Ruochen Cui — accepted AI-conference papers

2026

Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation

Boyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang, Ruochen Cui, Xilin Zhao +1

CVPR 2026

The limited understanding capacity of the visual encoder in Contrastive Language-Image Pre-training (CLIP) has become a key bottleneck for downstream performance. This capacity includes both Discriminative Ability (D-Ability), which reflects class separability, and Detail Perceptual Ability (P-Abili

Cited by 0 Source ↗code ↗Scholar ↗

2025

Rethinking Chain-of-Thought from the Perspective of Self-Training

Zongqian Wu, Baoduo Xu, Ruochen Cui, Mengmeng Zhan, Xiaofeng Zhu, Lei Feng

ICML 2025poster

Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in LLMs. Interestingly, we observe that both CoT reasoning and self-training share the core objective: iteratively leveraging model-generated information to progressively reduce prediction uncert…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗