3 accepted papers
We introduce **Native Parallel Reasoner (NPR)**, a teacher-free framework that enables Large Language Models (LLMs) to self-evolve genuine parallel reasoning capabilities. NPR transforms the model from sequential emulation to native parallel cognition through three key innovations: 1) a **self-disti…
Recent advancements have demonstrated the advantage of converting pretrained large language models into powerful text encoders by enabling bidirectional attention in transformer layers. However, existing methods often require extensive training on large-scale datasets, posing challenges in low-resou…
Semantic similarity between two sentences is inherently subjective and can vary significantly based on the specific aspects emphasized. Consequently, traditional sentence encoders must be capable of generating conditioned sentence representations that account for diverse conditions or aspects. In th…