SOTAVerified

Zero-shot Generalization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 251–275 of 572 papers

TitleStatusHype
Amortized Active Causal Induction with Deep Reinforcement Learning—0
M^3GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and GenerationCode1
SMART: Scalable Multi-agent Real-time Motion Generation via Next-token PredictionCode3
Gradient Projection For Continual Parameter-Efficient Tuning—0
Prompt Learning for Generalized Vehicle RoutingCode0
Revisiting the Robust Generalization of Adversarial Prompt Tuning—0
A Minimalist Prompt for Zero-Shot Policy Learning—0
Enhancing Vision-Language Models Generalization via Diversity-Driven Novel Feature Synthesis—0
On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?Code2
MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-ExpertsCode3
Instruction Matters: A Simple yet Effective Task Selection for Optimized Instruction Tuning of Specific TasksCode0
The Third Monocular Depth Estimation Challenge—0
CompilerDream: Learning a Compiler World Model for General Code OptimizationCode1
Enabling Natural Zero-Shot Prompting on Encoder Models via Statement-Tuning—0
Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement LearningCode0
PromptSync: Bridging Domain Gaps in Vision-Language Models through Class-Aware Prototype Alignment and Discrimination—0
GeoSynth: Contextually-Aware High-Resolution Satellite Image SynthesisCode2
CLIP-Embed-KD: Computationally Efficient Knowledge Distillation Using Embeddings as TeachersCode1
Visually Descriptive Language Model for Vector Graphics ReasoningCode9
DiffCJK: Conditional Diffusion Model for High-Quality and Wide-coverage CJK Character Generation—0
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model PerformanceCode2
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language ReasoningCode2
Decision Transformer as a Foundation Model for Partially Observable Continuous Control—0
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale PredictionCode9
Where to Move Next: Zero-shot Generalization of LLMs for Next POI RecommendationCode1
Show:102550
← PrevPage 11 of 23Next →

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