English
Related papers

Related papers: Beyond Imitation: Reinforcement Learning-Based Sim…

200 papers

Recently, reinforcement learning (RL)-based tuning has shifted the trajectory of Multimodal Large Language Models (MLLMs), particularly following the introduction of Group Relative Policy Optimization (GRPO). However, directly applying it…

Computation and Language · Computer Science 2025-05-21 Wenhui Zhu , Xuanzhao Dong , Xin Li , Peijie Qiu , Xiwen Chen , Abolfazl Razi , Aris Sotiras , Yi Su , Yalin Wang

The growing adoption of Vision-Language-Action (VLA) models in embodied AI intensifies the demand for diverse manipulation demonstrations. However, high costs associated with data collection often result in insufficient data coverage across…

Robotics · Computer Science 2025-08-05 Liming Zheng , Feng Yan , Fanfan Liu , Chengjian Feng , Yufeng Zhong , Lin Ma

While state-of-the-art vision-language models (VLMs) have demonstrated remarkable capabilities in complex visual-text tasks, their success heavily relies on massive model scaling, limiting their practical deployment. Small-scale VLMs offer…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Huilin Deng , Ding Zou , Rui Ma , Hongchen Luo , Yang Cao , Yu Kang

Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) are two prominent post-training paradigms for refining the capabilities and aligning the behavior of Large Language Models (LLMs). Existing approaches that integrate SFT and RL…

Machine Learning · Computer Science 2026-03-18 Wenhao Zhang , Yuexiang Xie , Yuchang Sun , Yanxi Chen , Guoyin Wang , Yaliang Li , Bolin Ding , Jingren Zhou

Enhancing the mathematical reasoning of Large Language Models (LLMs) is a pivotal challenge in advancing AI capabilities. While Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) are the dominant training paradigms, a systematic…

Machine Learning · Computer Science 2025-07-14 Hiroshi Yoshihara , Taiki Yamaguchi , Yuichi Inoue

Pre-trained Vision-Language-Action (VLA) models represent a major leap towards general-purpose robots, yet efficiently adapting them to novel, specific tasks in-situ remains a significant hurdle. While reinforcement learning (RL) is a…

Robotics · Computer Science 2026-04-10 Baicheng Li , Dong Wu , Zike Yan , Xinchen Liu , Lusong Li , Zecui Zeng , Hongbin Zha

Reinforcement learning (RL) algorithms have demonstrated promising results on complex tasks, yet often require impractical numbers of samples since they learn from scratch. Meta-RL aims to address this challenge by leveraging experience…

Machine Learning · Computer Science 2020-10-28 Russell Mendonca , Abhishek Gupta , Rosen Kralev , Pieter Abbeel , Sergey Levine , Chelsea Finn

Learning visuomotor policies for agile quadrotor flight presents significant difficulties, primarily from inefficient policy exploration caused by high-dimensional visual inputs and the need for precise and low-latency control. To address…

Robotics · Computer Science 2024-11-13 Jiaxu Xing , Angel Romero , Leonard Bauersfeld , Davide Scaramuzza

Debates about large language model post-training often treat supervised fine-tuning (SFT) as imitation and reinforcement learning (RL) as discovery. But this distinction is too coarse. What matters is whether a training procedure increases…

Artificial Intelligence · Computer Science 2026-05-12 Yuhao Li , Shengchao Liu

Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly improve desirable aspects such as image quality and prompt…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 David McAllister , Miika Aittala , Tero Karras , Janne Hellsten , Angjoo Kanazawa , Timo Aila , Samuli Laine

Reinforcement learning with AI feedback (RLAIF) is a popular paradigm for improving the instruction-following abilities of powerful pre-trained language models. RLAIF first performs supervised fine-tuning (SFT) using demonstrations from a…

Machine Learning · Computer Science 2024-02-20 Archit Sharma , Sedrick Keh , Eric Mitchell , Chelsea Finn , Kushal Arora , Thomas Kollar

Multi-rotor UAVs suffer from a restricted range and flight duration due to limited battery capacity. Autonomous landing on a 2D moving platform offers the possibility to replenish batteries and offload data, thus increasing the utility of…

Robotics · Computer Science 2024-05-17 Pascal Goldschmid , Aamir Ahmad

Vision-based reinforcement learning (RL) is a promising technique to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…

Machine Learning · Computer Science 2021-09-29 Elie Aljalbout , Maximilian Ulmer , Rudolph Triebel

Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent…

Artificial Intelligence · Computer Science 2026-03-24 Dongyoung Kim , Sumin Park , Woomin Song , Seungku Kim , Taeyoung Kim , Huiwon Jang , Jinwoo Shin , Jaehyung Kim , Younggyo Seo

Learning generalizable robot manipulation policies, especially for complex multi-fingered humanoids, remains a significant challenge. Existing approaches primarily rely on extensive data collection and imitation learning, which are…

Robotics · Computer Science 2025-09-03 Toru Lin , Kartik Sachdev , Linxi Fan , Jitendra Malik , Yuke Zhu

Post-training has demonstrated its importance in enhancing the reasoning capabilities of large language models (LLMs). The primary post-training methods can be categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning…

Machine Learning · Computer Science 2025-10-21 Mingyang Liu , Gabriele Farina , Asuman Ozdaglar

Reinforcement learning (RL) is a promising approach for solving robotic manipulation tasks. However, it is challenging to apply the RL algorithms directly in the real world. For one thing, RL is data-intensive and typically requires…

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Binbin Ji , Siddharth Agrawal , Qiance Tang , Yvonne Wu

Current Reinforcement Learning (RL) algorithms struggle with long-horizon tasks where time can be wasted exploring dead ends and task progress may be easily reversed. We develop the SPOT framework, which explores within action safety zones,…

Distilling the tool-using capabilities of large language models (LLMs) into smaller, more efficient small language models (SLMs) is a key challenge for their practical application. The predominant approach, supervised fine-tuning (SFT),…

Computation and Language · Computer Science 2025-10-29 ChangSu Choi , Hoyun Song , Dongyeon Kim , WooHyeon Jung , Minkyung Cho , Sunjin Park , NohHyeob Bae , Seona Yu , KyungTae Lim