Weekly Reads

Learning to Correct Geometry in Generated Videos — Weijie Lyu, Tiancheng Shen et al.
Generated videos often lose geometric consistency under camera motion: structures warp under viewpoint change, parallax becomes inconsistent, and s...
Rethinking the design space of Vanilla Pixel Diffusion Transformers — Soumik Mukhopadhyay, Long Mai et al.
Pixel-space diffusion models have recently re-emerged as a compelling alternative to latent diffusion, avoiding the lossy latent bottleneck and sep...
Behavioral Couplings: From Formation to Behavioral Emergence in Language Models — Dongyoon Hahm, Woogyeol Jin et al.
Fine-tuning large language models (LLMs) can induce behaviors beyond those explicitly targeted. For example, training a model to respond more warml...
AI-Driven Reproducibility and Analytical Robustness in Scientific Discovery — Shicheng Liu, Krista Opsahl-Ong et al.
Reproducible and analytically robust research findings are essential to scientific progress, but evaluating these properties typically requires cos...
StopWatch: Goal Grounding for Object-goal Navigation — Xinhao Liu, Yunsheng Tian et al.
Pretrained VLMs bring rich world knowledge and semantic priors to object-goal navigation, and fine-tuning a VLM into a navigation policy has become...

How Itaú is building generative AI for its entire customer base — OpenAI Blog
With ia.i, a conversational interface, and the IARA governance platform, Itaú is applying its AI First strategy to customers and employees — in one...
Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline — Hugging Face Blog
Benefit Street Partners answers questions faster with Codex — OpenAI Blog
Anant Kumar builds tools to compare loan valuations and analyze credit agreements, using Codex for code review and faster follow-ups.