English
Related papers

Related papers: Architecture-Sensitive Supervised Fine-Tuning for …

200 papers

Randomized smoothing is the primary certified robustness method for accessing the robustness of deep learning models to adversarial perturbations in the l2-norm, by adding isotropic Gaussian noise to the input image and returning the…

Machine Learning · Computer Science 2024-04-09 Chengyan Fu , Wenjie Wang

Recent advancements in large language models have demonstrated enhanced capabilities in visual reasoning tasks by employing additional encoders for aligning different modalities. While the Q-Former has been widely used as a general encoder…

Computation and Language · Computer Science 2024-10-15 Sungkyung Kim , Adam Lee , Junyoung Park , Andrew Chung , Jusang Oh , Jay-Yoon Lee

In this work, we present an in-depth and systematic analysis using tools such as local interpretable model-agnostic explanations (LIME) (arXiv:1602.04938) and divergence measures to analyze what changes lead to improvement in performance in…

Image and Video Processing · Electrical Eng. & Systems 2021-03-18 Sarah Walker , Joshua Peeples , Jeff Dale , James Keller , Alina Zare

Two questions regarding practitioners' use of patent embeddings arise: (i) Does one fine-tuning recipe suffice for all downstream applications? (ii) Is fine-tuning on one patent landscape sufficient for downstream application on other…

Information Retrieval · Computer Science 2026-05-27 Amirhossein Yousefiramandi , Ciaran Cooney

Segment Anything Model (SAM) is an advanced foundational model for image segmentation, which is gradually being applied to remote sensing images (RSIs). Due to the domain gap between RSIs and natural images, traditional methods typically…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Nanqing Liu , Xun Xu , Yongyi Su , Haojie Zhang , Heng-Chao Li

Few-Shot Action Recognition (FS-AR) has shown promising results but is often limited by a closed-set assumption that fails in real-world open-set scenarios. While Few-Shot Open-Set (FSOS) recognition is well-established for images, its…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Stefano Berti , Giulia Pasquale , Lorenzo Natale

Accurate multi-sensor calibration is essential for deploying robust perception systems in applications such as autonomous driving and intelligent transportation. Existing LiDAR-camera calibration methods often rely on manually placed…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Lei Cheng , Lihao Guo , Tianya Zhang , Tam Bang , Austin Harris , Mustafa Hajij , Mina Sartipi , Siyang Cao

Due to the scarcity of annotated data and the substantial computational costs of model, conventional tuning methods in medical image segmentation face critical challenges. Current approaches to adapting pretrained models, including…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Chenlin Xu , Lei Zhang , Lituan Wang , Xinyu Pu , Pengfei Ma , Guangwu Qian , Zizhou Wang , Yan Wang

In this work, we address the TrackRAD2025 challenge of real-time tumor tracking in cine-MRI sequences of the thoracic and abdominal regions under strong data scarcity constraints. Two complementary strategies were explored: (i) unsupervised…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Valentin Boussot , Cédric Hémon , Jean-Claude Nunes , Jean-Louis Dillenseger

Open-world deployment requires models to recognize both known categories and remain reliable when novel classes appear. We present a unified experimental study spanning open-set recognition (OSR) and few-shot class-incremental learning…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Ayush Vaibhav Bhatti , Deniz Karakay , Debottama Das , Nilotpal Rajbongshi , Yuito Sugimoto

Reinforcement learning (RL) is widely used for humanoid control, with on-policy methods such as Proximal Policy Optimization (PPO) enabling robust training via large-scale parallel simulation and, in some cases, zero-shot deployment to real…

Robotics · Computer Science 2026-02-24 Weidong Huang , Zhehan Li , Hangxin Liu , Biao Hou , Yao Su , Jingwen Zhang

We propose a UNet-based foundation model and its self-supervised learning method to address two key challenges: 1) lack of qualified annotated analog layout data, and 2) excessive variety in analog layout design tasks. For self-supervised…

Signal Processing · Electrical Eng. & Systems 2025-11-25 Sungyu Jeong , Won Joon Choi , Junung Choi , Anik Biswas , Byungsub Kim

Mitigating explicit and implicit biases in Large Language Models (LLMs) has become a critical focus in the field of natural language processing. However, many current methodologies evaluate scenarios in isolation, without considering the…

Computation and Language · Computer Science 2025-02-04 Robert Morabito , Sangmitra Madhusudan , Tyler McDonald , Ali Emami

Vision foundation models have achieved remarkable progress across various image analysis tasks. In the image segmentation task, foundation models like the Segment Anything Model (SAM) enable generalizable zero-shot segmentation through…

Computer Vision and Pattern Recognition · Computer Science 2025-01-17 Xingxin He , Yifan Hu , Zhaoye Zhou , Mohamed Jarraya , Fang Liu

Image-text training like CLIP has dominated the pretraining of vision foundation models in recent years. Subsequent efforts have been made to introduce region-level visual learning into CLIP's pretraining but face scalability challenges due…

Computer Vision and Pattern Recognition · Computer Science 2024-04-12 Xiaohu Jiang , Yixiao Ge , Yuying Ge , Dachuan Shi , Chun Yuan , Ying Shan

Pedestrian intention prediction is essential for autonomous driving in complex urban environments. Conventional approaches depend on supervised learning over frame sequences and require extensive retraining to adapt to new scenarios. Here,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Pallavi Zambare , Venkata Nikhil Thanikella , Ying Liu

Zero-shot and prompt-based models have excelled at visual reasoning tasks by leveraging large-scale natural image corpora, but they often fail on sparse and domain-specific scientific image data. We introduce Zenesis, a no-code interactive…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Shubhabrata Mukherjee , Jack Lang , Obeen Kwon , Iryna Zenyuk , Valerie Brogden , Adam Weber , Daniela Ushizima

We present a new paradigm for fine-tuning large-scale visionlanguage pre-trained models on downstream task, dubbed Prompt Regularization (ProReg). Different from traditional fine-tuning which easily overfits to the downstream task data,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Beier Zhu , Yulei Niu , Saeil Lee , Minhoe Hur , Hanwang Zhang

Aspect sentiment quad prediction (ASQP) facilitates a detailed understanding of opinions expressed in a text by identifying the opinion term, aspect term, aspect category and sentiment polarity for each opinion. However, annotating a full…

Computation and Language · Computer Science 2025-05-30 Nils Constantin Hellwig , Jakob Fehle , Udo Kruschwitz , Christian Wolff

We probe OpenAI's open-weights 20-billion-parameter model gpt-oss-20b to study how sociopragmatic framing, language choice, and instruction hierarchy affect refusal behavior. Across 80 seeded iterations per scenario, we test several harm…

Computation and Language · Computer Science 2025-10-03 Nils Durner