7 papers
Refine Thought: A Test-Time Inference Method for Embedding Model Reasoning
Guangzhi Wang, Kai Li, Yinghao Jiao +1
We propose RT (Refine Thought), a method that can enhance the semantic reasoning ability of text embedding models. The method obtains the final semantic representation by running m…
CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models
Zhi Liu
Vision-Language-Action (VLA) models have rapidly converged on a small set of architectural patterns: discrete-token autoregression (e.g. OpenVLA) and continuous-action flow-matchin…
ChipLingo: A Systematic Training Framework for Large Language Models in EDA
Lei Li, Xingwen Yu, Jianguo Ni +4
With the rapid advancement of semiconductor technology, Electronic Design Automation (EDA) has become an increasingly knowledge-intensive and document-driven engineering domain. Al…
CRE-T1 Preview Technical Report: Beyond Contrastive Learning for Reasoning-Intensive Retrieval
Guangzhi Wang, Yinghao Jiao, Zhi Liu
The central challenge of reasoning-intensive retrieval lies in identifying implicitreasoning relationships between queries and documents, rather than superficial se-mantic or lexic…
PJB: A Reasoning-Aware Benchmark for Person-Job Retrieval
Guangzhi Wang, Xiaohui Yang, Kai Li +4
As retrieval models converge on generic benchmarks, the pressing question is no longer "who scores higher" but rather "where do systems fail, and why?" Person-job matching is a dom…
From Physician Expertise to Clinical Agents: Preserving, Standardizing, and Scaling Physicians' Medical Expertise with Lightweight LLM
Chanyong Luo, Jirui Dai, Zhendong Wang +14
Medicine is an empirical discipline refined through long-term observation and the messy, high-variance reality of clinical practice. Physicians build diagnostic and therapeutic com…