ scoring systems, numerical rating and pairwise comparison, are effective in distinguishing high-performing companies from others, with the pairwise comparison system showing greater robustness against LLM-greenwashed responses.

Jeremy Gordon, John Chuang

What do humans do when confronted with a common challenge: we know where we want to go but we are not yet sure the best way to get there, or even if we can. This is the problem posed to agents during spatial navigation and pathfinding, and its solution may give us clues about the more abstract domain of planning in general. In this work, we model pathfinding behavior in a continuous, explicitly exploratory paradigm. In our task, participants (and agents) must coordinate both visual exploration and navigation within a partially observable environment. Our contribution has three primary components: 1) an analysis of behavioral data from 81 human participants in a novel pathfinding paradigm conducted as an online experiment, 2) a proposal to model prospective mental simulation during navigation as particle filtering, and 3) an instantiation of this proposal in a computational agent. We show that our model, Active Dynamical Prospection, demonstrates similar patterns of map solution rate, path selection, and trial duration, as well as attentional behavior (at both aggregate and individual levels) when compared with data from human participants. We also find that both distal attention and delay prior to first move (both potential correlates of prospective simulation) are predictive of task performance.

Thomas Maillart, Mingyi Zhao, Jens Grossklags et al.

Bug bounty programs offer a modern platform for organizations to crowdsource their software security and for security researchers to be fairly rewarded for the vulnerabilities they find. Little is known however on the incentives set by bug bounty programs: How they drive new bug discoveries, and how they supposedly improve security through the progressive exhaustion of discoverable vulnerabilities. Here, we recognize that bug bounty programs create tensions, for organizations running them on the one hand, and for security researchers on the other hand. At the level of one bug bounty program, security researchers face a sort of St-Petersburg paradox: The probability of finding additional bugs decays fast, and thus can hardly be matched with a sufficient increase of monetary rewards. Furthermore, bug bounty program managers have an incentive to gather the largest possible crowd to ensure a larger pool of expertise, which in turn increases competition among security researchers. As a result, we find that researchers have high incentives to switch to newly launched programs, for which a reserve of low-hanging fruit vulnerabilities is still available. Our results inform on the technical and economic mechanisms underlying the dynamics of bug bounty program contributions, and may in turn help improve the mechanism design of bug bounty programs that get increasingly adopted by cybersecurity savvy organizations.