English
Related papers

Related papers: $\pi$-Play: Multi-Agent Self-Play via Privileged S…

200 papers

It has been recently demonstrated that multi-generational self-distillation can improve generalization. Despite this intriguing observation, reasons for the enhancement remain poorly understood. In this paper, we first demonstrate…

Machine Learning · Computer Science 2020-10-23 Zhilu Zhang , Mert R. Sabuncu

Current Reinforcement Learning (RL) methods often suffer from sample-inefficiency, resulting from blind exploration strategies that neglect causal relationships among states, actions, and rewards. Although recent causal approaches aim to…

Artificial Intelligence · Computer Science 2025-02-17 Hongye Cao , Fan Feng , Tianpei Yang , Jing Huo , Yang Gao

Conditional image generation models have achieved remarkable results by leveraging text-based control to generate customized images. However, the high resource demands of these models and the scarcity of well-annotated data have hindered…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Yicheng Jiang , Jin Yuan , Hua Yuan , Yao Zhang , Yong Rui

The problem of learning from few labeled examples while using large amounts of unlabeled data has been approached by various semi-supervised methods. Although these methods can achieve superior performance, the models are often not…

Computer Vision and Pattern Recognition · Computer Science 2021-09-21 Sahil Khose , Shruti Jain , V Manushree

We introduce DIP, a novel unsupervised post-training method designed to enhance dense image representations in large-scale pretrained vision encoders for in-context scene understanding. Unlike prior approaches that rely on complex…

Computer Vision and Pattern Recognition · Computer Science 2025-09-10 Sophia Sirko-Galouchenko , Spyros Gidaris , Antonin Vobecky , Andrei Bursuc , Nicolas Thome

The outpouring of various pre-trained models empowers knowledge distillation by providing abundant teacher resources, but there lacks a developed mechanism to utilize these teachers adequately. With a massive model repository composed of…

Machine Learning · Computer Science 2022-09-29 Su Lu , Han-Jia Ye , De-Chuan Zhan

To prevent implicit privacy disclosure in sharing gradients among data owners (DOs) under federated learning (FL), differential privacy (DP) and its variants have become a common practice to offer formal privacy guarantees with low…

Computer Science and Game Theory · Computer Science 2023-02-16 Yuntao Wang , Zhou Su , Yanghe Pan , Abderrahim Benslimane , Yiliang Liu , Tom H. Luan , Ruidong Li

Large language models often solve tasks from a fully specified prompt but degrade when the same requirements unfold over multiple turns, known as the lost-in-conversation (LiC) gap. We trace part of this degradation to self-contamination:…

Computation and Language · Computer Science 2026-05-27 Haoyu Zheng , Yun Zhu , Shu Yuan , Shangming Chen , Qing Wang , Wenqiao Zhang , Jun Xiao , Yueting Zhuang

One of the key challenges in visual imitation learning is collecting large amounts of expert demonstrations for a given task. While methods for collecting human demonstrations are becoming easier with teleoperation methods and the use of…

Robotics · Computer Science 2021-07-20 Sarah Young , Jyothish Pari , Pieter Abbeel , Lerrel Pinto

Recent advances in Competitive Self-Play (CSP) have achieved, or even surpassed, human level performance in complex game environments such as Dota 2 and StarCraft II using Distributed Multi-Agent Reinforcement Learning (MARL). One core…

Machine Learning · Computer Science 2023-11-30 Daniel Bairamian , Philippe Marcotte , Joshua Romoff , Gabriel Robert , Derek Nowrouzezahrai

Imitation Learning offers a promising approach to learn directly from data without requiring explicit models, simulations, or detailed task definitions. During inference, actions are sampled from the learned distribution and executed on the…

Robotics · Computer Science 2025-10-28 Amirreza Razmjoo , Sylvain Calinon , Michael Gienger , Fan Zhang

Vision-based deep reinforcement learning (RL) typically obtains performance benefit by using high capacity and relatively large convolutional neural networks (CNN). However, a large network leads to higher inference costs (power, latency,…

Machine Learning · Computer Science 2019-05-01 Sam Green , Craig M. Vineyard , Çetin Kaya Koç

One of the main challenges in the field of embodied artificial intelligence is the open-ended autonomous learning of complex behaviours. Our approach is to use task-independent, information-driven intrinsic motivation(s) to support…

Artificial Intelligence · Computer Science 2013-09-27 Keyan Zahedi , Georg Martius , Nihat Ay

Direct Preference Optimization (DPO) has emerged as a predominant alignment method for diffusion models, facilitating off-policy training without explicit reward modeling. However, its reliance on large-scale, high-quality human preference…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Khiem Pham , Quang Nguyen , Tung Nguyen , Jingsen Zhu , Michele Santacatterina , Dimitris Metaxas , Ramin Zabih

We introduce Proximal Policy Distillation (PPD), a novel policy distillation method that integrates student-driven distillation and Proximal Policy Optimization (PPO) to increase sample efficiency and to leverage the additional rewards that…

Machine Learning · Computer Science 2026-05-11 Giacomo Spigler

At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specifically active learning…

Machine Learning · Computer Science 2024-03-11 Andreas Kirsch

Deep reinforcement learning (DRL) is a booming area of artificial intelligence. Many practical applications of DRL naturally involve more than one collaborative learners, making it important to study DRL in a multi-agent context. Previous…

Machine Learning · Computer Science 2019-10-22 Gang Chen

Data efficiency is a key challenge for deep reinforcement learning. We address this problem by using unlabeled data to pretrain an encoder which is then finetuned on a small amount of task-specific data. To encourage learning…

Many high-performance human activities are executed with little or no external feedback: think of a figure skater landing a triple jump, a pitcher throwing a curveball for a strike, or a barista pouring latte art. To study the process of…

Artificial Intelligence · Computer Science 2025-12-10 Antonio Terpin , Raffaello D'Andrea

We introduce a new unsupervised anomaly detection ensemble called SPI which can harness privileged information - data available only for training examples but not for (future) test examples. Our ideas build on the Learning Using Privileged…

Machine Learning · Computer Science 2018-05-25 Shubhranshu Shekhar , Leman Akoglu