2 citations · 3 across the 6 of their papers we have counts for
6 papers
Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training
Miaosen Zhang, Yishan Liu, Shuxia Lin +8
Supervised fine-tuning (SFT) is computationally efficient but often yields inferior generalization compared to reinforcement learning (RL). This gap is primarily driven by RL's use…
The "Robert Boulton" Singularity: Semantic Tunneling and Manifold Unfolding in Recursive AI
Pengyue Hou
The stability of generative artificial intelligence trained on recursive synthetic data is conventionally monitored via Perplexity (PPL). We demonstrate that PPL is a deceptive met…
MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models
Yongshun Zhang, Zhongyi Fan, Yonghang Zhang +6
In recent years, large-scale generative models for visual content (\textit{e.g.,} images, videos, and 3D objects/scenes) have made remarkable progress. However, training large-scal…
Improving Contrastive Learning of Sentence Embeddings with Focal-InfoNCE
Pengyue Hou, Xingyu Li
The recent success of SimCSE has greatly advanced state-of-the-art sentence representations. However, the original formulation of SimCSE does not fully exploit the potential of har…
Improving Adversarial Robustness with Self-Paced Hard-Class Pair Reweighting
Pengyue Hou, Jie Han, Xingyu Li
Deep Neural Networks are vulnerable to adversarial attacks. Among many defense strategies, adversarial training with untargeted attacks is one of the most effective methods. Theore…
Adversarial Fine-tune with Dynamically Regulated Adversary
Pengyue Hou, Ming Zhou, Jie Han +2
Adversarial training is an effective method to boost model robustness to malicious, adversarial attacks. However, such improvement in model robustness often leads to a significant…