Viral News - CybAI news

14 Aug

RW-NSGCN: A Robust Approach to Structural Attacks via Negative Sampling

stp2y0 CommentsViral News

arXiv:2408.06665v1 Announce Type: new Abstract: Node classification using Graph Neural Networks (GNNs) has been widely applied in various practical scenarios, such as predicting user interests and detecting communities in social networks. However, recent studies have shown that graph-structured networks often contain potential noise and attacks, in the form of topological perturbations and weight disturbances, which can lead to decreased classification performance in GNNs. To improve the robustness of the model, we propose a novel method: Random Walk Negative Sampling Graph Convolutional Network (RW-NSGCN). Specifically, RW-NSGCN integrates the Random Walk with Restart (RWR) and PageRank (PGR) algorithms for negative sampling and…

14 Aug

HDRGS: High Dynamic Range Gaussian Splatting

stp2y0 CommentsViral News

arXiv:2408.06543v1 Announce Type: new Abstract: Recent years have witnessed substantial advancements in the field of 3D reconstruction from 2D images, particularly following the introduction of the neural radiance field (NeRF) technique. However, reconstructing a 3D high dynamic range (HDR) radiance field, which aligns more closely with real-world conditions, from 2D multi-exposure low dynamic range (LDR) images continues to pose significant challenges. Approaches to this issue fall into two categories: grid-based and implicit-based. Implicit methods, using multi-layer perceptrons (MLP), face inefficiencies, limited solvability, and overfitting risks. Conversely, grid-based methods require significant memory and struggle with image quality and long training times.…

14 Aug

A Perspective on Large Language Models, Intelligent Machines, and Knowledge Acquisition

stp2y0 CommentsViral News

arXiv:2408.06598v1 Announce Type: new Abstract: Large Language Models (LLMs) are known for their remarkable ability to generate synthesized 'knowledge', such as text documents, music, images, etc. However, there is a huge gap between LLM's and human capabilities for understanding abstract concepts and reasoning. We discuss these issues in a larger philosophical context of human knowledge acquisition and the Turing test. In addition, we illustrate the limitations of LLMs by analyzing GPT-4 responses to questions ranging from science and math to common sense reasoning. These examples show that GPT-4 can often imitate human reasoning, even though it lacks understanding. However, LLM…

14 Aug

COD: Learning Conditional Invariant Representation for Domain Adaptation Regression

stp2y0 CommentsViral News

arXiv:2408.06638v1 Announce Type: new Abstract: Aiming to generalize the label knowledge from a source domain with continuous outputs to an unlabeled target domain, Domain Adaptation Regression (DAR) is developed for complex practical learning problems. However, due to the continuity problem in regression, existing conditional distribution alignment theory and methods with discrete prior, which are proven to be effective in classification settings, are no longer applicable. In this work, focusing on the feasibility problems in DAR, we establish the sufficiency theory for the regression model, which shows the generalization error can be sufficiently dominated by the cross-domain conditional discrepancy. Further, to…

14 Aug

Benchmarking tree species classification from proximally-sensed laser scanning data: introducing the FOR-species20K dataset

stp2y0 CommentsViral News

arXiv:2408.06507v1 Announce Type: new Abstract: Proximally-sensed laser scanning offers significant potential for automated forest data capture, but challenges remain in automatically identifying tree species without additional ground data. Deep learning (DL) shows promise for automation, yet progress is slowed by the lack of large, diverse, openly available labeled datasets of single tree point clouds. This has impacted the robustness of DL models and the ability to establish best practices for species classification. To overcome these challenges, the FOR-species20K benchmark dataset was created, comprising over 20,000 tree point clouds from 33 species, captured using terrestrial (TLS), mobile (MLS), and drone laser…

14 Aug

Biomedical Event Extraction via Structure-aware Generation

stp2y0 CommentsViral News

arXiv:2408.06583v1 Announce Type: new Abstract: Biomedical Event Extraction (BEE) is a critical task that involves modeling complex relationships between fine-grained entities in biomedical text data. However, most existing BEE models rely on classification methods that neglect the label semantics and argument dependency structure within the data. To address these limitations, we propose GenBEE, a generative model enhanced with a structure-aware prefix for biomedical event extraction. GenBEE constructs event prompts that leverage knowledge distilled from large language models (LLMs), thereby incorporating both label semantics and argument dependency relationships. Additionally, GenBEE introduces a structural prefix learning module that generates structure-aware prefixes with…

14 Aug

Databricks University Alliance Crosses 1,000 University Threshold

stp2y0 CommentsViral News

Databricks is thrilled to share that our University Alliance has welcomed its one-thousandth-member school! This milestone is a testament to our mission to empower universities and colleges around the world with the tools and resources they need to cultivate a new generation of AI talent. With members spanning 85 countries and over 100,000 students, our program is truly global. By equipping faculty with Databricks tools and teaching materials, we are helping students gain the skills and knowledge that will prepare them for real-world careers. Databricks brings AI to your data, and the talented graduates from our member schools are ready…

14 Aug

Towards Robust and Cost-Efficient Knowledge Unlearning for Large Language Models

stp2y0 CommentsViral News

arXiv:2408.06621v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated strong reasoning and memorization capabilities via pretraining on massive textual corpora. However, training LLMs on human-written text entails significant risk of privacy and copyright violations, which demands an efficient machine unlearning framework to remove knowledge of sensitive data without retraining the model from scratch. While Gradient Ascent (GA) is widely used for unlearning by reducing the likelihood of generating unwanted information, the unboundedness of increasing the cross-entropy loss causes not only unstable optimization, but also catastrophic forgetting of knowledge that needs to be retained. We also discover its joint…

14 Aug

Prompt Recovery for Image Generation Models: A Comparative Study of Discrete Optimizers

stp2y0 CommentsViral News

arXiv:2408.06502v1 Announce Type: new Abstract: Recovering natural language prompts for image generation models, solely based on the generated images is a difficult discrete optimization problem. In this work, we present the first head-to-head comparison of recent discrete optimization techniques for the problem of prompt inversion. We evaluate Greedy Coordinate Gradients (GCG), PEZ , Random Search, AutoDAN and BLIP2's image captioner across various evaluation metrics related to the quality of inverted prompts and the quality of the images generated by the inverted prompts. We find that focusing on the CLIP similarity between the inverted prompts and the ground truth image acts…

14 Aug

OpenEP: Open-Ended Future Event Prediction

stp2y0 CommentsViral News

arXiv:2408.06578v1 Announce Type: new Abstract: Future event prediction (FEP) is a long-standing and crucial task in the world, as understanding the evolution of events enables early risk identification, informed decision-making, and strategic planning. Existing work typically treats event prediction as classification tasks and confines the outcomes of future events to a fixed scope, such as yes/no questions, candidate set, and taxonomy, which is difficult to include all possible outcomes of future events. In this paper, we introduce OpenEP (an Open-Ended Future Event Prediction task), which generates flexible and diverse predictions aligned with real-world scenarios. This is mainly reflected in two…