English
Related papers

Related papers: MA-ROESL: Motion-aware Rapid Reward Optimization f…

200 papers

Traditional reinforcement learning (RL) methods typically employ a fixed control loop, where each cycle corresponds to an action. This rigidity poses challenges in practical applications, as the optimal control frequency is task-dependent.…

Machine Learning · Computer Science 2024-06-04 Dong Wang , Giovanni Beltrame

Vision Language Models (VLMs) pretrained on Internet-scale vision-language data have demonstrated the potential to transfer their knowledge to robotic learning. However, the existing paradigm encounters three critical challenges: (1)…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Haoxuan Li , Sixu Yan , Yuhan Li , Xinggang Wang

Recent Multimodal Large Language Models (MLLMs) have shown high potential for spatial reasoning within 3D scenes. However, they typically rely on computationally expensive 3D representations like point clouds or reconstructed Bird's-Eye…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Shuyao Shi , Kang G. Shin

Long video understanding is still challenging for recent Large Video-Language Models (LVLMs) due to the conflict between long-form temporal understanding and detailed spatial perception. LVLMs with a uniform frame sampling mechanism, which…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Shenghao Fu , Qize Yang , Yuan-Ming Li , Xihan Wei , Xiaohua Xie , Wei-Shi Zheng

Inspired by the impressive reasoning capabilities demonstrated by reinforcement learning approaches like DeepSeek-R1, recent emerging research has begun exploring the use of reinforcement learning (RL) to enhance vision-language models…

Computer Vision and Pattern Recognition · Computer Science 2025-06-19 Yizhen Zhang , Yang Ding , Shuoshuo Zhang , Xinchen Zhang , Haoling Li , Zhong-zhi Li , Peijie Wang , Jie Wu , Lei Ji , Yelong Shen , Yujiu Yang , Yeyun Gong

We present LARL-RM (Large language model-generated Automaton for Reinforcement Learning with Reward Machine) algorithm in order to encode high-level knowledge into reinforcement learning using automaton to expedite the reinforcement…

Machine Learning · Computer Science 2024-02-13 Shayan Meshkat Alsadat , Jean-Raphael Gaglione , Daniel Neider , Ufuk Topcu , Zhe Xu

Recent advances in vision-language models (VLMs) have significantly improved performance in embodied tasks such as goal decomposition and visual comprehension. However, providing accurate rewards for robotic manipulation without fine-tuning…

Robotics · Computer Science 2025-07-08 Yinuo Zhao , Jiale Yuan , Zhiyuan Xu , Xiaoshuai Hao , Xinyi Zhang , Kun Wu , Zhengping Che , Chi Harold Liu , Jian Tang

Vision-language models (VLMs) show promise in automating reward design in humanoid locomotion, which could eliminate the need for tedious manual engineering. However, current VLM-based methods are essentially "blind", as they lack the…

Robotics · Computer Science 2025-12-19 Enis Yalcin , Joshua O'Hara , Maria Stamatopoulou , Chengxu Zhou , Dimitrios Kanoulas

Ultra long video understanding remains an open challenge, as existing vision language models (VLMs) falter on such content due to limited context length and inefficient long term memory retention. To address this, recent works have…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Hongbo Jin , Qingyuan Wang , Wenhao Zhang , Yang Liu , Sijie Cheng

Large vision-language models (VLMs) have made significant strides in 2D visual understanding tasks, sparking interest in extending these capabilities to 3D scene understanding. However, current 3D VLMs often struggle with robust reasoning…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Ting Huang , Zeyu Zhang , Hao Tang

Vision-language models (VLMs) pretrained on large-scale multimodal datasets encode rich visual and linguistic knowledge, making them a strong foundation for robotics. Rather than training robotic policies from scratch, recent approaches…

Reinforcement learning (RL) has demonstrated compelling performance in robotic tasks, but its success often hinges on the design of complex, ad hoc reward functions. Researchers have explored how Large Language Models (LLMs) could enable…

Robotics · Computer Science 2025-05-13 Letian Chen , Nina Moorman , Matthew Gombolay

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…

Robotics · Computer Science 2019-02-15 Tianhe Yu , Gleb Shevchuk , Dorsa Sadigh , Chelsea Finn

Deep Reinforcement Learning (DRL) is a promising approach for teaching robots new behaviour. However, one of its main limitations is the need for carefully hand-coded reward signals by an expert. We argue that it is crucial to automate the…

Robotics · Computer Science 2021-08-09 Abdalkarim Mohtasib , Gerhard Neumann , Heriberto Cuayahuitl

Vision-Language-Action models (VLA) have demonstrated remarkable capabilities and promising potential in solving complex robotic manipulation tasks. However, their substantial parameter sizes and high inference latency pose significant…

Robotics · Computer Science 2025-06-24 Yuxuan Chen , Xiao Li

Robots can use Visual Imitation Learning (VIL) to learn manipulation tasks from video demonstrations. However, translating visual observations into actionable robot policies is challenging due to the high-dimensional nature of video data.…

Robotics · Computer Science 2025-01-22 Ananth Jonnavittula , Sagar Parekh , Dylan P. Losey

Reinforcement learning with verifiable rewards (RLVR) has proven effective in eliciting complex reasoning in large language models (LLMs). However, standard RLVR training often leads to excessively verbose processes (in reasoning tasks) and…

Artificial Intelligence · Computer Science 2025-10-01 Gang Li , Yulei Qin , Xiaoyu Tan , Dingkang Yang , Yuchen Shi , Zihan Xu , Xiang Li , Xing Sun , Ke Li

Automatically generating training supervision for embodied tasks is crucial, as manual designing is tedious and not scalable. While prior works use large language models (LLMs) or vision-language models (VLMs) to generate rewards, these…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Xiaowen Qiu , Yian Wang , Jiting Cai , Zhehuan Chen , Chunru Lin , Tsun-Hsuan Wang , Chuang Gan

Mastering robotic manipulation skills through reinforcement learning (RL) typically requires the design of shaped reward functions. Recent developments in this area have demonstrated that using sparse rewards, i.e. rewarding the agent only…

Machine Learning · Computer Science 2021-11-12 Ozsel Kilinc , Giovanni Montana

Current Vision-Language-Action (VLA) models predominantly rely on end-to-end fine-tuning. While effective, this paradigm compromises the inherent generalization capabilities of Vision-Language Models (VLMs) and incurs catastrophic…