Category
2,285 papers
Through PlayTrain, an RL framework that combines the abilities of large language models to robustly generate JavaScript games from a minimal human prompt, and an efficient pipeline that can run any JS game in a standard'gym'environment, this work reimagine RL VGE development.
Large Language Models (LLMs) are increasingly deployed in settings where rare but severe harmful generations can have significant consequences. Existing Risk-Averse RLHF addresses this issue by optimizing Conditional Value-at-Risk (CVaR), but it trains policies for fixed risk levels and therefore cannot adjust the desi...
Adapting large language models (LLMs) to specialized financial reasoning typically requires expensive fine-tuning that produces model-locked expertise. Training-free alternatives have emerged, yet our experiments show that leading methods (GEPA and ACE) achieve only marginal gains on the FAMMA financial reasoning bench...
This work establishes a feedback design strategy that reformulates environments by transitioning from action guidance to observation enrichment during the later stages of both intra-episode exploration and inter-episode evolution, and reveals that FEEs consistently yield performance improvements over standard settings.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This study studies how large language model (LLM)-powered chatbots respond to series of questions about legal reasonableness, and suggests that chatbot responses generally track those of human participants.
A World Values Survey-grounded simulation framework where culturally diverse agents with different communication styles engage in longitudinal, value-laden discussions suggests that current LLM agents can generate plausible conversations, but remain limited proxies for representing and preserving diverse human value pr...
Poster presented at the 10th Research Software Engineering Conference (RSECon26) in Sheffield, UK, 9-11 September, 2026. Abstract The use of generative AI tools to generate source code or to augment a programmer's own code is ever more widespread in research software development. While evidence of associated gains in p...
Poster presented at the 10th Research Software Engineering Conference (RSECon26) in Sheffield, UK, 9-11 September, 2026. Abstract The use of generative AI tools to generate source code or to augment a programmer's own code is ever more widespread in research software development. While evidence of associated gains in p...
Poster presented at the 10th Research Software Engineering Conference (RSECon26) in Sheffield, UK, 9-11 September, 2026. Abstract The use of generative AI tools to generate source code or to augment a programmer's own code is ever more widespread in research software development. While evidence of associated gains in p...
Large Language Models (LLMs) have transformed natural language processing (NLP), but their billions of parameters make them opaque. This lack of transparency is especially problematic in high-risk areas such as healthcare, finance, and content moderation, where understanding model decisions is essential for responsible...
In complex industrial scenarios, traditional Industrial Anomaly Detection methods often perform poorly under extreme conditions such as low light, high-speed motion, and strong light interference. To address this, we propose RGB-Event Industrial Anomaly Detection via Vision-Language Model (ReIAD-VL), integrating RGB im...
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
By rethinking how large cloud computing systems operate, Associate Professor Christina Delimitrou seeks to make data centers more energy efficient.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
