ICE-G:ImageConditionalEditingof3DGaussianSplats
Recently many techniques have emerged to create high quality 3D assets and scenes. When it comes to
首页 > 研究论文
-
-
RMem:RestrictedMemoryBanksImproveVideoObjectSegmentation
With recent video object segmentation (VOS) benchmarks evolving to challenging scenarios, we revisit
-
Real2Code:ReconstructArticulatedObjectsviaCodeGeneration
We present Real2Code, a novel approach to reconstructing articulated objects via code generation. Gi
-
RILe:ReinforcedImitationLearning
Reinforcement Learning has achieved significant success in generating complex behavior but often req
-
Surprise!UsingPhysiologicalStressforAllostaticRegulationUndertheActiveInferenceFramework[Pre-Print]
Allostasis proposes that long-term viability of a living system is achieved through anticipatory adj
-
DafnyBench:ABenchmarkforFormalSoftwareVerification
We introduce DafnyBench, the largest benchmark of its kind for training and evaluating machine learn
-
ScalingLawsinLinearRegression:Compute,Parameters,andData
Empirically, large-scale deep learning models often satisfy a neural scaling law: the test error of
-
Magpie:AlignmentDataSynthesisfromScratchbyPromptingAlignedLLMswithNothing
High-quality instruction data is critical for aligning large language models (LLMs). Although some m
-
TheImpactofInitializationonLoRAFinetuningDynamics
In this paper, we study the role of initialization in Low Rank Adaptation (LoRA) as originally intro
-
OLMES:AStandardforLanguageModelEvaluations
Progress in AI is often demonstrated by new models claiming improved performance on tasks measuring
-
TasTe:TeachingLargeLanguageModelstoTranslatethroughSelf-Reflection
Large language models (LLMs) have exhibited remarkable performance in various natural language proce
-
DiffusionSoup:ModelMergingforText-to-ImageDiffusionModels
We present Diffusion Soup, a compartmentalization method for Text-to-Image Generation that averages
-
ImprovingNoiseRobustnessthroughAbstractionsanditsImpactonMachineLearning
Noise is a fundamental problem in learning theory with huge effects in the application of Machine Le
-
Next-GenerationDatabaseInterfaces:ASurveyofLLM-basedText-to-SQL
Generating accurate SQL according to natural language questions (text-to-SQL) is a long-standing pro
-
AWGUNET:Attention-AidedWaveletGuidedU-NetforNucleiSegmentationinHistopathologyImages
Accurate nuclei segmentation in histopathological images is crucial for cancer diagnosis. Automating
-
StateSoup:In-ContextSkillLearning,RetrievalandMixing
A new breed of gated-linear recurrent neural networks has reached state-of-the-art performance on a
-
OmniCorpus:AnUnifiedMultimodalCorpusof10Billion-LevelImagesInterleavedwithText
Image-text interleaved data, consisting of multiple images and texts arranged in a natural document
-
TailoringGenerativeAIChatbotsforMultiethnicCommunitiesinDisasterPreparednessCommunication:ExtendingtheCASAParadigm
This study is among the first to develop different prototypes of generative AI (GenAI) chatbots powe
-
MMWorld:TowardsMulti-disciplineMulti-facetedWorldModelEvaluationinVideos
Multimodal Language Language Models (MLLMs) demonstrate the emerging abilities of "world models" --
-
ScalingValueIterationNetworksto5000LayersforExtremeLong-TermPlanning
The Value Iteration Network (VIN) is an end-to-end differentiable architecture that performs value i
