5 papers
Sigma: The Key for Vision-Language-Action Models toward Telepathic Alignment
Libo Wang
To address a fundamental limitation in cognitive systems, namely the absence of a time-updatable mediating thought space between semantics and continuous control, this work constru…
Reducing Reasoning Costs: The Path of Optimization for Chain of Thought via Sparse Attention Mechanism
Libo Wang
In order to address the chain of thought in the large language model inference cost surge, this research proposes to use a sparse attention mechanism that only focuses on a few rel…
Graph-of-Causal Evolution: Challenging Chain-of-Model for Reasoning
Libo Wang
In view of the problem that each subchain in the chain-of-model (CoM) relies only on the information of the previous subchain and may lose long-range dependencies due to the causal…
Wormhole Memory: A Rubik's Cube for Cross-Dialogue Retrieval
Libo Wang
In view of the gap in the current large language model in sharing memory across dialogues, this research proposes a wormhole memory module (WMM) to realize memory as a Rubik's cube…
"Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks
Libo Wang
As the application of large language models continues to expand in various fields, it poses higher challenges to the effectiveness of identifying harmful content generation and gua…