8 papers
A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint Principle
Guancheng Zhou, Yisi Luo, Zhengfu He +5
Most current paradigms in visual mechanistic interpretability (MI) remain confined to interpreting internal units of the vision model via heuristic methods (e.g., top- activatio…
Tracing the Thought of a Grandmaster-level Chess-Playing Transformer
Rui Lin, Zhenyu Jin, Guancheng Zhou +7
While modern transformer neural networks achieve grandmaster-level performance in chess and other reasoning tasks, their internal computation process remains largely opaque. Focusi…
Evolution of Concepts in Language Model Pre-Training
Xuyang Ge, Wentao Shu, Jiaxing Wu +3
Language models obtain extensive capabilities through pre-training. However, the pre-training process remains a black box. In this work, we track linear interpretable feature evolu…
Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary Learning
Junxuan Wang, Xuyang Ge, Wentao Shu +2
Transformer architectures, and their attention mechanisms in particular, form the foundation of modern large language models. While transformer models are widely believed to operat…
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
AGI Team, Yuxuan Cai, Lu Chen +62
The evolution of Large Language Models (LLMs) from passive responders to autonomous agents necessitates a fundamental shift in learning paradigms -- from static imitation to incent…
Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition
Zhengfu He, Junxuan Wang, Rui Lin +5
We propose Low-Rank Sparse Attention (Lorsa), a sparse replacement model of Transformer attention layers to disentangle original Multi Head Self Attention (MHSA) into individually…