· ai
[Paper] Mechanisms of Non-Monotonic Scaling in Vision Transformers
Deeper Vision Transformers often perform worse than shallower ones, which challenges common scaling assumptions. Through a systematic empirical analysis of ViT-...
-
- · ai
[Paper] Qwen3-VL Technical Report
We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benc...
- · ai
[Paper] The author is dead, but what if they never lived? A reception experiment on Czech AI- and human-authored poetry
Large language models are increasingly capable of producing creative texts, yet most studies on AI-generated poetry focus on English -- a language that dominate...
- · ai
[Paper] Scale-Agnostic Kolmogorov-Arnold Geometry in Neural Networks
Recent work by Freedman and Mulligan demonstrated that shallow multilayer perceptrons spontaneously develop Kolmogorov-Arnold geometric (KAG) structure during t...
- · ai
[Paper] Active Learning for GCN-based Action Recognition
Despite the notable success of graph convolutional networks (GCNs) in skeleton-based action recognition, their performance often depends on large volumes of lab...
- · ai
[Paper] TAGFN: A Text-Attributed Graph Dataset for Fake News Detection in the Age of LLMs
Large Language Models (LLMs) have recently revolutionized machine learning on text-attributed graphs, but the application of LLMs to graph outlier detection, pa...
- · ai
[Paper] On the Origin of Algorithmic Progress in AI
Algorithms have been estimated to increase AI training FLOP efficiency by a factor of 22,000 between 2012 and 2023 [Ho et al., 2024]. Running small-scale ablati...
- · ai
[Paper] Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining
Incorporating metadata in Large Language Models (LLMs) pretraining has recently emerged as a promising approach to accelerate training. However prior work highl...
- · ai
[Paper] Auxiliary Metrics Help Decoding Skill Neurons in the Wild
Large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, yet their internal mechanisms remain largely opaque. In this paper, w...
- · ai
[Paper] Beyond Accuracy: An Empirical Study of Uncertainty Estimation in Imputation
Handling missing data is a central challenge in data-driven analysis. Modern imputation methods not only aim for accurate reconstruction but also differ in how ...
- · ai
[Paper] ReSAM: Refine, Requery, and Reinforce: Self-Prompting Point-Supervised Segmentation for Remote Sensing Images
Interactive segmentation models such as the Segment Anything Model (SAM) have demonstrated remarkable generalization on natural images, but perform suboptimally...
- · ai
[Paper] TAB-DRW: A DFT-based Robust Watermark for Generative Tabular Data
The rise of generative AI has enabled the production of high-fidelity synthetic tabular data across fields such as healthcare, finance, and public policy, raisi...