paper-with-me

Papers model

“model” 태그가 달린 논문 5,434편 · 필터 해제

Making Language Model a Hierarchical Classifier and Generator

2025-07-17 · Yihong Wang, Zhonglin Jiang, Ningyuan Xi, Yue Zhao 외

Decoder-only language models, such as GPT and LLaMA, generally decode on the last layer. Motivated by human's hierarchical thinking capability, we propose that a hierarchical decoder architecture could be built with diff…

DecoderLanguage ModelingLanguage Modellingmodel+3

RegCL: Continual Adaptation of Segment Anything Model via Model Merging

2025-07-16 · Yuan-Chen Shu, Zhiwei Lin, Yongtao Wang

To address the performance limitations of the Segment Anything Model (SAM) in specific domains, existing works primarily adopt adapter-based one-step adaptation paradigms. However, some of these methods are specific deve…

Continual Learningmodel

Implementing Adaptations for Vision AutoRegressive Model

2025-07-15 · Kaif Shaikh, Antoni Kowalczuk, Franziska Boenisch, Adam Dziedzic

Vision AutoRegressive model (VAR) was recently introduced as an alternative to Diffusion Models (DMs) in image generation domain. In this work we focus on its adaptations, which aim to fine-tune pre-trained models to per…

Image Generationmodel

Graph World Model

2025-07-14 · Tao Feng, Yexin Wu, GuanYu Lin, Jiaxuan You

World models (WMs) demonstrate strong capabilities in prediction, generation, and planning tasks. Existing WMs primarily focus on unstructured data and cannot leverage the ubiquitous structured data, often represented as…

Graph LearningmodelRetrieval-augmented Generation

Compress Any Segment Anything Model (SAM)

2025-07-11 · Juntong Fan, Zhiwei Hao, Jianqiang Shen, Shang-Ling Jui 외

Due to the excellent performance in yielding high-quality, zero-shot segmentation, Segment Anything Model (SAM) and its variants have been widely applied in diverse scenarios such as healthcare and intelligent manufactur…

modelQuantizationZero Shot Segmentation

Model Parallelism With Subnetwork Data Parallelism

2025-07-11 · Vaibhav Singh, Zafir Khalid, Edouard Oyallon, Eugene Belilovsky

Distributed pre-training of large models at scale often imposes heavy memory demands on individual nodes and incurs significant intra-node communication costs. We propose a novel alternative approach that reduces the mem…

AttributeFederated Learningmodel

Temporal Information Retrieval via Time-Specifier Model Merging

2025-07-09 · SeungYoon Han, Taeho Hwang, Sukmin Cho, Soyeong Jeong 외

The rapid expansion of digital information and knowledge across structured and unstructured sources has heightened the importance of Information Retrieval (IR). While dense retrieval methods have substantially improved s…

Information RetrievalmodelRetrieval

A Wireless Foundation Model for Multi-Task Prediction

2025-07-08 · Yucheng Sheng, Jiacheng Wang, Xingyu Zhou, Le Liang 외

With the growing complexity and dynamics of the mobile communication networks, accurately predicting key system parameters, such as channel state information (CSI), user location, and network traffic, has become essentia…

modelPredictionPrediction Intervals

LRM-1B: Towards Large Routing Model

2025-07-04 · Han Li, Fei Liu, Zhenkun Wang, Qingfu Zhang

Vehicle routing problems (VRPs) are central to combinatorial optimization with significant practical implications. Recent advancements in neural combinatorial optimization (NCO) have demonstrated promising results by lev…

Combinatorial Optimizationmodel

Autoadaptive Medical Segment Anything Model

2025-07-02 · Tyler Ward, Meredith K. Owen, O'Kira Coleman, Brian Noehren 외

Medical image segmentation is a key task in the imaging workflow, influencing many image-based decisions. Traditional, fully-supervised segmentation models rely on large amounts of labeled training data, typically obtain…

Image SegmentationMedical Image SegmentationmodelSegmentation+1

Epona: Autoregressive Diffusion World Model for Autonomous Driving

2025-06-30 · Kaiwen Zhang, Zhenyu Tang, Xiaotao Hu, Xingang Pan 외

Diffusion models have demonstrated exceptional visual quality in video generation, making them promising for autonomous driving world modeling. However, existing video diffusion-based world models struggle with flexible-…

Autonomous DrivingmodelMotion PlanningNavSim+3

RoboScape: Physics-informed Embodied World Model

2025-06-29 · Yu Shang, Xin Zhang, Yinzhou Tang, Lei Jin 외

World models have become indispensable tools for embodied intelligence, serving as powerful simulators capable of generating realistic robotic videos while addressing critical data scarcity challenges. However, current e…

3D geometryDepth EstimationDepth Predictionmodel+1

WorldVLA: Towards Autoregressive Action World Model

2025-06-26 · Jun Cen, Chaohui Yu, Hangjie Yuan, Yuming Jiang 외

We present WorldVLA, an autoregressive action world model that unifies action and image understanding and generation. Our WorldVLA intergrates Vision-Language-Action (VLA) model and world model in one single framework. T…

Action GenerationmodelVision-Language-Action

Data Efficacy for Language Model Training

2025-06-26 · Yalun Dai, Yangyu Huang, Xin Zhang, Wenshan Wu 외

Data is fundamental to the training of language models (LM). Recent research has been dedicated to data efficiency, which aims to maximize performance by selecting a minimal or optimal subset of training data. Techniques…

Language ModelingLanguage Modellingmodel

Model State Arithmetic for Machine Unlearning

2025-06-26 · Keivan Rezaei, Mehrdad Saberi, Abhilasha Ravichander, Soheil Feizi

Large language models are trained on massive corpora of web data, which may include private data, copyrighted material, factually inaccurate data, or data that degrades model performance. Eliminating the influence of suc…

Machine Unlearningmodel

Enterprise Large Language Model Evaluation Benchmark

2025-06-25 · Liya Wang, David Yi, Damien Jose, John Passarelli 외

Large Language Models (LLMs) ) have demonstrated promise in boosting productivity across AI-powered tools, yet existing benchmarks like Massive Multitask Language Understanding (MMLU) inadequately assess enterprise-speci…

Language Model EvaluationLanguage ModelingLanguage ModellingLarge Language Model+4

IRanker: Towards Ranking Foundation Model

2025-06-25 · Tao Feng, Zhigang Hua, Zijie Lei, Yan Xie 외

Ranking tasks are ubiquitous, encompassing applications such as recommendation systems, LLM routing, and item re-ranking. We propose to unify these tasks using a single ranking foundation model (FM), as it eliminates the…

GSM8KmodelPassage RankingRecommendation Systems+3

FlightKooba: A Fast Interpretable FTP Model

2025-06-24 · Jing Lu, Xuan Wu, Yizhun Tian, Songhan Fan 외

The Koopman theory is a powerful and effective modeling tool for converting nonlinear systems into linear representations, and flight trajectory prediction (FTP) is a complex nonlinear system. However, current models app…

MambamodelTime Series ForecastingTrajectory Prediction

Private Model Personalization Revisited

2025-06-24 · Conor Snedeker, Xinyu Zhou, Raef Bassily

We study model personalization under user-level differential privacy (DP) in the shared representation framework. In this problem, there are $n$ users whose data is statistically heterogeneous, and their optimal paramete…

Binary ClassificationFederated Learningmodel

Unified Vision-Language-Action Model

2025-06-24 · Yuqi Wang, Xinghang Li, Wenxuan Wang, Junbo Zhang 외

Vision-language-action models (VLAs) have garnered significant attention for their potential in advancing robotic manipulation. However, previous approaches predominantly rely on the general comprehension capabilities of…

Autonomous DrivingmodelVision-Language-Action
1–20 / 5,434 다음 →