SOTAVerified

The Open Verification Layer for ML Research

Community benchmark tracking and reproducibility verification. Built for researchers and autonomous research agents.

661,570 papers248,326 code links4,818 tasks

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 5001–5050 of 177340 papers

TitleStatusHype
ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGSCode2
FOCUS: Towards Universal Foreground SegmentationCode2
Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented GenerationCode2
Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio GenerationCode2
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual TransferCode2
TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight DetectionCode2
T-LoRA: Single Image Diffusion Model Customization Without OverfittingCode2
Uni-Sign: Toward Unified Sign Language Understanding at ScaleCode2
Mask-Adapter: The Devil is in the Masks for Open-Vocabulary SegmentationCode2
Autoregressive Image Generation with Randomized Parallel DecodingCode2
Contrastive Audio-Visual Masked AutoencoderCode2
Content-Aware Transformer for All-in-one Image RestorationCode2
Liger: Linearizing Large Language Models to Gated Recurrent StructuresCode2
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete RepresentationsCode2
LongForm: Effective Instruction Tuning with Reverse InstructionsCode2
DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy ProtectionCode2
ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly SegmentationCode2
CellViT: Vision Transformers for Precise Cell Segmentation and ClassificationCode2
Your Transformer is Secretly LinearCode2
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of DiffusionCode2
Diffusion-based Visual Anagram as Multi-task LearningCode2
Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse ProblemsCode2
AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-benchCode2
Big Transfer (BiT): General Visual Representation LearningCode2
HourVideo: 1-Hour Video-Language UnderstandingCode2
Learnware of Language Models: Specialized Small Language Models Can Do BigCode2
An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated LearningCode2
VM-UNET-V2 Rethinking Vision Mamba UNet for Medical Image SegmentationCode2
Sparse Upcycling: Training Mixture-of-Experts from Dense CheckpointsCode2
RefMask3D: Language-Guided Transformer for 3D Referring SegmentationCode2
Perceiver-Actor: A Multi-Task Transformer for Robotic ManipulationCode2
Towards a Multimodal Large Language Model with Pixel-Level Insight for BiomedicineCode2
Lightweight, Pre-trained Transformers for Remote Sensing TimeseriesCode2
MOSE: A New Dataset for Video Object Segmentation in Complex ScenesCode2
SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports ScenesCode2
Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge DistillationCode2
Attention Prompting on Image for Large Vision-Language ModelsCode2
Scaling Spike-driven Transformer with Efficient Spike Firing Approximation TrainingCode2
Brain Tumour Removing and Missing Modality Generation using 3D WDMCode2
Center-based 3D Object Detection and TrackingCode2
Vision6D: 3D-to-2D Interactive Visualization and Annotation Tool for 6D Pose EstimationCode2
SlimSAM: 0.1% Data Makes Segment Anything SlimCode2
Personality Alignment of Large Language ModelsCode2
STCOcc: Sparse Spatial-Temporal Cascade Renovation for 3D Occupancy and Scene Flow PredictionCode2
Exploiting Multimodal Spatial-temporal Patterns for Video Object TrackingCode2
Fast Training of Diffusion Models with Masked TransformersCode2
SkiROS2: A skill-based Robot Control Platform for ROSCode2
Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingCode2
VibeCheck: Discover and Quantify Qualitative Differences in Large Language ModelsCode2
Prodigy: An Expeditiously Adaptive Parameter-Free LearnerCode2
Show:102550
← PrevPage 101 of 3547Next →