中文
相关论文

相关论文: PRISM: Position-encoded Regressive Inverse Spectra…

200 篇论文

Designing protein sequences that fold into a target 3-D structure, termed as the inverse folding problem, is central to protein engineering. However, it remains challenging due to the vast sequence space and the importance of local…

定量方法 · 定量生物学 2026-03-17 Sazan Mahbub , Souvik Kundu , Eric P. Xing

Recent advances in photonic inverse design have demonstrated the ability to automatically synthesize compact, high-performance photonic components that surpass conventional, hand-designed structures, offering a promising path toward…

光学 · 物理学 2026-02-18 Hongjian Zhou , Haoyu Yang , Nicholas Gangi , Tianle Xu , Rena Huang , Jiaqi Gu

Diffusion models are now commonly used to solve inverse problems in computational imaging. However, most diffusion-based inverse solvers require complete knowledge of the forward operator to be used. In this work, we introduce a novel…

图像与视频处理 · 电气工程与系统科学 2025-09-22 Yuanyun Hu , Evan Bell , Guijin Wang , Yu Sun

We present PRISM, a unified framework that enables multiple image generation and editing tasks in a single foundational model. Starting from a pre-trained text-to-image diffusion model, PRISM proposes an effective fine-tuning strategy to…

图形学 · 计算机科学 2025-05-15 Alara Dirik , Tuanfeng Wang , Duygu Ceylan , Stefanos Zafeiriou , Anna Frühstück

Scientific and environmental imagery often suffer from complex mixtures of noise related to the sensor and the environment. Existing restoration methods typically remove one degradation at a time, leading to cascading artifacts,…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Rupa Kurinchi-Vendhan , Pratyusha Sharma , Antonio Torralba , Sara Beery

Robotic imitation learning typically requires models that capture multimodal action distributions while operating at real-time control rates and accommodating multiple sensing modalities. Although recent generative approaches such as…

机器人学 · 计算机科学 2026-02-03 Amisha Bhaskar , Pratap Tokekar , Stefano Di Cairano , Alexander Schperberg

Video dataset condensation aims to reduce the immense computational cost of video processing. However, it faces a fundamental challenge regarding the inseparable interdependence between spatial appearance and temporal dynamics. Prior work…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Jaehyun Choi , Jiwan Hur , Gyojin Han , Jaemyung Yu , Junmo Kim

Foundation models (FMs) have achieved remarkable success across a wide range of applications, from image classification to natural langurage processing, but pose significant challenges for deployment at edge. This has sparked growing…

机器学习 · 计算机科学 2025-07-17 Muhammad Azlan Qazi , Alexandros Iosifidis , Qi Zhang

We propose PRISM, an optimizer that enhances first-order spectral descent methods like Muon with partial second-order information. It constructs an efficient, low-rank quasi-second-order preconditioner via innovation-augmented polar…

机器学习 · 计算机科学 2026-02-04 Yujie Yang

Generative sequence modeling faces a fundamental tension between the expressivity of Transformers and the efficiency of linear sequence models. Existing efficient architectures are theoretically bounded by shallow, single-step linear…

机器学习 · 计算机科学 2026-02-13 Jie Jiang , Ke Cheng , Xin Xu , Mengyang Pang , Tianhao Lu , Jiaheng Li , Yue Liu , Yuan Wang , Jun Zhang , Huan Yu , Zhouchen Lin

Scene graphs have emerged as accurate descriptive priors for image generation and manipulation tasks, however, their complexity and diversity of the shapes and relations of objects in data make it challenging to incorporate them into the…

机器学习 · 计算机科学 2023-11-07 Pavel Jahoda , Azade Farshad , Yousef Yeganeh , Ehsan Adeli , Nassir Navab

Learned progressive image compression is gaining momentum as it allows improved image reconstruction as more bits are decoded at the receiver. We propose a progressive image compression method in which an image is first represented as a…

计算机视觉与模式识别 · 计算机科学 2025-01-13 Alberto Presta , Enzo Tartaglione , Attilio Fiandrotti , Marco Grangetto , Pamela Cosman

Simulation plays a central role in scientific discovery. In many applications, the bottleneck is no longer running a simulator; it is choosing among large families of plausible simulators, each corresponding to different forward…

We introduce Projection-based Reduction of Implicit Spurious bias in vision-language Models (PRISM), a new data-free and task-agnostic solution for bias mitigation in VLMs like CLIP. VLMs often inherit and amplify biases in their training…

计算机视觉与模式识别 · 计算机科学 2025-07-15 Mahdiyar Molahasani , Azadeh Motamedi , Michael Greenspan , Il-Min Kim , Ali Etemad

We propose PRISM, a novel framework designed to overcome the limitations of 2D-based Preference-Based Reinforcement Learning (PBRL) by unifying 3D point cloud modeling and future-aware preference refinement. At its core, PRISM adopts a 3D…

计算与语言 · 计算机科学 2025-03-20 Yirong Sun , Yanjun Chen

This paper explores improvements to the masked image modeling (MIM) paradigm. The MIM paradigm enables the model to learn the main object features of the image by masking the input image and predicting the masked part by the unmasked part.…

计算机视觉与模式识别 · 计算机科学 2022-05-24 Jiawei Mao , Xuesong Yin , Yuanqi Chang , Honggu Zhou

Large Language Models (LLMs), constrained by their auto-regressive nature, suffer from slow decoding. Speculative decoding methods have emerged as a promising solution to accelerate LLM decoding, attracting attention from both systems and…

人工智能 · 计算机科学 2026-02-03 Xuliang Wang , Yuetao Chen , Maochan Zhen , Fang Liu , Xinzhou Zheng , Xingwu Liu , Hong Xu , Ming Li

Developing reliable and generalizable deep learning systems for medical imaging faces significant obstacles due to spurious correlations, data imbalances, and limited text annotations in datasets. Addressing these challenges requires…

计算机视觉与模式识别 · 计算机科学 2025-07-23 Amar Kumar , Anita Kriz , Mohammad Havaei , Tal Arbel

Optical multilayer thin film structures have been widely used in numerous photonic applications. However, existing inverse design methods have many drawbacks because they either fail to quickly adapt to different design targets, or are…

光学 · 物理学 2024-04-05 Taigao Ma , Haozhu Wang , L. Jay Guo

Deep sequence models typically degrade in accuracy when test sequences significantly exceed their training lengths, yet many critical tasks--such as algorithmic reasoning, multi-step arithmetic, and compositional generalization--require…

机器学习 · 计算机科学 2025-12-24 Philip Heejun Lee
‹ 上一页 1 2 3 10 下一页 ›