Search Results for author:
Found 13 papers, 8 papers with code
On a Connection Between Imitation Learning and RLHF
We establish a close theoretical connection between reinforcement learning from human feedback RLHF and imitation learning (IL), revealing that RLHF implicitly performs imitation learning on the preference data distribution.
MIGE: A Unified Framework for Multimodal Instruction-Based Image Generation and Editing
Experiments show that MIGE excels in both subject-driven generation and instruction-based editing while setting a state-of-the-art in the new task of instruction-based subject-driven editing.
SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters
Existing preference optimization objectives for language model alignment require additional hyperparameters that must be extensively tuned to achieve optimal performance, increasing both the complexity and time required for fine-tuning large language models.
Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment
Contrastive preference optimization has shown promising results in aligning LLMs with available preference data by optimizing the implicit reward associated with the policy.
Fact-Level Confidence Calibration and Self-Correction
Confidence calibration in LLMs, i. e., aligning their self-assessed confidence with the actual accuracy of their responses, enabling them to self-evaluate the correctness of their outputs.
How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective
This paper introduces a novel generalized self-imitation learning ($\textbf{GSIL}$) framework, which effectively and efficiently aligns large language models with offline demonstration data.
MITA: Bridging the Gap between Model and Data for Test-time Adaptation
Test-Time Adaptation (TTA) has emerged as a promising paradigm for enhancing the generalizability of models.
Negative as Positive: Enhancing Out-of-distribution Generalization for Graph Contrastive Learning
Graph contrastive learning (GCL), standing as the dominant paradigm in the realm of graph pre-training, has yielded considerable progress.
TEA: Test-time Energy Adaptation
To address this, we propose a novel energy-based perspective, enhancing the model's perception of target data distributions without requiring access to training data or processes.
PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion
The generalization of neural networks is a central challenge in machine learning, especially concerning the performance under distributions that differ from training ones.
Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective
Guided by the bound, we design a GCL framework named InfoAdv with enhanced generalization ability, which jointly optimizes the generalization metric and InfoMax to strike the right balance between pretext task fitting and the generalization ability on downstream tasks.
Hierarchical Estimation for Effective and Efficient Sampling Graph Neural Network
On account that previous studies either lacks variance analysis or only focus on a particular sampling paradigm, we firstly propose an unified node sampling variance analysis framework and analyze the core challenge "circular dependency" for deriving the minimum variance sampler, i. e., sampling probability depends on node embeddings while node embeddings can not be calculated until sampling is finished.
Augmentation-Aware Self-Supervision for Data-Efficient GAN Training
Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting.
