9 citations · 15 across the 19 of their papers we have counts for
16 papers · 1 filter
Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
Yixiu Mao, Yun Qu, Qi Wang +2
Reinforcement learning (RL) finetuning has become a key technique for enhancing the reasoning abilities of large language models (LLMs). However, its effectiveness critically depen…
VAO: Validation-Aligned Optimization for Cross-Task Generative Auto-Bidding
Yiqin Lv, Zhiyu Mou, Miao Xu +9
Generative auto-bidding has demonstrated strong performance in online advertising, yet it often suffers from data scarcity in small-scale settings with limited advertiser participa…
Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
Yun Qu, Qi Cheems Wang, Yixiu Mao +2
Task robust adaptation is a long-standing pursuit in sequential decision-making. Some risk-averse strategies, e.g., the conditional value-at-risk principle, are incorporated in dom…
DynaPrompt: Dynamic Test-Time Prompt Tuning
Zehao Xiao, Shilin Yan, Jack Hong +6
Test-time prompt tuning enhances zero-shot generalization of vision-language models but tends to ignore the relatedness among test samples during inference. Online test-time prompt…
Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning
Yun Qu, Yuhang Jiang, Boyuan Wang +4
Reinforcement learning (RL) often encounters delayed and sparse feedback in real-world applications, even with only episodic rewards. Previous approaches have made some progress in…
Bridge the Inference Gaps of Neural Processes via Expectation Maximization
Qi Wang, Marco Federici, Herke van Hoof
The neural process (NP) is a family of computationally efficient models for learning distributions over functions. However, it suffers from under-fitting and shows suboptimal perfo…
Model Predictive Task Sampling for Efficient and Robust Adaptation
Qi Wang, Zehao Xiao, Yixiu Mao +4
Foundation models have revolutionized general-purpose problem-solving, offering rapid task adaptation through pretraining, meta-training, and finetuning. Recent crucial advances in…
Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
Yixiu Mao, Qi Wang, Chen Chen +2
In offline reinforcement learning (RL), addressing the out-of-distribution (OOD) action issue has been a focus, but we argue that there exists an OOD state issue that also impairs…
Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learning
Yiqin Lv, Qi Wang, Dong Liang +1
Meta learning is a promising paradigm in the era of large models and task distributional robustness has become an indispensable consideration in real-world scenarios. Recent advanc…
Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation
Cheems Wang, Yiqin Lv, Yixiu Mao +3
Meta-learning is a practical learning paradigm to transfer skills across tasks from a few examples. Nevertheless, the existence of task distribution shifts tends to weaken meta-lea…
Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
Yuchen Yang, Yingdong Shi, Cheems Wang +3
Fine-tuning pretrained large models to downstream tasks is an important problem, which however suffers from huge memory overhead due to large-scale parameters. This work strives to…
GO4Align: Group Optimization for Multi-Task Alignment
Jiayi Shen, Cheems Wang, Zehao Xiao +2
This paper proposes \textit{GO4Align}, a multi-task optimization approach that tackles task imbalance by explicitly aligning the optimization across tasks. To achieve this, we desi…
Episodic Multi-Task Learning with Heterogeneous Neural Processes
Jiayi Shen, Xiantong Zhen, Qi +2
This paper focuses on the data-insufficiency problem in multi-task learning within an episodic training setup. Specifically, we explore the potential of heterogeneous information a…
A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm
Qi Wang, Yiqin Lv, Yanghe Feng +2
Meta learning is a promising paradigm to enable skill transfer across tasks. Most previous methods employ the empirical risk minimization principle in optimization. However, the re…
Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models
Qi Wang, Herke van Hoof
Reinforcement learning is a promising paradigm for solving sequential decision-making problems, but low data efficiency and weak generalization across tasks are bottlenecks in real…
Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables
Qi Wang, Herke van Hoof
Neural processes (NPs) constitute a family of variational approximate models for stochastic processes with promising properties in computational efficiency and uncertainty quantifi…