Papers
Deep, long-form breakdowns of recent research in AI, machine learning, security & programming languages.
Spanning Diffusion and Flow-based Posterior Sampling via Exact Gaussian Conditioning
by Teo Deveney, Lea Bogensperger, Hok Shing Wong
QTestBench: A Test Framework for Evaluating LLM-Generated Quantum Code
by Meriem Terki, Nouhaila Innan, Minghao Shao, Muhammad Kashif, Alberto Marchisio, Muhammad Shafique
FORTE: A Production Framework for Feature Evaluation and Deprecation in Industrial Recommender Systems
by Vishnu Arun, Adam Obeng, Tianyou Wang, Zilin Ren, Mukuntha Narayanan Sundararaman, Han Wang, Shivin Thukral, Zhixiang Wang, Saurabh Vishwas Joshi, Darren Reger
BrickBench: Evaluating Agentic Brick Design
by Peter Kulits, Yiqing Xu, R. Kenny Jones, Cordelia Schmid, Jiajun Wu
On the estimation and validity of AI time horizons---a statistical look at the METR plot
by Drew T. Nguyen, William Fithian
From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents
by Abbas Raftari
OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning
by Zhongyu Yang, Jiale Tao, Ruitao Chen, Zuhao Yang, Yingfang Yuan, Xueliang Zhao, Auden, Kai Wang, Shuai Shao, Biao Wang, Steve Yves, Qinglin Lu
Hybrid Cinematography: Previsualizing and Managing Hallucination Risk in Generative Video Reshooting
by Nhan (Nathan) Tran, Neal Wadhwa, Abe Davis, Stefan Stojanov
Bi-FORK: Generative Modeling of High-Dimensional Bifurcating Systems
by Anna Zimmel, Fleur Hendriks, Markus Holzleitner, Florian Sestak, Martin Weichselbaumer, Vlado Menkovski, Johannes Brandstetter
One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
by Adrian Bulat, Yassine Ouali, Georgios Tzimiropoulos