zero-shot inference
The process of making predictions or classifications on unseen classes without any prior examples, leveraging learned knowledge from previously seen categories.
- Axial Neural Networks for Dimension-Free Foundation Models
- Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies
- Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies
- Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark
- D-VST: Diffusion Transformer for Pathology-Correct Tone-Controllable Cross-Dye Virtual Staining of Whole Slide Images
- Once Upon an Input: Reasoning via Per-Instance Program Synthesis
- Physics-Constrained Flow Matching: Sampling Generative Models with Hard Constraints
- Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models
- Tree of Preferences for Diversified Recommendation
- True Zero-Shot Inference of Dynamical Systems Preserving Long-Term Statistics