137 citations · 233 across the 26 of their papers we have counts for
31 papers
Query-adaptive Recurrent Tokenization
Bavesh Balaji, Pranav Gopinath, Pouya Sadeghi +1
Visual information worth extracting from an image and the token budget it warrants depend on the text query. Yet modern vision and vision-language models largely encode images inde…
MaskMerge: Structure-aware Token Merging for Efficient Instance Segmentation
Bavesh Balaji, Letian Jiang, Alexander Wong +2
Token merging improves the efficiency of Vision Transformers by combining redundant tokens, but existing methods largely rely on feature similarity to determine which tokens to mer…
Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation
Utku Cicek, Mahip Singh, Ziyao Shang +5
While foundation models and vision transformers (ViTs) have redefined visual representations, current active learning (AL) strategies for these backbones largely operate at the pat…
Clean: Second-order LLM Training at Linear Memory Cost via Nystr{ö}m Sketching
Beheshteh T. Rakhshan, Sahar Rajabi, Maziar Sargordi Shikai Fang +4
Training large language models (LLMs) entails a fundamental trade-off: memory-efficient optimizers such as Adam discard cross-parameter curvature, whereas full-curvature methods su…
How Far Can INRs Go? Cross-Domain Parameter-efficient INR-Based Semantic Segmentation for Brain MRI
Ziyao Shang, Pouya Sadeghi, Letian Jiang +2
Biomedical image segmentation is central to medical image analysis, but practical deployment often faces limited annotations, memory constraints, and cross-site distribution shifts…
PinPoint: Prompting with Informative Interior Points
Pouya Sadeghi, Shawn He, Pedro Pablo Guerrero Vela +3
Modern referring image segmentation pipelines couple a vision-language model (VLM) for grounding with a promptable segmenter such as the Segment Anything Model (SAM) for mask gener…
Zero-Shot Object Re-Identification in Egocentric Kitchen Videos via Multi-Stage SAM3 Feature Fusion
Dmytro Klepachevskyi, Alexander Wong, Sirisha Rambhatla +1
Object re-identification (ReID) in egocentric kitchen videos is challenging due to rapid viewpoint changes, frequent occlusions, cluttered scenes, and large intra-class appearance…
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
Saad Hossain, Tom Tseng, Punya Syon Pandey +8
As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, be…
Avatar4D: Synthesizing Domain-Specific 4D Humans for Real-World Pose Estimation
Jerrin Bright, Zhibo Wang, Dmytro Klepachevskyi +4
We present Avatar4D, a real-world transferable pipeline for generating customizable synthetic human motion datasets tailored to domain-specific applications. Unlike prior works, wh…
Geometrically Principled Randomized Optimization for Efficient LLM Training
Sahar Rajabi, Nayeema Nonta, Sirisha Rambhatla
Low-rank gradient optimization for large language models is currently divided into two categories: structured methods that rigorously identify subspaces, and randomized approaches…
Human vs. LLM-Based Thematic Analysis for Digital Mental Health Research: Proof-of-Concept Comparative Study
Karisa Parkington, Bazen G. Teferra, Marianne Rouleau-Tang +12
Thematic analysis provides valuable insights into participants' experiences through coding and theme development, but its resource-intensive nature limits its use in large healthca…
Gen4D: Synthesizing Humans and Scenes in the Wild
Jerrin Bright, Zhibo Wang, Yuhao Chen +3
Lack of input data for in-the-wild activities often results in low performance across various computer vision tasks. This challenge is particularly pronounced in uncommon human-cen…
SafeTuneBed: A Toolkit for Benchmarking LLM Safety Alignment in Fine-Tuning
Saad Hossain, Samanvay Vajpayee, Sirisha Rambhatla
As large language models (LLMs) become ubiquitous, parameter-efficient fine-tuning methods and safety-first defenses have proliferated rapidly. However, the number of approaches an…
Estimating Quality in Therapeutic Conversations: A Multi-Dimensional Natural Language Processing Framework
Alice Rueda, Argyrios Perivolaris, Niloy Roy +15
Engagement between client and therapist is a critical determinant of therapeutic success. We propose a multi-dimensional natural language processing (NLP) framework that objectivel…
Understanding LLM Scientific Reasoning through Promptings and Model's Explanation on the Answers
Alice Rueda, Mohammed S. Hassan, Argyrios Perivolaris +9
Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding, reasoning, and problem-solving across various domains. However, their abil…
LOCATEdit: Graph Laplacian Optimized Cross Attention for Localized Text-Guided Image Editing
Achint Soni, Meet Soni, Sirisha Rambhatla
Text-guided image editing aims to modify specific regions of an image according to natural language instructions while maintaining the general structure and the background fidelity…
LangDA: Building Context-Awareness via Language for Domain Adaptive Semantic Segmentation
Chang Liu, Bavesh Balaji, Saad Hossain +5
Unsupervised domain adaptation for semantic segmentation (DASS) aims to transfer knowledge from a label-rich source domain to a target domain with no labels. Two key approaches in…
SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training
Sahar Rajabi, Nayeema Nonta, Sirisha Rambhatla
Training large language models (LLMs) is highly resource-intensive due to their massive number of parameters and the overhead of optimizer states. While recent work has aimed to re…
Domain-Guided Masked Autoencoders for Unique Player Identification
Bavesh Balaji, Jerrin Bright, Sirisha Rambhatla +4
Unique player identification is a fundamental module in vision-driven sports analytics. Identifying players from broadcast videos can aid with various downstream tasks such as play…
Medical Misinformation in AI-Assisted Self-Diagnosis: Development of a Method (EvalPrompt) for Analyzing Large Language Models
Troy Zada, Natalie Tam, Francois Barnard +3
Rapid integration of large language models (LLMs) in health care is sparking global discussion about their potential to revolutionize health care quality and accessibility. At a ti…
Is Generative Modeling-based Stylization Necessary for Domain Adaptation in Regression Tasks?
Jinman Park, Francois Barnard, Saad Hossain +2
Unsupervised domain adaptation (UDA) aims to bridge the gap between source and target domains in the absence of target domain labels using two main techniques: input-level alignmen…
Domain Generalization for Domain-Linked Classes
Kimathi Kaai, Saad Hossain, Sirisha Rambhatla
Domain generalization (DG) focuses on transferring domain-invariant knowledge from multiple source domains (available at train time) to an, a priori, unseen target domain(s). This…
Building Spatio-temporal Transformers for Egocentric 3D Pose Estimation
Jinman Park, Kimathi Kaai, Saad Hossain +3
Egocentric 3D human pose estimation (HPE) from images is challenging due to severe self-occlusions and strong distortion introduced by the fish-eye view from the head mounted camer…
Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling
Chuizheng Meng, Sirisha Rambhatla, Yan Liu
Vast amount of data generated from networks of sensors, wearables, and the Internet of Things (IoT) devices underscores the need for advanced modeling techniques that leverage the…