pretrained models
Models that have been previously trained on large datasets and can be fine-tuned or used directly for specific tasks. Pretrained models often serve as starting points, significantly reducing training time and data requirements.
- AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping
- BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning
- Brain-Informed Fine-Tuning for Improved Multilingual Understanding in Language Models
- Composition and Alignment of Diffusion Models using Constrained Learning
- Corrector Sampling in Language Models
- Cross-Modal Representational Knowledge Distillation for Enhanced Spike-informed LFP Modeling
- Curvature Tuning: Provable Training-free Model Steering From a Single Parameter
- Differentiable Hierarchical Visual Tokenization
- Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation
- Exploring Diffusion Transformer Designs via Grafting
- Exploring Diffusion Transformer Designs via Grafting
- HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models
- LMFusion: Adapting Pretrained Language Models for Multimodal Generation
- MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching
- Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions
- More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models
- Noise Matters: Optimizing Matching Noise for Diffusion Classifiers
- One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
- PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation
- Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling
- Reward Reasoning Models
- Structured Initialization for Vision Transformers
- Towards Automated Petrography
- Universal Few-shot Spatial Control for Diffusion Models
- Value Gradient Guidance for Flow Matching Alignment
- Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection