Viral News - CybAI news

22 Nov

Generation through the lens of learning theory

stp2y0 CommentsViral News

[Submitted on 17 Oct 2024 (v1), last revised 21 Nov 2024 (this version, v4)] View a PDF of the paper titled Generation through the lens of learning theory, by Jiaxun Li and 2 other authors View PDF HTML (experimental) Abstract:We study generation through the lens of statistical learning theory. First, we abstract and formalize the results of Gold [1967], Angluin [1979], Angluin [1980] and Kleinberg and Mullainathan [2024] in terms of a binary hypothesis class defined over an abstract example space. Then, we extend the notion of "generation" from Kleinberg and Mullainathan [2024] to two new settings, we call "uniform"…

22 Nov

Multi-times Monte Carlo Rendering for Inter-reflection Reconstruction

stp2y0 CommentsViral News

[Submitted on 8 Jul 2024 (v1), last revised 21 Nov 2024 (this version, v3)] View a PDF of the paper titled Multi-times Monte Carlo Rendering for Inter-reflection Reconstruction, by Tengjie Zhu and 4 other authors View PDF HTML (experimental) Abstract:Inverse rendering methods have achieved remarkable performance in reconstructing high-fidelity 3D objects with disentangled geometries, materials, and environmental light. However, they still face huge challenges in reflective surface reconstruction. Although recent methods model the light trace to learn specularity, the ignorance of indirect illumination makes it hard to handle inter-reflections among multiple smooth objects. In this work, we propose Ref-MC2 that…

22 Nov

Evaluating the Robustness of Analogical Reasoning in Large Language Models

stp2y0 CommentsViral News

arXiv:2411.14215v1 Announce Type: new Abstract: LLMs have performed well on several reasoning benchmarks, including ones that test analogical reasoning abilities. However, there is debate on the extent to which they are performing general abstract reasoning versus employing non-robust processes, e.g., that overly rely on similarity to pre-training data. Here we investigate the robustness of analogy-making abilities previously claimed for LLMs on three of four domains studied by Webb, Holyoak, and Lu (2023): letter-string analogies, digit matrices, and story analogies. For each domain we test humans and GPT models on robustness to variants of the original analogy problems that test the…

22 Nov

When Online Algorithms Influence the Environment: A Dynamical Systems Analysis of the Unintended Consequences

stp2y0 CommentsViral News

arXiv:2411.13883v1 Announce Type: new Abstract: We analyze the effect that online algorithms have on the environment that they are learning. As a motivation, consider recommendation systems that use online algorithms to learn optimal product recommendations based on user and product attributes. It is well known that the sequence of recommendations affects user preferences. However, typical learning algorithms treat the user attributes as static and disregard the impact of their recommendations on user preferences. Our interest is to analyze the effect of this mismatch between the model assumption of a static environment, and the reality of an evolving environment affected by…

22 Nov

ID-Patch: Robust ID Association for Group Photo Personalization

stp2y0 CommentsViral News

arXiv:2411.13632v1 Announce Type: new Abstract: The ability to synthesize personalized group photos and specify the positions of each identity offers immense creative potential. While such imagery can be visually appealing, it presents significant challenges for existing technologies. A persistent issue is identity (ID) leakage, where injected facial features interfere with one another, resulting in low face resemblance, incorrect positioning, and visual artifacts. Existing methods suffer from limitations such as the reliance on segmentation models, increased runtime, or a high probability of ID leakage. To address these challenges, we propose ID-Patch, a novel method that provides robust association between identities and…

22 Nov

OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs

stp2y0 CommentsViral News

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol

22 Nov

Model-Based Transfer Learning for Contextual Reinforcement Learning

stp2y0 CommentsViral News

[Submitted on 8 Aug 2024 (v1), last revised 21 Nov 2024 (this version, v2)] View a PDF of the paper titled Model-Based Transfer Learning for Contextual Reinforcement Learning, by Jung-Hoon Cho and 3 other authors View PDF HTML (experimental) Abstract:Deep reinforcement learning (RL) is a powerful approach to complex decision making. However, one issue that limits its practical application is its brittleness, sometimes failing to train in the presence of small changes in the environment. Motivated by the success of zero-shot transfer-where pre-trained models perform well on related tasks-we consider the problem of selecting a good set of training tasks…

22 Nov

FlightPatchNet: Multi-Scale Patch Network with Differential Coding for Flight Trajectory Prediction

stp2y0 CommentsViral News

[Submitted on 25 May 2024 (v1), last revised 21 Nov 2024 (this version, v2)] View a PDF of the paper titled FlightPatchNet: Multi-Scale Patch Network with Differential Coding for Flight Trajectory Prediction, by Lan Wu and 6 other authors View PDF HTML (experimental) Abstract:Accurate multi-step flight trajectory prediction plays an important role in Air Traffic Control, which can ensure the safety of air transportation. Two main issues limit the flight trajectory prediction performance of existing works. The first issue is the negative impact on prediction accuracy caused by the significant differences in data range. The second issue is that real-world…

22 Nov

Why do language models perform worse for morphologically complex languages?

stp2y0 CommentsViral News

arXiv:2411.14198v1 Announce Type: new Abstract: Language models perform differently across languages. It has been previously suggested that morphological typology may explain some of this variability (Cotterell et al., 2018). We replicate previous analyses and find additional new evidence for a performance gap between agglutinative and fusional languages, where fusional languages, such as English, tend to have better language modeling performance than morphologically more complex languages like Turkish. We then propose and test three possible causes for this performance gap: morphological alignment of tokenizers, tokenization quality, and disparities in dataset sizes and measurement. To test the morphological alignment hypothesis, we present…

22 Nov

Exploring applications of topological data analysis in stock index movement prediction

stp2y0 CommentsViral News

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol