SOTAVerified

Attribute

Papers

Showing 51100 of 5387 papers

TitleStatusHype
Non-destructive Degradation Pattern Decoupling for Ultra-early Battery Prototype Verification Using Physics-informed Machine LearningCode2
MVGamba: Unify 3D Content Generation as State Space Sequence ModelingCode2
Objaverse++: Curated 3D Object Dataset with Quality AnnotationsCode2
PACO: Parts and Attributes of Common ObjectsCode2
Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive DecodingCode2
Modular Primitives for High-Performance Differentiable RenderingCode2
NMS Strikes BackCode2
Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language ModelsCode2
Measuring Style Similarity in Diffusion ModelsCode2
MetaFormer: A Unified Meta Framework for Fine-Grained RecognitionCode2
On the Role of Attention Heads in Large Language Model SafetyCode2
OpenFACADES: An Open Framework for Architectural Caption and Attribute Data Enrichment via Street View ImageryCode2
Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion ModelsCode2
MagicFace: High-Fidelity Facial Expression Editing with Action-Unit ControlCode2
LVOS: A Benchmark for Large-scale Long-term Video Object SegmentationCode2
MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object DetectionCode2
Link Prediction without Graph Neural NetworksCode2
LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential RecommendationCode2
LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural AnnotationsCode2
MARLIN: Masked Autoencoder for facial video Representation LearnINgCode2
MMFashion: An Open-Source Toolbox for Visual Fashion AnalysisCode2
Pedestrian Detection: Domain Generalization, CNNs, Transformers and BeyondCode2
InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANsCode2
High-fidelity 3D GAN Inversion by Pseudo-multi-view OptimizationCode2
Interpreting the Latent Space of GANs for Semantic Face EditingCode2
HairCLIPv2: Unifying Hair Editing via Proxy Feature BlendingCode2
Hard Sample Aware Network for Contrastive Deep Graph ClusteringCode2
Is CLIP ideal? No. Can we fix it? Yes!Code2
GenEval: An Object-Focused Framework for Evaluating Text-to-Image AlignmentCode2
A Synthetic Dataset for Personal Attribute InferenceCode2
GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement LearningCode2
FaceDancer: Pose- and Occlusion-Aware High Fidelity Face SwappingCode2
A Survey of Machine UnlearningCode2
Faceptor: A Generalist Model for Face PerceptionCode2
Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic SegmentationCode2
EmbodiedEval: Evaluate Multimodal LLMs as Embodied AgentsCode2
GPT4RoI: Instruction Tuning Large Language Model on Region-of-InterestCode2
DigiFace-1M: 1 Million Digital Face Images for Face RecognitionCode2
DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group LearningCode2
Description and Discussion on DCASE 2024 Challenge Task 2: First-Shot Unsupervised Anomalous Sound Detection for Machine Condition MonitoringCode2
DreamMix: Decoupling Object Attributes for Enhanced Editability in Customized Image InpaintingCode2
Hierarchical Fine-Grained Image Forgery Detection and LocalizationCode2
HumanBench: Towards General Human-centric Perception with Projector Assisted PretrainingCode2
Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic DirectionsCode2
Apply Hierarchical-Chain-of-Generation to Complex Attributes Text-to-3D GenerationCode2
ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape DisentanglementCode2
Closed-Form Factorization of Latent Semantics in GANsCode2
CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept MatchingCode2
LLM Attributor: Interactive Visual Attribution for LLM GenerationCode2
DynRefer: Delving into Region-level Multi-modality Tasks via Dynamic ResolutionCode2
Show:102550
← PrevPage 2 of 108Next →

No leaderboard results yet.