This paper introduces BBOmix, an open-source benchmark for unsupervised representation learning on real-world biological data.

This paper introduces Neural Certificate Pricing (NCP), an unsupervised learning framework that exploits the asymmetry between certifiable discrete structures and structural feasibility in combinatori…

The paper proposes a unified, constrained optimization framework using KL divergence and likelihood constraints to achieve effective and principled unlearning in diffusion models.

This paper derives bounds on the probability of incorrect clustering of noisy short sequences using statistically optimal rules, focusing on DNA storage decoders.

The paper applies network science to demonstrate the feasibility of unsupervised dependency parsing in non-human primates due to their sequence length distribution.

This paper systematically investigates unlearnable examples (UEs) across diverse training paradigms, finding that existing UEs fail under pretraining-finetuning (PF) settings, and proposes Shallow Sem…

This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.

This paper extends gradient boosting to functions of vector inputs using a simple algorithm with histogram-based decision trees.

The paper theoretically analyzes the properties that optimal sparse autoencoder (SAE) dictionaries must satisfy, deriving constraints that explain observed SAE behaviors like hierarchical splitting an…

SUPREME is an open-source, multi-GPU framework designed to efficiently and reproducibly evaluate machine unlearning methods for image classification by distributing computationally intensive tasks acr…

This paper introduces survey sampling techniques to estimate or minimize empirical pairwise loss functions, showing that targeting informative pairs significantly reduces computational cost while main…

This paper provides the first integrated analysis of model dememorization, unifying unlearnability and unlearning methods, and offering theoretical guarantees on dememorization depth.

This paper analyzes the poor performance of Meta-learning for Training-data Selection (MTS) and proposes that increasing the batch size and incorporating informative features can significantly improve…

This paper proposes a two-stage clustering algorithm to ensure per-sample guardrails in LLM-based applications, reducing inference cost and latency.

A new boosting algorithm that strong learns concept classes closed under O(log 1/γ)-XOR using O(log 1/ε) calls to a γ-advantage weak learner and additional samples, by connecting boosting with list-de…

The paper introduces PRAXIS, a novel algorithm that efficiently approximates the computation of 'Rashomon sets' for decision trees, significantly reducing memory and runtime complexity.

TailLoR is a new parameter-efficient finetuning method that uses the singular bases of pre-trained weights to learn low-rank updates, specifically penalizing updates along dominant directions to impro…

The paper proposes pretraining a Perceiver-style in-context learner on synthetic data to solve Multiple Instance Learning (MIL) tasks efficiently in the low-label regime.