Category
8,786 papers
LocUS (Localized Unembedding Steering), a method which grounds activation steering to the model's own output vocabulary subspace within the unembedding matrix, enforces a geometric constraint that restricts the steering transformation to a specific subspace and at the same time localizes its application to a sparse sub...
KuaFu is a unified behavior-compression layer whose minimal unit is one behavior item, with fidelity-oriented four-stage training and layered intermediate evaluation, which matches or exceeds uncompressed single-task production models on all five headline metrics, raises per-GPU throughput by 37%-350%, and saves 190 GP...
A unified score, $\mu_i+\lambda_1\sigma_i+\lambda_2\mathrm{corr}(i,S)$, is studied, adding attention dispersion across window queries and redundancy relative to selected tokens to test whether this relevance-diversity balance should vary with depth.
Audio language models state numbers for acoustic quantities, and neither human opinion nor a judge model says whether such a number is true of the signal. AcoustiClaim extracts each numeric claim from free text, scores it against the instrument that defines the quantity, and classes each quantity by where its reference...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Applied out-of-domain, the same audit recipe flags 25.5% of BIRD-financial's expert-authored gold SQLs as candidate gold-SQL issues under the authors' annotation protocol under their annotation protocol.
This work replaces attention with a stack of autoencoder-based mixing modules, one operating over local neighborhoods, one over the full sequence, and one across attention heads, each compressing and reconstructing its input through a bottleneck, and its width is a hyperparameter rather than a training effect.
Large language models (LLMs) implicitly infer attributes of their users and adapt their behavior accordingly, yet these beliefs remain difficult to inspect and causally manipulate. We introduce Belief Self-Distillation (BSD), a unified read-write framework that bridges linear and causal probing by learning a compact us...
Accumulating the GPTQ Hessian across recurrence steps outperforms both one-step GPTQ and RTN on all nine checkpoints and recovers bf16-level accuracy on Huginn.
RAZOR, a training-free pruning method based on consensus residuals, the deviations of expert outputs from their original weighted mixture, gives the exact output change for a single deletion under survivor renormalization and router refill.
It is shown that the annual pretraining run is not necessary, and it is found that a small adapter is enough to add a new period to the knowledge an old checkpoint already encodes, and that this outperforms continued pretraining.
A single-user case study of InMyStyle, a privacy-first, single-user system that adapts small language models to rewrite AI-edited text towards an individual user's writing style without an instruction prompt at inference, finds gains favor content-preserving naturalization more than recovery of personal style.
INFUSER is introduced, an iterative co-training framework with two co-evolving roles: a Generator that drafts questions and reference golden answers from a pool of unstructured, automatically collected documents, and a Solver that improves by training on them, and DuGRPO, a dual-normalized variant of GRPO, for generato...
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
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.
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
