26 citations · 91 across the 22 of their papers we have counts for
28 papers
SeeSE3: Emergence of 3D Space in Vision Features
Caroline Chen, Sayna Ebrahimi, Fedor Kitashov +4
In this paper, we ask whether vision foundation models construct representations that reflect the intrinsic properties of 3D Euclidean space. Unlike previous works that probe 3D aw…
Unique Lives, Shared World: Learning from Single-Life Videos
Tengda Han, Sayna Ebrahimi, Dilara Gokay +8
We introduce the "single-life" learning paradigm, where we train a distinct vision model exclusively on egocentric videos captured by one individual. We leverage the multiple viewp…
ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality
Shayne Longpre, Sneha Kudugunta, Niklas Muennighoff +6
Scaling laws research has focused overwhelmingly on English -- yet the most prominent AI models explicitly serve billions of international users. In this work, we undertake the lar…
Reverse Thinking Makes LLMs Stronger Reasoners
Justin Chih-Yao Chen, Zifeng Wang, Hamid Palangi +8
Reverse thinking plays a crucial role in human reasoning. Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towa…
Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Shangbin Feng, Zifeng Wang, Yike Wang +9
We propose Model Swarms, a collaborative search algorithm to adapt LLMs via swarm intelligence, the collective behavior guiding individual systems. Specifically, Model Swarms start…
CROME: Cross-Modal Adapters for Efficient Multimodal LLM
Sayna Ebrahimi, Sercan O. Arik, Tejas Nama +1
Multimodal Large Language Models (MLLMs) demonstrate remarkable image-language capabilities, but their widespread use faces challenges in cost-effective training and adaptation. Ex…
Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment
Pritam Sarkar, Sayna Ebrahimi, Ali Etemad +3
Despite their significant advancements, Multimodal Large Language Models (MLLMs) often generate factually inaccurate information, referred to as hallucination. In this work, we add…
TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents
James Enouen, Hootan Nakhost, Sayna Ebrahimi +3
Large language models (LLMs) have attracted huge interest in practical applications given their increasingly accurate responses and coherent reasoning abilities. Given their nature…
Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs
Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi +3
Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation. However, their use in high-stakes de…
PAITS: Pretraining and Augmentation for Irregularly-Sampled Time Series
Nicasia Beebe-Wang, Sayna Ebrahimi, Jinsung Yoon +2
Real-world time series data that commonly reflect sequential human behavior are often uniquely irregularly sampled and sparse, with highly nonuniform sampling over time and entitie…
LANISTR: Multimodal Learning from Structured and Unstructured Data
Sayna Ebrahimi, Sercan O. Arik, Yihe Dong +1
Multimodal large-scale pretraining has shown impressive performance for unstructured data such as language and image. However, a prevalent real-world scenario involves structured d…
ASPEST: Bridging the Gap Between Active Learning and Selective Prediction
Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi +3
Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. These predictions can then be deferred to humans for further evaluation. A…
Test-Time Adaptation for Visual Document Understanding
Sayna Ebrahimi, Sercan O. Arik, Tomas Pfister
For visual document understanding (VDU), self-supervised pretraining has been shown to successfully generate transferable representations, yet, effective adaptation of such represe…
Contrastive Test-Time Adaptation
Dian Chen, Dequan Wang, Trevor Darrell +1
Test-time adaptation is a special setting of unsupervised domain adaptation where a trained model on the source domain has to adapt to the target domain without accessing source da…
DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning
Zifeng Wang, Zizhao Zhang, Sayna Ebrahimi +8
Continual learning aims to enable a single model to learn a sequence of tasks without catastrophic forgetting. Top-performing methods usually require a rehearsal buffer to store pa…
On-target Adaptation
Dequan Wang, Shaoteng Liu, Sayna Ebrahimi +2
Domain adaptation seeks to mitigate the shift between training on the \emph{source} domain and testing on the \emph{target} domain. Most adaptation methods rely on the source data…
Predicting with Confidence on Unseen Distributions
Devin Guillory, Vaishaal Shankar, Sayna Ebrahimi +2
Recent work has shown that the performance of machine learning models can vary substantially when models are evaluated on data drawn from a distribution that is close to but differ…
Region-level Active Detector Learning
Michael Laielli, Giscard Biamby, Dian Chen +6
Active learning for object detection is conventionally achieved by applying techniques developed for classification in a way that aggregates individual detections into image-level…
Self-Supervised Pretraining Improves Self-Supervised Pretraining
Colorado J. Reed, Xiangyu Yue, Ani Nrusimha +9
While self-supervised pretraining has proven beneficial for many computer vision tasks, it requires expensive and lengthy computation, large amounts of data, and is sensitive to da…
Minimax Active Learning
Sayna Ebrahimi, William Gan, Dian Chen +5
Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator. Current active learning techniques either…
Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting
Sayna Ebrahimi, Suzanne Petryk, Akash Gokul +4
The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting. Previous work has shown that leveraging memory…
Adversarial Continual Learning
Sayna Ebrahimi, Franziska Meier, Roberto Calandra +2
Continual learning aims to learn new tasks without forgetting previously learned ones. We hypothesize that representations learned to solve each task in a sequence have a shared st…
WiCV 2019: The Sixth Women In Computer Vision Workshop
Irene Amerini, Elena Balashova, Sayna Ebrahimi +3
In this paper we present the Women in Computer Vision Workshop - WiCV 2019, organized in conjunction with CVPR 2019. This event is meant for increasing the visibility and inclusion…
Uncertainty-guided Continual Learning with Bayesian Neural Networks
Sayna Ebrahimi, Mohamed Elhoseiny, Trevor Darrell +1
Continual learning aims to learn new tasks without forgetting previously learned ones. This is especially challenging when one cannot access data from previous tasks and when the m…