English
Related papers

Related papers: ReMoT: Reinforcement Learning with Motion Contrast…

200 papers

One of the central tasks of multi-object tracking involves learning a distance metric that is consistent with the semantic similarities of objects. The design of an appropriate loss function that encourages discriminative feature learning…

Computer Vision and Pattern Recognition · Computer Science 2021-02-09 Amit Satish Unde , Renu M. Rameshan

Large multimodal models (LMMs) have gained impressive performance due to their outstanding capability in various understanding tasks. However, these models still suffer from some fundamental limitations related to robustness and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Thanh-Dat Truong , Huu-Thien Tran , Tran Thai Son , Bhiksha Raj , Khoa Luu

Reinforcement learning (RL) has emerged as a crucial approach for enhancing the capabilities of large language models. However, in Mixture-of-Experts (MoE) models, the routing mechanism often introduces instability, even leading to…

Computation and Language · Computer Science 2025-10-22 Wenhan Ma , Hailin Zhang , Liang Zhao , Yifan Song , Yudong Wang , Zhifang Sui , Fuli Luo

Reinforcement learning (RL) has emerged as a key paradigm for aligning and optimizing large language models (LLMs). Standard approaches treat the LLM as the policy and apply RL directly over the full vocabulary space. However, this…

Machine Learning · Computer Science 2026-02-17 Jing-Cheng Pang , Liang Lu , Xian Tang , Kun Jiang , Sijie Wu , Kai Zhang , Xubin Li

End-to-end autonomous driving systems map sensor data directly to control commands, but remain opaque, lack interpretability, and offer no formal safety guarantees. While recent vision-language-guided reinforcement learning (RL) methods…

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Computation and Language · Computer Science 2026-03-03 Ruoxi Cheng , Haoxuan Ma , Weixin Wang , Ranjie Duan , Jiexi Liu , Xiaoshuang Jia , Simeng Qin , Xiaochun Cao , Yang Liu , Xiaojun Jia

Long-form video understanding, characterized by long-range temporal dependencies and multiple events, remains a challenge. Existing methods often rely on static reasoning or external visual-language models (VLMs), which face issues like…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Yuan Xie , Tianshui Chen , Zheng Ge , Lionel Ni

Self-correction is essential for solving complex reasoning problems in vision-language models (VLMs). However, existing reinforcement learning (RL) methods struggle to learn it, as effective self-correction behaviors emerge only rarely,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Yi Ding , Ziliang Qiu , Bolian Li , Ruqi Zhang

Aligning a lens system relative to an imager is a critical challenge in camera manufacturing. While optimal alignment can be mathematically computed under ideal conditions, real-world deviations caused by manufacturing tolerances often…

Robotics · Computer Science 2025-10-06 Matthias Burkhardt , Tobias Schmähling , Pascal Stegmann , Michael Layh , Tobias Windisch

Large language models (LLMs) and classical machine learning methods offer complementary strengths for predictive modeling, yet their fundamentally different representations and training paradigms hinder effective integration: LLMs rely on…

Computation and Language · Computer Science 2026-04-21 Yunshuo Tian , Akayou Kitessa , Tanuja Chitnis , Yijun Zhao

Multimodal adaptation equips large language models (LLMs) with perceptual capabilities, but often weakens the reasoning ability inherited from language-only pretraining. This trade-off is especially pronounced in video-language models…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Zihang Fu , Haonan Wang , Jian Kang , Kenji Kawaguchi , Jiaying Wu

Multimodal instruction tuning has proven to be an effective strategy for achieving zero-shot generalization by fine-tuning pre-trained Large Multimodal Models (LMMs) with instruction-following data. However, as the scale of LMMs continues…

This study presents a comparative analysis between single-objective and multi-objective reinforcement learning methods for training a robot to navigate effectively to an end goal while efficiently avoiding obstacles. Traditional…

Robotics · Computer Science 2023-12-15 Vicki Young , Jumman Hossain , Nirmalya Roy

Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system. However, due to its instability, successfully RL training is challenging,…

Machine Learning · Computer Science 2018-08-28 Lijun Wu , Fei Tian , Tao Qin , Jianhuang Lai , Tie-Yan Liu

In recent years, reinforcement learning (RL)-based methods for learning driving policies have gained increasing attention in the autonomous driving community and have achieved remarkable progress in various driving scenarios. However,…

Robotics · Computer Science 2024-12-23 Zilin Huang , Zihao Sheng , Yansong Qu , Junwei You , Sikai Chen

Model-based reinforcement learning (MBRL) has gained much attention for its ability to learn complex behaviors in a sample-efficient way: planning actions by generating imaginary trajectories with predicted rewards. Despite its success, we…

Machine Learning · Computer Science 2024-02-20 Vint Lee , Pieter Abbeel , Youngwoon Lee

Given a collection of untrimmed and unsegmented videos, video corpus moment retrieval (VCMR) is to retrieve a temporal moment (i.e., a fraction of a video) that semantically corresponds to a given text query. As video and text are from two…

Computation and Language · Computer Science 2021-05-14 Hao Zhang , Aixin Sun , Wei Jing , Guoshun Nan , Liangli Zhen , Joey Tianyi Zhou , Rick Siow Mong Goh

Visual Language Models (VLMs), with powerful multimodal reasoning capabilities, are gradually integrated into autonomous driving by several automobile manufacturers to enhance planning capability in challenging environments. However, the…

Next-token prediction is the fundamental principle for training large language models (LLMs), and reinforcement learning (RL) further enhances their reasoning performance. As an effective way to model language, image, video, and other…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Zuyao Chen , Jinlin Wu , Zhen Lei , Marc Pollefeys , Chang Wen Chen

We study how robots can autonomously learn skills that require a combination of navigation and grasping. While reinforcement learning in principle provides for automated robotic skill learning, in practice reinforcement learning in the real…

Machine Learning · Computer Science 2021-12-08 Charles Sun , Jędrzej Orbik , Coline Devin , Brian Yang , Abhishek Gupta , Glen Berseth , Sergey Levine