SOTAVerified

Zero-shot Generalization

Papers

Showing 1120 of 572 papers

TitleStatusHype
Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation ModelsCode4
Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive ReinforcementCode4
MonSter: Marry Monodepth to Stereo Unleashes PowerCode4
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense PredictionCode4
Repurposing Diffusion-Based Image Generators for Monocular Depth EstimationCode4
Metric3D: Towards Zero-shot Metric 3D Prediction from A Single ImageCode4
Zero-1-to-3: Zero-shot One Image to 3D ObjectCode4
Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text RetrieversCode4
Detect Anything 3D in the WildCode3
PE3R: Perception-Efficient 3D ReconstructionCode3
Show:102550
← PrevPage 2 of 58Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GR-MGAvg. sequence length4.04Unverified
2MoDEAvg. sequence length4.01Unverified
3RoboUniViewAvg. sequence length3.65Unverified
43D Diffuser ActorAvg. sequence length3.27Unverified
5GR-1Avg. sequence length3.06Unverified