4 citations · 7 across the 10 of their papers we have counts for
10 papers
1.x-Distill: Breaking the Diversity, Quality, and Efficiency Barrier in Distribution Matching Distillation
Haoyu Li, Tingyan Wen, Lin Qi +6
Diffusion models produce high-quality text-to-image results, but their iterative denoising is computationally expensive.Distribution Matching Distillation (DMD) emerges as a promis…
Safety Reasoning with Guidelines
Haoyu Wang, Zeyu Qin, Li Shen +3
Training safe LLMs remains a critical challenge. The most widely used method, Refusal Training (RT), struggles to generalize against various Out-of-Distribution (OOD) jailbreaking…
Decentralized Directed Collaboration for Personalized Federated Learning
Yingqi Liu, Yifan Shi, Qinglun Li +3
Personalized Federated Learning (PFL) is proposed to find the greatest personalized models for each client. To avoid the central failure and communication bottleneck in the server-…
AlignIQL: Policy Alignment in Implicit Q-Learning through Constrained Optimization
Longxiang He, Li Shen, Xueqian Wang
Implicit Q-learning (IQL) serves as a strong baseline for offline RL, which learns the value function using only dataset actions through quantile regression. However, it is unclear…
Heterogeneous Federated Learning with Splited Language Model
Yifan Shi, Yuhui Zhang, Ziyue Huang +4
Federated Split Learning (FSL) is a promising distributed learning paradigm in practice, which gathers the strengths of both Federated Learning (FL) and Split Learning (SL) paradig…
Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy
Chenyang Cao, Zichen Yan, Renhao Lu +2
Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset. While prior work has demonstrated various ap…
Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping
Haoyu Wang, Guozheng Ma, Ziqiao Meng +9
Self-alignment is an effective way to reduce the cost of human annotation while ensuring promising model capability. However, most current methods complete the data collection and…
Efficient Federated Prompt Tuning for Black-box Large Pre-trained Models
Zihao Lin, Yan Sun, Yifan Shi +4
With the blowout development of pre-trained models (PTMs), the efficient tuning of these models for diverse downstream applications has emerged as a pivotal research concern. Altho…
Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages
Guozheng Ma, Lu Li, Sen Zhang +6
Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL). Although methods like…
Are Large Language Models Really Robust to Word-Level Perturbations?
Haoyu Wang, Guozheng Ma, Cong Yu +10
The swift advancement in the scales and capabilities of Large Language Models (LLMs) positions them as promising tools for a variety of downstream tasks. In addition to the pursuit…