Activation Addition: Steering Language Models Without Optimization Paper β’ 2308.10248 β’ Published Aug 20, 2023 β’ 1
PaperBanana: Automating Academic Illustration for AI Scientists Paper β’ 2601.23265 β’ Published 27 days ago β’ 201
Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives Paper β’ 2601.20833 β’ Published 29 days ago β’ 178
Digital Red Queen: Adversarial Program Evolution in Core War with LLMs Paper β’ 2601.03335 β’ Published Jan 6 β’ 2
Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance Paper β’ 2601.14171 β’ Published Jan 20 β’ 50
LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics Paper β’ 2511.08544 β’ Published Nov 11, 2025 β’ 10
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning Paper β’ 2506.09985 β’ Published Jun 11, 2025 β’ 31
V-JEPA 2 Collection A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann β’ 8 items β’ Updated Jun 13, 2025 β’ 192
DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation Paper β’ 2601.09688 β’ Published Jan 14 β’ 126
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning Paper β’ 2504.17192 β’ Published Apr 24, 2025 β’ 123
Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits Paper β’ 2512.20578 β’ Published Dec 23, 2025 β’ 85
Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding Paper β’ 2512.17220 β’ Published Dec 19, 2025 β’ 113
Understanding Chain-of-Thought in Large Language Models via Topological Data Analysis Paper β’ 2512.19135 β’ Published Dec 22, 2025 β’ 1
Harnessing the Universal Geometry of Embeddings Paper β’ 2505.12540 β’ Published May 18, 2025 β’ 9
Understanding World or Predicting Future? A Comprehensive Survey of World Models Paper β’ 2411.14499 β’ Published Nov 21, 2024 β’ 1