Category
17,191 papers
This paper examines what can be reliably inferred when LLMs perform well on test sets produced by CLadder and finds that even simple models such as random forests perform well on CLadder-generated data sets after training on a sample of generated data.
SkillMem is introduced, which represents each reusable skill as a small external latent memory and makes it directly available during latent multi-agent reasoning, showing that compact procedural memories can be reused without sacrificing the efficiency of latent multi-agent reasoning.
An evaluation framework is developed that distinguishes solution quality from execution failures, including numerical inaccuracies, constraint violations, and output-format errors, and demonstrates that iterative refinement substantially improves reliability and extends the range of problem dimensions over which LLMs p...
Evaluating seven LLM agents on the HQ-50 subset under a standardized budget, it is found that closed-book rediscovery is rare, at most 7 of 40 resolved problems, whereas live-web success mostly reflects retrieval of published solutions.
Reach audiences
Advertise in front of researchers, engineers, and readers.
ThinkJev builds a fast and a slow system from one open hybrid-thinking model that can answer directly or after a thought, and chooses when to think from System 1's confidence alone saves less, because the decisions System 1 is least sure of are often not the ones thinking fixes.
An application to the k-$\epsilon$ turbulence closure in a single-column ocean model, with atmospheric surface forcing as context, shows that localized posterior calibration reduces temperature and zonal-velocity errors relative to deterministic and global-posterior calibration.
LRMoE is presented, a memory-aware MoE training system that jointly recalibrates backward demand and balances the retained workload, and reduces cumulative MoE-layer training time to fixed-loss targets by 21.2-44.8% relative to SYMI.
Decoding sensory-evoked functional magnetic resonance imaging (fMRI) data is a central analytical tool in cognitive neuroscience. Here we ask whether self-supervised learning (SSL), which has been scarcely explored in this domain, can yield representations that support strong downstream performance. To do so, we adapt...
Zero-real Agent Policy (ZAP), a recipe that teaches a small off-the-shelf vision-language model to control a robot via a simple tool harness, uses a pretrained 27B parameter model to bootstrap world understanding and reasoning, followed by supervised fine-tuning and GRPO on simple simulated tasks to teach it how to mov...
Multi-fidelity training, which combines abundant low-fidelity data with scarce high-fidelity labels, is increasingly common in atomistic modeling, but its effect on predictive uncertainty remains largely unexplored. We investigate this question using deep ensembles of mean-variance MACE models trained on ANI-1x, contra...
Science agents increasingly package domain expertise as reusable skills that plan analyses, select tools, and execute workflows. This modularity creates a confidentiality risk: the interactions that deliver a skill's capability can also reveal the skill itself. We build an extensible benchmark of 40 protected skills ac...
On-device fine-tuning lets a large language model (LLM) learn from its user's private data without uploading it. Low-rank adaptation (LoRA) reduces the trainable parameters, but each first-order training step still multiplies by the frozen base-model weights during the forward pass, activation recomputation, and input-...
A Blog post by Ai2 on Hugging Face
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
Learn how Google Antigravity and our Cheminformatics Skills accelerate drug discovery workflows, search compounds, and propose novel rigidified macrocycles.
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
Prabha Jha used her experience with MIT Open Learning’s program for senior executives to develop AI solutions for her employer, Verizon, and to write a book.
Education Innovation
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
