Tootfinder

Towards Improving Learning from Demonstration Algorithms via MCMC Methods
Hanwen Qi, Edward Sun, Harry Zhang
https://arxiv.org/abs/2405.02243 https://

Towards Improving Learning from Demonstration Algorithms via MCMC Methods
Behavioral cloning, or more broadly, learning from demonstrations (LfD) is a priomising direction for robot policy learning in complex scenarios. Albeit being straightforward to implement and data-efficient, behavioral cloning has its own drawbacks, limiting its efficacy in real robot setups. In this work, we take one step towards improving learning from demonstration algorithms by leveraging implicit energy-based policy models. Results suggest that in selected complex robot policy learning sce…

The timespan of these projects is inspiring.
"It takes three months for the molten glass to cool. Over the next four years, the mirror will be mounted, ground and slowly polished to a precision of around one millionth of an inch. The [Giant Magellan Telescope's] first mirror was cast in [2005]; its seventh will be finished sometime in [2027].
[…] big telescopes require […] the world’s most patient risk capital."

Stumbling Towards First Light
Why has Chile, a country riven by inequality and political conflict, become a global sanctuary for the long science that drives astronomical discovery?

Towards Neural Synthesis for SMT-Assisted Proof-Oriented Programming
Saikat Chakraborty, Gabriel Ebner, Siddharth Bhat, Sarah Fakhoury, Sakina Fatima, Shuvendu Lahiri, Nikhil Swamy
https://arxiv.org/abs/2405.01787

Towards Neural Synthesis for SMT-Assisted Proof-Oriented Programming
Proof-oriented programs mix computational content with proofs of program correctness. However, the human effort involved in programming and proving is still substantial, despite the use of Satisfiability Modulo Theories (SMT) solvers to automate proofs in languages such as F*. Seeking to spur research on using AI to automate the construction of proof-oriented programs, we curate a dataset of 600K lines of open-source F* programs and proofs, including software used in production systems rangin…

OpenAI hits back at Elon Musk's lawsuit, accusing Musk of suing the company when it "started making meaningful progress towards OpenAI's mission without him" (Bloomberg)
https://www.bloomberg.com/news/articles/20

OpenAI Responds to Musk Lawsuit: ‘Sad It’s Come to This’
OpenAI responded to a lawsuit filed against it by Elon Musk in a blog post Tuesday — saying he signed off on the company’s decision to become a for-profit entity and that he insisted it needed to raise “billions” of dollars to be relevant compared with Google.

Towards a Formal Creativity Theory: Preliminary results in Novelty and Transformativeness
Lu\'is Esp\'irito Santo, Geraint Wiggins, Am\'ilcar Cardoso
https://arxiv.org/abs/2405.02148

Towards a Formal Creativity Theory: Preliminary results in Novelty and Transformativeness
Formalizing creativity-related concepts has been a long-term goal of Computational Creativity. To the same end, we explore Formal Learning Theory in the context of creativity. We provide an introduction to the main concepts of this framework and a re-interpretation of terms commonly found in creativity discussions, proposing formal definitions for novelty and transformational creativity. This formalisation marks the beginning of a research branch we call Formal Creativity Theory, exploring how …

Towards Calibrated Deep Clustering Network
Yuheng Jia, Jianhong Cheng, Hui Liu, Junhui Hou
https://arxiv.org/abs/2403.02998 https://a…

Towards Calibrated Deep Clustering Network
Deep clustering has exhibited remarkable performance; however, the overconfidence problem, i.e., the estimated confidence for a sample belonging to a particular cluster greatly exceeds its actual prediction accuracy, has been overlooked in prior research. To tackle this critical issue, we pioneer the development of a calibrated deep clustering framework. Specifically, we propose a novel dual-head deep clustering pipeline that can effectively calibrate the estimated confidence and the actual acc…

Towards A Double-Edged Sword: Modelling the Impact in Agile Software Development
Michael Neumann, Philipp Diebold
https://arxiv.org/abs/2405.01757 https://…

Towards A Double-Edged Sword: Modelling the Impact in Agile Software Development
Agile methods are state of the art in software development. Companies worldwide apply agile to counter the dynamics of the markets. We know, that various factors like culture influence the successfully application of agile methods in practice and the sucess is differing from company to company. To counter these problems, we combine two causal models presented in literature: The Agile Practices Impact Model and the Model of Cultural Impact. In this paper, we want to better understand the two fac…

I actually have a lot planned for today... but there are other pressures! #CatsOfMastondon #Caturday #Catsodon

This https://arxiv.org/abs/2404.02405 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression
In this paper, we investigate that the normalized coordinate expression is a key factor as reliance on hand-crafted components in query-based detectors for temporal action detection (TAD). Despite significant advancements towards an end-to-end framework in object detection, query-based detectors have been limited in achieving full end-to-end modeling in TAD. To address this issue, we propose \modelname{}, a full end-to-end temporal action detection transformer that integrates time-aligned coord…

This https://arxiv.org/abs/2404.02405 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression
In this paper, we investigate that the normalized coordinate expression is a key factor as reliance on hand-crafted components in query-based detectors for temporal action detection (TAD). Despite significant advancements towards an end-to-end framework in object detection, query-based detectors have been limited in achieving full end-to-end modeling in TAD. To address this issue, we propose \modelname{}, a full end-to-end temporal action detection transformer that integrates time-aligned coord…