Weekly Reads

Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark — Muyao Niu, Mingze Ma et al.
Robust low-light imaging remains challenging for the community. Recent studies have explored fusing Near-Infrared (NIR) with noisy RGB to achieve i...
Scaling Properties of Text Conditioning in Visual Generation — Zilong Chen, Chaorui Deng et al.
We study empirical scaling properties for text conditioning in visual generation. Such properties have rarely been measured because diffusion loss ...
TokTier: Exact Stateful Tokenization for Agentic LLM Serving — Zhenyu Zhang, Zhichao Cao
LLM serving systems cache prompt KV state, yet most front ends still re-tokenize the full request text on every call. The cost lands on coding agen...
ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction — Boyang Zhang, Adrian Lyjak et al.
Enterprise workflows increasingly rely on agents for \emph{schema-guided extraction}: given a document and a user-defined schema, the agent faithfu...
Differentially Private Nonparametric Modal Learning with Applications to Regression and Clustering — Arkajyoti Bhattacharjee, Arnab Auddy
Density modes provide a localized and interpretable summary of multimodal distributions, but their estimation under rigorous differential privacy c...

Ten advances in mathematics and theoretical computer science — OpenAI Blog
OpenAI shares new results on long-standing open problems in mathematics and theoretical computer science, including advances in geometry, cryptogra...
Advancing responsible AI across Europe — OpenAI Blog
OpenAI shares how its safety, security, transparency, and provenance practices support responsible AI governance in Europe. The work will continue ...
Building abundant intelligence — OpenAI Blog
A full-stack approach to making advanced AI more capable, more affordable, and more widely useful.