activity
20242026
collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2026

Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks

Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1

With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…

cs.LG2026

Dual Advantage Fields

Alexey Zemtsov, Maxim Bobrin, Alexander Nikulin +5

Offline goal-conditioned reinforcement learning requires both long-horizon reachability estimates and local action comparisons. Dual goal representations provide value fields that…

cs.LG2026

Zero-Shot Off-Policy Learning

Arip Asadulaev, Maksim Bobrin, Salem Lahlou +3

Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to t…

cs.LG2026

Convex Compositional Reasoning Models

Meir Roketlishvili, Semyon Semenov, Maksim Bobrin +7

Compositional energy-based models can generalize to larger combinatorial reasoning problems by reusing a learned factor energy across many local constraints. In our paper, we show…

cs.LG2026

In-Context Learning Operates as Concept Subspace Learning

Wei Tang, Xinyan Jiang, Fakhri Karray +1

Regression and Bayesian accounts of in-context learning (ICL) explain how demonstrations can induce predictors, while mechanistic analyses often identify compact activation directi…

cs.LG2026

Y-Shaped Generative Flows

Arip Asadulaev, Semyon Semenov, Abduragim Shtanchaev +3

Modern continuous-time generative models typically induce \emph{V-shaped} flows: each sample travels independently along a nearly straight trajectory from the prior to the data. Al…