← Search

Guangyan Sun

2 accepted papers

2025

MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper

EMNLP 2025

Considering deep neural networks as manifold mappers, the pretrain-then-fine-tune paradigm can be interpreted as a two-stage process: pretrain establishes a broad knowledge base, and fine-tune adjusts the model parameters to activate specific neural pathways to align with the target manifold. Althou

Cited by 0SourcePDFScholar
2025

Visual Agents as Fast and Slow Thinkers

ICLR 2025poster

Achieving human-level intelligence requires refining cognitive distinctions between \textit{System 1} and \textit{System 2} thinking. While contemporary AI, driven by large language models, demonstrates human-like traits, it falls short of genuine cognition. Transitioning from structured benchmarks…