SOTAVerified

Zero-shot Generalization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 572 papers

TitleStatusHype
HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image PriorsCode2
Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language ModelsCode2
Unleashing Large-Scale Video Generative Pre-training for Visual Robot ManipulationCode2
GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned PolicyCode2
GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation ModelsCode2
GeoSynth: Contextually-Aware High-Resolution Satellite Image SynthesisCode2
vesselFM: A Foundation Model for Universal 3D Blood Vessel SegmentationCode2
BigBIO: A Framework for Data-Centric Biomedical Natural Language ProcessingCode2
Segment Any Anomaly without Training via Hybrid Prompt RegularizationCode2
SAM2MOT: A Novel Paradigm of Multi-Object Tracking by SegmentationCode2
Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion ModelCode2
RoboUniView: Visual-Language Model with Unified View Representation for Robotic ManipulationCode2
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal AlignmentCode2
RecGPT: A Foundation Model for Sequential RecommendationCode2
Semantic Guidance Tuning for Text-To-Image Diffusion ModelsCode2
VIMA: General Robot Manipulation with Multimodal PromptsCode2
Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot LearningCode2
OpenCity: Open Spatio-Temporal Foundation Models for Traffic PredictionCode2
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion PreimageCode2
Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language ModelCode2
NeRF-Supervised Deep StereoCode2
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model PerformanceCode2
Q-Insight: Understanding Image Quality via Visual Reinforcement LearningCode2
EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerceCode2
On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?Code2
Exploring the Limits of Vision-Language-Action Manipulations in Cross-task GeneralizationCode2
Efficient Alignment of Unconditioned Action Prior for Language-conditioned Pick and Place in ClutterCode2
Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model DisentanglementCode2
Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite ImageryCode2
Collaborative Decoding Makes Visual Auto-Regressive Modeling EfficientCode2
Autoregressive Image Generation with Randomized Parallel DecodingCode2
Matryoshka Diffusion ModelsCode2
RSBuilding: Towards General Remote Sensing Image Building Extraction and Change Detection with Foundation ModelCode2
Crosslingual Generalization through Multitask FinetuningCode2
Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask LearningCode2
Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge DistillationCode2
Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache CompressionCode2
Multitask Prompted Training Enables Zero-Shot Task GeneralizationCode2
CLIP-Forge: Towards Zero-Shot Text-to-Shape GenerationCode1
LR0.FM: Low-Res Benchmark and Improving Robustness for Zero-Shot Classification in Foundation ModelsCode1
CLIP-Embed-KD: Computationally Efficient Knowledge Distillation Using Embeddings as TeachersCode1
M^3GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and GenerationCode1
Learning Quadrupedal Locomotion over Challenging TerrainCode1
Learning Modular Simulations for Homogeneous SystemsCode1
Large Language Models are Good Prompt Learners for Low-Shot Image ClassificationCode1
Learning the Travelling Salesperson Problem Requires Rethinking GeneralizationCode1
MAgNet: Mesh Agnostic Neural PDE SolverCode1
Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTVCode1
Knowledge Transfer and Domain Adaptation for Fine-Grained Remote Sensing Image SegmentationCode1
Boosting Segment Anything Model Towards Open-Vocabulary LearningCode1
Show:102550
← PrevPage 2 of 12Next →

Benchmark Results

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