About

Octavia Camps is a Professor in the Electrical and Computer Engineering Department at Northeastern University. She received her B.S. degrees in computer science and electrical engineering from the Universidad de la Republica in Montevideo, Uruguay, and her M.S. and Ph.D. degrees in electrical engineering from the University of Washington. Her research interests include robust computer vision, image processing, and machine learning. She has previously been a faculty member at The Pennsylvania State University from 1991 to 2006, and has held visiting positions at the California Institute of Technology and the University of Southern California. Her work focuses on advancing the fields of computer vision, artificial intelligence, and related algorithms, contributing to various research projects and publications in these areas.

Research topics

• Artificial Intelligence
• Computer Science
• Machine Learning
• Computer vision

Selected publications

• HIERAMP: Coarse-to-Fine Autoregressive Amplification for Generative Dataset Distillation

  arXiv (Cornell University) · 2026-03-06

  articleOpen access

  Dataset distillation often prioritizes global semantic proximity when creating small surrogate datasets for original large-scale ones. However, object semantics are inherently hierarchical. For example, the position and appearance of a bird's eyes are constrained by the outline of its head. Global proximity alone fails to capture how object-relevant structures at different levels support recognition. In this work, we investigate the contributions of hierarchical semantics to effective distilled data. We leverage the vision autoregressive (VAR) model whose coarse-to-fine generation mirrors this hierarchy and propose HIERAMP to amplify semantics at different levels. At each VAR scale, we inject class tokens that dynamically identify salient regions and use their induced maps to guide amplification at that scale. This adds only marginal inference cost while steering synthesis toward discriminative parts and structures. Empirically, we find that semantic amplification leads to more diverse token choices in constructing coarse-scale object layouts. Conversely, at fine scales, the amplification concentrates token usage, increasing focus on object-related details. Across popular dataset distillation benchmarks, HIERAMP consistently improves validation performance without explicitly optimizing global proximity, demonstrating the importance of semantic amplification for effective dataset distillation.

  PublisherOA PDF

• HIERAMP: Coarse-to-Fine Autoregressive Amplification for Generative Dataset Distillation

  Open MIND · 2026-03-06

  preprint

  Dataset distillation often prioritizes global semantic proximity when creating small surrogate datasets for original large-scale ones. However, object semantics are inherently hierarchical. For example, the position and appearance of a bird's eyes are constrained by the outline of its head. Global proximity alone fails to capture how object-relevant structures at different levels support recognition. In this work, we investigate the contributions of hierarchical semantics to effective distilled data. We leverage the vision autoregressive (VAR) model whose coarse-to-fine generation mirrors this hierarchy and propose HIERAMP to amplify semantics at different levels. At each VAR scale, we inject class tokens that dynamically identify salient regions and use their induced maps to guide amplification at that scale. This adds only marginal inference cost while steering synthesis toward discriminative parts and structures. Empirically, we find that semantic amplification leads to more diverse token choices in constructing coarse-scale object layouts. Conversely, at fine scales, the amplification concentrates token usage, increasing focus on object-related details. Across popular dataset distillation benchmarks, HIERAMP consistently improves validation performance without explicitly optimizing global proximity, demonstrating the importance of semantic amplification for effective dataset distillation.

  DOI

• Grounding Multimodal Large Language Models with Quantitative Skin Attributes: A Retrieval Study

  ArXiv.org · 2025-08-27

  preprintOpen access

  Artificial Intelligence models have demonstrated significant success in diagnosing skin diseases, including cancer, showing the potential to assist clinicians in their analysis. However, the interpretability of model predictions must be significantly improved before they can be used in practice. To this end, we explore the combination of two promising approaches: Multimodal Large Language Models (MLLMs) and quantitative attribute usage. MLLMs offer a potential avenue for increased interpretability, providing reasoning for diagnosis in natural language through an interactive format. Separately, a number of quantitative attributes that are related to lesion appearance (e.g., lesion area) have recently been found predictive of malignancy with high accuracy. Predictions grounded as a function of such concepts have the potential for improved interpretability. We provide evidence that MLLM embedding spaces can be grounded in such attributes, through fine-tuning to predict their values from images. Concretely, we evaluate this grounding in the embedding space through an attribute-specific content-based image retrieval case study using the SLICE-3D dataset.

  PublisherOA PDFDOI

• 3D-HGS: 3D Half-Gaussian Splatting^*

  2025-06-10 · 7 citations

  articleSenior author

  Photo-realistic image rendering from 3D scene reconstruction has advanced significantly with neural rendering techniques. Among these, 3D Gaussian Splatting (3D-GS) outperforms Neural Radiance Fields (NeRFs) in quality and speed but struggles with shape and color discontinuities. We propose 3D Half-Gaussian (3D-HGS) kernels as a plug-and-play solution to address these limitations. Our experiments show that 3D-HGS enhances existing 3D-GS methods, achieving state-of-the-art rendering quality without compromising speed. More demos and code are available at https://lihaolin88.github.io/CVPR-2025-3DHGS.

  PublisherDOI

• TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection

  ArXiv.org · 2025-04-03

  preprintOpen accessSenior author

  We aim to solve unsupervised anomaly detection in a practical challenging environment where the normal dataset is both contaminated with defective regions and its product class distribution is tailed but unknown. We observe that existing models suffer from tail-versus-noise trade-off where if a model is robust against pixel noise, then its performance deteriorates on tail class samples, and vice versa. To mitigate the issue, we handle the tail class and noise samples independently. To this end, we propose TailSampler, a novel class size predictor that estimates the class cardinality of samples based on a symmetric assumption on the class-wise distribution of embedding similarities. TailSampler can be utilized to sample the tail class samples exclusively, allowing to handle them separately. Based on these facets, we build a memory-based anomaly detection model TailedCore, whose memory both well captures tail class information and is noise-robust. We extensively validate the effectiveness of TailedCore on the unsupervised long-tail noisy anomaly detection setting, and show that TailedCore outperforms the state-of-the-art in most settings.

  PublisherOA PDFDOI

• REEF: Relevance-Aware and Efficient LLM Adapter for Video Understanding

  2025-06-11

  articleSenior author

  Integrating vision models into large language models (LLMs) has sparked significant interest in creating visionlanguage foundation models, especially for video understanding. Recent methods often utilize memory banks to handle untrimmed videos for video-level understanding. However, they typically compress visual memory using similarity-based greedy approaches, which can overlook the contextual importance of individual tokens. To address this, we introduce an efficient LLM adapter designed for video-level understanding of untrimmed videos that prioritizes the contextual relevance of spatio-temporal tokens. Our framework leverages scorer networks to selectively compress the visual memory bank and filter spatial tokens based on relevance, using a differentiable Top-K operator for end-to-end training. Across three key video-level understanding tasks- untrimmed video classification, video question answering, and video captioning-our method achieves competitive or superior results on four large-scale datasets while reducing computational overhead by up to 34%. Code is available at: https://github.com/EW-iC/REEF-VideoLLM/.

  PublisherDOI

• Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention

  ArXiv.org · 2025-02-03

  preprintOpen access

  State-space models (SSMs) have recently emerged as a compelling alternative to Transformers for sequence modeling tasks. This paper presents a theoretical generalization analysis of selective SSMs, the core architectural component behind the Mamba model. We derive a novel covering number-based generalization bound for selective SSMs, building upon recent theoretical advances in the analysis of Transformer models. Using this result, we analyze how the spectral abscissa of the continuous-time state matrix influences the model's stability during training and its ability to generalize across sequence lengths. We empirically validate our findings on a synthetic majority task, the IMDb sentiment classification benchmark, and the ListOps task, demonstrating how our theoretical insights translate into practical model behavior.

  PublisherOA PDFDOI

• Real-Time Adaptive Motion Planning via Point Cloud-Guided, Energy-Based Diffusion and Potential Fields

  IEEE Robotics and Automation Letters · 2025-07-23

  articleOpen access

  Motivated by the problem of pursuit-evasion, we present a motion planning framework that combines energy-based diffusion models with artificial potential fields for robust real time trajectory generation in complex environments. Our approach processes obstacle information directly from point clouds, enabling efficient planning without requiring complete geometric representations. The framework employs classifier-free guidance training and integrates local potential fields during sampling to enhance obstacle avoidance. In dynamic scenarios, the system generates initial trajectories using the diffusion model and continuously refines them through potential field-based adaptation, demonstrating effective performance in pursuit-evasion scenarios with partial pursuer observability.

  PublisherOA PDFDOI

• TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection

  2025-06-10

  articleSenior author

  We aim to solve unsupervised anomaly detection in a practical challenging environment where the normal dataset is both contaminated with defective regions and its product class distribution is tailed but unknown. We observe that existing models suffer from tail-versus-noise trade-off where if a model is robust against pixel noise, then its performance deteriorates on tail class samples, and vice versa. To mitigate the issue, we handle the tail class and noise samples independently. To this end, we propose TailSampler, a novel class size predictor that estimates the class cardinality of samples based on a symmetric assumption on the class-wise distribution of embedding similarities. TailSampler can be utilized to sample the tail class samples exclusively, allowing to handle them separately. Based on these facets, we build a memory-based anomaly detection model TailedCore, whose memory both well captures tail class information and is noise-robust. We extensively validate the effectiveness of TailedCore on the unsupervised long-tail noisy anomaly detection setting, and show that TailedCore outperforms the state-of-the-art in most settings. Code is available in TailedCore

  PublisherDOI

• REEF: Relevance-Aware and Efficient LLM Adapter for Video Understanding

  ArXiv.org · 2025-04-07

  preprintOpen accessSenior author

  Integrating vision models into large language models (LLMs) has sparked significant interest in creating vision-language foundation models, especially for video understanding. Recent methods often utilize memory banks to handle untrimmed videos for video-level understanding. However, they typically compress visual memory using similarity-based greedy approaches, which can overlook the contextual importance of individual tokens. To address this, we introduce an efficient LLM adapter designed for video-level understanding of untrimmed videos that prioritizes the contextual relevance of spatio-temporal tokens. Our framework leverages scorer networks to selectively compress the visual memory bank and filter spatial tokens based on relevance, using a differentiable Top-K operator for end-to-end training. Across three key video-level understanding tasks$\unicode{x2013}$ untrimmed video classification, video question answering, and video captioning$\unicode{x2013}$our method achieves competitive or superior results on four large-scale datasets while reducing computational overhead by up to 34%. The code will be available soon on GitHub.

  PublisherOA PDFDOI

Recent grants

• ITR: Robust Ad-Hoc Active Vision Networks and Applications

  NSF · $211k · 2006–2008

• RI: Small: Dynamic Invariants for Video Scenes Understanding

  NSF · $455k · 2013–2018

• Systems Theoretic Methods for Dynamic Problems in Computer Vision

  NSF · $400k · 2007–2012

• RI:Small: Dynamic and Statistical Based Invariants on Manifolds for Video Analysis

  NSF · $500k · 2018–2023

Frequent coauthors

• Mario Sznaier

  103 shared

• Rangachar Kasturi

  University of South Florida

  18 shared

• Mengran Gou

  15 shared

• Richard J. Radke

  Rensselaer Polytechnic Institute

  10 shared

• Srikrishna Karanam

  9 shared

• Sandesh Ghimire

  9 shared

• Jennifer Dy

  Northeastern University

  9 shared

• Constantino Lagoa

  8 shared

Labs

• Octavia CampsPI

Awards & honors

• Best Paper Award at the 2018 International Conference on Dis…