A brand new Foundation Model framework for deep learning in the future.

Traditional methods are based on block-wise regression. This framework, Enhanced Blockwise Classification (**EBC**), however, is based on the idea that aims to classify the count value within each block into several pre-defined bins. The enhancement comes from 3 aspects: discretization policy, label correction and loss function. 

Notice that the original block-wise classification concept was introduced by Liu *et al.* in *Counting Objects by Blockwise Classification*.

CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification

DAHSF

Digestion Algorithm in Hierarchical Symbolic Forests: A Fast Text Normalization Algorithm and Semantic Parsing Framework for Specific Scenarios and Lightweight Deployment

It is often desirable to distill the capabilities of large language models (LLMs) into smaller student models due to compute and memory constraints. One way to do this for classification tasks is via dataset synthesis. Prior approaches to synthesis use few-shot prompting, which relies on the LLM's parametric knowledge to generate usable examples. However, this leads to issues of repetition, bias towards popular entities, and stylistic differences from human text. We propose Synthesize by Retrieval and Refinement (SynthesizRR), which uses retrieval augmentation to introduce variety into the dataset synthesis process: as retrieved passages vary, the LLM is seeded with different content to generate its examples. We find that SynthesizRR greatly improves lexical and semantic diversity, similarity to human-written text, and distillation performance,

Source	Digestion Algorithm in Hierarchical Symbolic Forests: A Fast Text Normalization Algorithm and Semantic Parsing Framework for Specific Scenarios and Lightweight Deployment
Year
Data Source	Papers with Code archive (CC BY-SA)