Goto

Collaborating Authors

 Large Language Model


DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning Hao Bai 1,2 Yifei Zhou

Neural Information Processing Systems

While training with static demonstrations has shown some promise, we show that such methods fall short for controlling real GUIs due to their failure to deal with real world stochasticity and non-stationarity not captured in static observational data.



OpenAI says new GPT-5 models show major drop in political bias

FOX News

OpenAI's new GPT-5 Instant and GPT-5 Thinking models show a 30% reduction in political bias compared to GPT-4o, according to an internal report obtained by Fox News Digital.


UniToxSupplementaryMaterials

Neural Information Processing Systems

Datasheet Dataset URL Responsibility and statement of license Hosting/maintenance plan Data format Structured metadata UniTox Datasheet Motivation For what purpose was the dataset created? UniTox was created as a unified toxicity dataset across eight types of drug toxicities (cardiotoxicity, liver toxicity, renal toxicity, pulmonary toxicity, hematological toxicity, dermatological toxicity, ototoxicity, and infertility). We generated information across all toxicities for the same set of 2,418 drugs with the same methodology of applying LLMs. For each drug, for each toxicity, we provide an LLM-generated summary of the relevant portions of the drug label, as well as ternary (No/Less/Most) predictions and binary (No/Yes) predictions for that toxicity. Who created the dataset (e.g., which team, research group) and on behalf of which entity (e.g., company, institution, organization)?





Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition

Neural Information Processing Systems

Automating mathematical reasoning is a longstanding goal in artificial intelligence (Newell et al., 1957). A prominent line of work on the problem (Li et al., 2024) uses neural models to direct