Judah Goldfeder | Ravid Shwartz-Zivhttps://www.ravid-shwartz-ziv.com/author/judah-goldfeder/Judah GoldfederSource Themes Academic (https://sourcethemes.com/academic/)en-usMon, 24 Aug 2026 03:33:39 +0000https://www.ravid-shwartz-ziv.com/img/ravid-shwartz-ziv-social-v2.pngJudah Goldfederhttps://www.ravid-shwartz-ziv.com/author/judah-goldfeder/Don't Repeat Yourself: Stopping Verbatim Loops at Sampling Timehttps://www.ravid-shwartz-ziv.com/publication/dry-sampling/Mon, 24 Aug 2026 03:33:39 +0000https://www.ravid-shwartz-ziv.com/publication/dry-sampling/XTC: Head-Aware Sampling by Excluding Top Choiceshttps://www.ravid-shwartz-ziv.com/publication/xtc-sampling/Mon, 24 Aug 2026 03:27:30 +0000https://www.ravid-shwartz-ziv.com/publication/xtc-sampling/S-JEPA: Soft Clustering Anchors for Self-Supervised Speech Representation Learninghttps://www.ravid-shwartz-ziv.com/publication/s-jepa/Wed, 17 Jun 2026 00:00:00 +0000https://www.ravid-shwartz-ziv.com/publication/s-jepa/<p>Related work: the earlier <a href="https://www.ravid-shwartz-ziv.com/publication/gmm-anchored-jepa/">GMM-Anchored JEPA study</a> uses fixed soft acoustic clusters to support speech representation learning.</p>Mirage Probes: How Vision Models Fake Visual Understandinghttps://www.ravid-shwartz-ziv.com/publication/mirage-probes/Thu, 11 Jun 2026 19:51:44 +0000https://www.ravid-shwartz-ziv.com/publication/mirage-probes/AI Must Embrace Specialization via Superhuman Adaptable Intelligencehttps://www.ravid-shwartz-ziv.com/publication/superhuman-adaptable-intelligence/Fri, 27 Feb 2026 03:26:21 +0000https://www.ravid-shwartz-ziv.com/publication/superhuman-adaptable-intelligence/Do Multi-Agents Dream of Electric Screens? Achieving Perfect Accuracy on AndroidWorld Through Task Decompositionhttps://www.ravid-shwartz-ziv.com/publication/minitap/Sun, 08 Feb 2026 00:00:00 +0000https://www.ravid-shwartz-ziv.com/publication/minitap/Soft Clustering Anchors for Self-Supervised Speech Representation Learning in Joint Embedding Prediction Architectureshttps://www.ravid-shwartz-ziv.com/publication/gmm-anchored-jepa/Fri, 30 Jan 2026 20:51:37 +0000https://www.ravid-shwartz-ziv.com/publication/gmm-anchored-jepa/<p>Related work: <a href="https://www.ravid-shwartz-ziv.com/publication/s-jepa/">S-JEPA</a> is the later speech study with a continuous two-phase training procedure and online clustering targets.</p>A superpersuasive autonomous policy debating systemhttps://www.ravid-shwartz-ziv.com/publication/deepdebater/Sat, 22 Nov 2025 00:45:01 +0000https://www.ravid-shwartz-ziv.com/publication/deepdebater/Exploring Human-AI Conceptual Alignment through the Prism of Chesshttps://www.ravid-shwartz-ziv.com/publication/chess-conceptual-alignment/Wed, 29 Oct 2025 00:00:00 +0000https://www.ravid-shwartz-ziv.com/publication/chess-conceptual-alignment/Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Modelshttps://www.ravid-shwartz-ziv.com/publication/antislop/Thu, 16 Oct 2025 18:22:22 +0000https://www.ravid-shwartz-ziv.com/publication/antislop/NdLinear: Preserving Multi-Dimensional Structure for Parameter-Efficient Neural Networkshttps://www.ravid-shwartz-ziv.com/publication/ndlinear/Fri, 21 Mar 2025 17:52:44 +0000https://www.ravid-shwartz-ziv.com/publication/ndlinear/