Papers

Deep, long-form breakdowns of recent research in AI, machine learning, security & programming languages.

All ai machine learning cybersecurity scraping programming languages technology Important
ai Sep 25 LLM Agents Can Easily Tamper With Their Own Traces by Jeremy Qin, David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner, Ameya Prabhu, Maksym Andriushchenko ai Sep 25 AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control by Jiabin Qiu, Zixuan Chen, Hongye Cao, Jieqi Shi, Jing Huo, Yang Gao machine learning Sep 25 Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning by Sudip Bhujel, Shanghao Shi, Ruiquan Huang, Ning Zhang, Yang Xiao programming languages Sep 25 Forte: A sensitivity type system for imperative Rust by Chiké Abuah ai Sep 25 Agentic Detection of Online Conspiracies by Lior Biton, Oren Tsur ai Sep 25 RAPID: Robot Agentic Programming from Demonstrations by Yuyao Liu, Jiayuan Mao, David Hsu, Leslie Pack Kaelbling, Tomás Lozano-Pérez machine learning Sep 25 To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech by Debajyoti Mazumder, Mamta, Abhirama Subramanyam Penamakuri machine learning Sep 25 PoEM: Predicting RL Outcomes from Existing Policies by Kimia Hamidieh, Giannis Daras, Antonio Torralba machine learning Sep 25 Minimally Invasive Steering of Language Models by Taha Entesari, Jingyu Zhang, Daniel Khashabi, Mahyar Fazlyab ai Sep 25 The Alignment Illusion in Multimodal Large Language Models by Hong-Han Wang, Yuntao Wang, Hu Ding