Tag: model distillation
Browse our exclusive articles!
Efficient mRNA Representation via Genomic Model Distillation
Discover how embedding matching distills large genomic models for efficient mRNA representation, reducing size while maintaining top performance.
Weakly Supervised Hallucination Detection in Transformers
Discover a novel weak supervision method to distill hallucination signals into transformer models for efficient, internal hallucination detection without e...
Diversity-Aware Reverse KL Divergence for LLM Distillation
Explore Diversity-aware Reverse KL Divergence (DRKL) to improve large language model distillation with better performance and output diversity.
Efficient Hybrid Sequence Models via Generation-Focused Distillation
Discover how generation-focused distillation improves hybrid sequence models, reducing inference costs while maintaining high-quality output generation.
Uni-DAD: Fast Few-Shot Image Generation with Diffusion Models
Uni-DAD unifies distillation and adaptation in diffusion models for rapid, high-quality few-shot image generation with improved diversity and stability.