arXiv:2606. 01060v1 Announce Type: cross Abstract: Preference alignment has substantially improved the observable behavior of large language models, yet it remains unclear what alignment changes internally.
By Partha Pratim Saha, Samarth Raina, Mayur Parvatikar, Amit Dhanda, Vinija Jain, Aman Chadha, Amitava Das
Topological Steering is a new framework that steers large language model (LLM) behavior by leveraging topological representations of activation spaces, specifically using persistence diagrams from Topological Data Analysis (TDA). Unlike traditional methods that intervene directly in activation or feature space, this approach captures global structure, making it more robust to outliers, distributional shifts, noise, and local perturbations. Experiments demonstrate that Topological Steering consistently modifies LLM behavior across multiple model families and sizes.
By Beno\^it Gu\'erand, Tan Minh Nguyen
arXiv:2608. 09997v1 Announce Type: new Abstract: Transformers have had a profound impact on the world of language processing and computer vision.
By Kaustubh Kapil, Kishor P. Upla
arXiv:2510. 24342v2 Announce Type: replace Abstract: Prior brain-AI alignment studies are typically constrained by specific inputs and tasks, limiting their ability to capture organizational properties across models with different modalities.
By Silin Chen, Yuzhong Chen, Caiwei Wang, Zifan Wang, Junhao Wang, Zifeng Jia, Keith M Kendrick, Tuo Zhang, Lin Zhao, Dezhong Yao, Tianming Liu, Xi Jiang
arXiv:2607. 17962v1 Announce Type: cross Abstract: TabPFN is a transformer-based foundation model for tabular prediction that performs inference without task-specific training by conditioning on a support set and query inputs.
By James Hu, Mahdi Ghelichi
arXiv:2607. 20484v1 Announce Type: new Abstract: Large Language Models (LLMs) are fundamentally limited by representation collapse, a bottleneck that severely degrades long-context performance.
By Yiheng Tao, Kaiwen Cheng, Yao Lu, Chang Liu, Jie Chen