Papers model
“model” 태그가 달린 논문 5,434편 · 필터 해제
Making Language Model a Hierarchical Classifier and Generator
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+3RegCL: Continual Adaptation of Segment Anything Model via Model Merging
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 LearningmodelImplementing Adaptations for Vision AutoRegressive Model
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 GenerationmodelGraph World Model
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 GenerationCompress Any Segment Anything Model (SAM)
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 SegmentationModel Parallelism With Subnetwork Data Parallelism
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 LearningmodelTemporal Information Retrieval via Time-Specifier Model Merging
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 RetrievalmodelRetrievalA Wireless Foundation Model for Multi-Task Prediction
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 IntervalsLRM-1B: Towards Large Routing Model
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 OptimizationmodelAutoadaptive Medical Segment Anything Model
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+1Epona: Autoregressive Diffusion World Model for Autonomous Driving
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+3RoboScape: Physics-informed Embodied World Model
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+1WorldVLA: Towards Autoregressive Action World Model
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-ActionData Efficacy for Language Model Training
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 ModellingmodelModel State Arithmetic for Machine Unlearning
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 UnlearningmodelEnterprise Large Language Model Evaluation Benchmark
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+4IRanker: Towards Ranking Foundation Model
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+3FlightKooba: A Fast Interpretable FTP Model
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 PredictionPrivate Model Personalization Revisited
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 LearningmodelUnified Vision-Language-Action Model
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