AIConfPaper
← Search

Sayna Ebrahimi

18 accepted papers

2026

ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality

Shayne Longpre, Sneha Kudugunta, Niklas Muennighoff, I-Hung Hsu, Isaac Rayburn Caswell, Alex Pentland +3
ICLR 2026poster

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 largest multilingual scaling laws study to date, totaling 774 multilingual training experiments, spanning 10M-8B model paramet…

Cited by 0Source ↗Scholar ↗
2026

Unique Lives, Shared World: Learning from Single-Life Videos

Tengda Han, Sayna Ebrahimi, Dilara Gokay, Li Yang Ku, Maks Ovsjanikov, Iva Babukova +5
CVPR 2026

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 viewpoints naturally captured within a single life to learn a visual encoder in a self-supervised manner. Our experiments dem

Cited by 0Source ↗Scholar ↗
2025

Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

Pritam Sarkar, Sayna Ebrahimi, Ali Etemad, Ahmad Beirami, Sercan O Arik, Tomas Pfister
ICLR 2025poster

Despite their significant advancements, Multimodal Large Language Models (MLLMs) often generate factually inaccurate information, referred to as hallucination. In this work, we address object hallucinations in MLLMs, where information is generated about an object not present in the input image. We i…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

Shangbin Feng, Zifeng Wang, Yike Wang, Sayna Ebrahimi, Hamid Palangi, Lesly Miculicich +6
ICML 2025poster

We propose Model Swarms, a collaborative search algorithm to adapt LLMs via swarm intelligence, the collective behavior guiding individual systems. Specifically, Model Swarms starts with a pool of LLM experts and a utility function. Guided by the best-found checkpoints across models, diverse LLM exp…

Cited by 6Source ↗PDF ↗Scholar ↗
2025

Reverse Thinking Makes LLMs Stronger Reasoners

Justin Chen, Zifeng Wang, Hamid Palangi, Rujun Han, Sayna Ebrahimi, Long Le +5
NAACL 2025long

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 towards the problem. This often enhances overall reasoning performance as it enables consistency checks between their forwar…

Cited by 3Source ↗PDF ↗Scholar ↗
2024

TextGenSHAP: Scalable Post-Hoc Explanations in Text Generation with Long Documents

James Enouen, Hootan Nakhost, Sayna Ebrahimi, Sercan Arik, Yan Liu, Tomas Pfister
ACL 2024findings

Large language models (LLMs) have attracted great interest in many real-world applications; however, their “black-box” nature necessitates scalable and faithful explanations. Shapley values have matured as an explainability method for deep learning, but extending them to LLMs is difficult due to lon…

Cited by 5Source ↗PDF ↗Scholar ↗
2023

Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs

Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan O Arik, Tomas Pfister, Somesh Jha
EMNLP 2023long findings

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 decision-making scenarios is still limited due to the potential for errors. *Selective prediction* is a technique that can…

Cited by 0Source ↗Scholar ↗
2023

Beyond Invariance: Test-Time Label-Shift Adaptation for Addressing "Spurious" Correlations

Qingyao Sun, Kevin Patrick Murphy, Sayna Ebrahimi, Alexander D'Amour
NeurIPS 2023poster

Changes in the data distribution at test time can have deleterious effects on the performance of predictive models $p(y|x)$. We consider situations where there are additional meta-data labels (such as group labels), denoted by $z$, that can account for such changes in the distribution. In particular…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2022

Differentiable Gradient Sampling for Learning Implicit 3D Scene Reconstructions from a Single Image

Shizhan Zhu, Sayna Ebrahimi, Angjoo Kanazawa, Trevor Darrell
ICLR 2022poster

Implicit shape models are promising 3D representations for modeling arbitrary locations, with Signed Distance Functions (SDFs) particularly suitable for clear mesh surface reconstruction. Existing approaches for single object reconstruction impose supervision signals based on the loss of the signed…

Cited by 4Source ↗PDF ↗Scholar ↗
2022

DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning

Zifeng Wang, Zizhao Zhang, Sayna Ebrahimi, Ruoxi Sun, Han Zhang, Chen-Yu Lee +5
ECCV 2022poster

"Continual learning aims at enabling a single model to learn a sequence of tasks without catastrophic forgetting. Top-performing methods usually require a rehearsal buffer to store past pristine examples for experience replay, which, however, limits their practical values due to privacy and memory c…

Cited by 646Source ↗PDF ↗code ↗Scholar ↗
2021

Predicting With Confidence on Unseen Distributions

Devin Guillory, Vaishaal Shankar, Sayna Ebrahimi, Trevor Darrell, Ludwig Schmidt
ICCV 2021poster

Recent work has shown that the accuracy of machine learning models can vary substantially when evaluated on a distribution that even slightly differs from that of the training data. As a result, predicting model performance on previously unseen distributions without access to labeled data is an impo…

Cited by 164PDF ↗Scholar ↗
2021

Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting

Sayna Ebrahimi, Suzanne Petryk, Akash Gokul, William Gan, Joseph E. Gonzalez, Marcus Rohrbach +1
ICLR 2021poster

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 in the form of a replay buffer can reduce performance degradation on prior tasks. We hypothesize that forgetting can be…

Cited by 65Source ↗PDF ↗code ↗Scholar ↗
2020

Adversarial Continual Learning

Sayna Ebrahimi, Franziska Meier, Roberto Calandra, Trevor Darrell, Marcus Rohrbach
ECCV 2020poster

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 structure while containing some task-specific properties. We show that shared features are significantly less prone to for…

Cited by 273Source ↗PDF ↗code ↗Scholar ↗
2020

Uncertainty-guided Continual Learning with Bayesian Neural Networks

Sayna Ebrahimi, Mohamed Elhoseiny, Trevor Darrell, Marcus Rohrbach
ICLR 2020poster

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 model has a fixed capacity. Current regularization-based continual learning algorithms need an external representation a…

Cited by 266Source ↗code ↗Scholar ↗
2019

Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders

Edgar Schonfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell, Zeynep Akata
CVPR 2019poster

Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space. As labeled images are expensive, one direction is to augment the dataset by generating either images or image features. However, the former misses fine-grained…

Cited by 834PDF ↗code ↗Scholar ↗