activity
20242026
collaborators
Showing 2025Show all

6 papers · 1 filter

cs.CV2025

SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models

Arijit Ray, Jiafei Duan, Ellis Brown +9

Reasoning about motion and space is a fundamental cognitive capability that is required by multiple real-world applications. While many studies highlight that large multimodal lang…

cs.LG2025

Scaling Up Temporal Domain Generalization via Temporal Experts Averaging

Aoming Liu, Kevin Miller, Venkatesh Saligrama +4

Temporal Domain Generalization (TDG) aims to generalize across temporal distribution shifts, e.g., lexical change over time. Prior work often addresses this by predicting future mo…

cs.CV2025

Web Artifact Attacks Disrupt Vision Language Models

Maan Qraitem, Piotr Teterwak, Kate Saenko +1

Vision-language models (VLMs) (e.g. CLIP, LLaVA) are trained on large-scale, lightly curated web datasets, leading them to learn unintended correlations between semantic concepts a…

cs.CV2025

Is Large-Scale Pretraining the Secret to Good Domain Generalization?

Piotr Teterwak, Kuniaki Saito, Theodoros Tsiligkaridis +2

Multi-Source Domain Generalization (DG) is the task of training on multiple source domains and achieving high classification performance on unseen target domains. Recent methods co…

cs.CV2025

RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks

Nazia Tasnim, Bryan A. Plummer

Incremental learning aims to adapt to new sets of categories over time with minimal computational overhead. Prior work often addresses this task by training efficient task-specific…

cs.CV2025

Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks

Maan Qraitem, Nazia Tasnim, Piotr Teterwak +2

Typographic attacks, adding misleading text to images, can deceive vision-language models (LVLMs). The susceptibility of recent large LVLMs like GPT4-V to such attacks is understud…