Category
18,068 papers
Activation steering controls large language model behavior by adding a direction to hidden activations during inference. For steering to work well, that direction must be a pure signal for the target concept: any confound entangled with it, such as an incidental topic or writing style, is injected into the residual str...
On-policy distillation (OPD) improves language-model by supervising a student on prefixes sampled from its own policy, but its supervision remains confined to the output space. Consequently, OPD transfers what a teacher predicts without supervising the intermediate computation that produces those predictions. Simply di...
CoEvoke is introduced, a cross-domain framework that evokes public interactions to evidence, decisions, and task-native outcomes during trajectory collection that supports designing collection conditions to obtain corrective supervision that improves collaborative decisions with frozen solving agents.
We propose Barycentric Anchored Search, a post-hoc weight-space procedure for improving fine-tuned vision models under distribution shift without additional gradient training or increased inference cost. Given a pre-trained initialization and two checkpoints fine-tuned on a source dataset, the method constructs barycen...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Learning-to-rank (LTR) models can align rankings with undesignated signals when those signals appear as features or leak into training labels. We compare label-free genetic multi-criteria sorting (open Pikaia strategy variants), which reranks fixed candidate pools using an explicit criteria vector C, to label-trained L...
Accurate day-ahead photovoltaic (PV) power forecasting requires both strong temporal modeling and adherence to physical PV system constraints. Purely data-driven models often ignore the underlying PV conversion process and may produce predictions that are outside the operational range of a PV system. In this paper, we...
Large AI models increasingly rely on distributed GPU execution, yet it remains unclear whether established failure analysis methods transfer effectively to this setting. We introduce GF-Bench, a PyTorch-based framework and dataset for generating diverse failures in distributed GPU workloads. The framework supports exte...
A familiar line of reasoning runs as follows: language models are flexible approximators trained under a strictly proper loss, so scale brings them closer to Solomonoff induction, and their predictive success is evidence of that approach. We apply known results from algorithmic information theory, universal prediction...
Since compact, interpretable classifiers correspond to simple programs, it is natural to ask if LLM-based coding agents can be used to learn interpretable models from data. In this paper we present a simple harness that repeatedly prompts a coding LLM to produce the next rule in a rule set, given a sample of labeled ex...
People often learn from others' demonstrations, and inverse reinforcement learning (IRL) techniques have realized this capacity in machines. In contrast, teaching by demonstration has been less well studied computationally. Here, we develop a Bayesian model for teaching by demonstration. Stark differences arise when de...
On-policy self-distillation (OPSD) uses a self-teacher conditioned on privileged information to turn the sparse outcome signal of reinforcement learning with verifiable rewards (RLVR) into dense token-level supervision. Yet the teacher's advantage may depend on information unavailable to the student at inference, raisi...
Group-relative reinforcement learning methods such as GRPO train large language model (LLM) agents by comparing rollouts for the same task. When every trajectory in a group fails with the same reward, relative advantages collapse toward zero, leaving no useful learning signal. A frozen teacher can recover from a studen...
The new approach, known as FLEX, could lead to more intuitive, interactive household and assistive robots.
By learning how matter moves, the WorldParticle system could assist with developing soft robots, medicines, and more.
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
