Category
3,017 papers
An exact distance identity for two coupled updates is derived and approximate non-expansiveness of the common-example map is proved, with a quadratic defect only when the two latent margins straddle zero.
This work introduces ERASE, Erasure via Reconstructive Adversarial Signal Editing, a framework for on-the-go forgetting that suppresses the observable influence of private data without modifying model weights, establishing a scalable, regulation-aligned pathway for continual, privacy-conscious learning.
This work introduces Selective Posterior Margin Regularization (SPMR), which preserves the Forward objective and converts this disagreement into a graded update on the clean classifier and transfers to estimated transitions, human annotations, architectural changes, and stronger Forward recipes.
We study adaptive routing of prompts to large language model (LLM) experts to maximize response quality in an online setting with limited feedback. We formulate it as a bandit problem with $K$ actions that represent experts and $d$ features that encode prompts, over a horizon of $T$ rounds. We propose algorithms that s...
Reach audiences
Advertise in front of researchers, engineers, and readers.
We study variance-preserving diffusion of the response in mixed linear regression (MLR) with unknown mixing weights. Our analysis separates the statistical guarantees of score matching from the loss geometry and optimization signal at a fixed diffusion noise level. The KL divergence links the denoising score matching o...
This paper applies the A4/LEARN PET archive, treating observed PET as a design laboratory for scarce-confirmation studies and asks a deliberately operational question: when is simple transparent PET validation enough, and when is a fitted residual-uncertainty score worth the added complexity?
LLM-guided search is usually adopted to solve complex tasks by ranking and pruning top-$K$ candidates based on evaluator scores. However, irreducible bias still exists even if popular methods, such as repeated sampling, are applied to reduce variance. Consequently, pruning may remove every continuation that can reach a...
CARE is introduced, a confounder-aware aggregation framework that explicitly models LLM judge scores as arising from both a latent true-quality signal and shared confounding factors and separates quality from confounders without access to ground-truth labels.
The performance of large language models (LLMs) on verifiable tasks is usually measured by pass@k, the probability of answering a question correctly at least once in k trials. At a fixed budget, a more suitable metric is coverage@cost, the average number of unique questions answered as a function of the total number of...
This study establishes DUA-D2C as a theoretically grounded and effective approach to combating overfitting in modern deep learning, analytically demonstrating how dynamic parameter fusion reduces model variance.
The framework thereby makes preference aggregation an explicit and statistically analyzable design choice rather than an implicit consequence of pooling human feedback, and produces a single policy with explicit collective-welfare guarantees.
A general procedure for evaluating epistemic potency in discrete settings is given, and it is shown that ID-pruned experiments are combinatorially inert, yielding a super-exponential reduction in the number of subsets evaluated.
Accelerating the search for novel antimicrobial peptides using Google Antigravity for Science.
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.
General Science
General Science
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
