English
Related papers

Related papers: ProcVLM: Learning Procedure-Grounded Progress Rewa…

200 papers

Enhancing the mathematical reasoning capabilities of Large Language Models (LLMs) is of great scientific and practical significance. Researchers typically employ process-supervised reward models (PRMs) to guide the reasoning process,…

Computation and Language · Computer Science 2025-07-24 Wei Sun , Qianlong Du , Fuwei Cui , Jiajun Zhang

Language-guided long-horizon manipulation of deformable objects presents significant challenges due to high degrees of freedom, complex dynamics, and the need for accurate vision-language grounding. In this work, we focus on multi-step…

Improving the effectiveness of human-robot interaction requires social robots to accurately infer human goals through robust intention understanding. This challenge is particularly critical in multimodal settings, where agents must…

Human-Computer Interaction · Computer Science 2026-04-28 Hamed Rahimi , Clemence Grislain , Adrien Jacquet Cretides , Olivier Sigaud , Mohamed Chetouani

Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities but often struggle with complex, multi-step mathematical reasoning, where minor errors in visual perception or logical deduction can lead to complete failure.…

Computation and Language · Computer Science 2025-08-08 Jianghangfan Zhang , Yibo Yan , Kening Zheng , Xin Zou , Song Dai , Xuming Hu

While autoregressive Large Vision-Language Models (LVLMs) demonstrate remarkable proficiency in multimodal tasks, they face a "Visual Signal Dilution" phenomenon, where the accumulation of textual history expands the attention partition…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Siyuan Huang , Xiaoye Qu , Yafu Li , Tong Zhu , Zefeng He , Muxin Fu , Daizong Liu , Wei-Long Zheng , Yu Cheng

Visual perception tasks often require vast amounts of labelled data, including 3D poses and image space segmentation masks. The process of creating such training data sets can prove difficult or time-intensive to scale up to efficacy for…

Robotics · Computer Science 2022-08-03 Xiaotong Chen , Huijie Zhang , Zeren Yu , Stanley Lewis , Odest Chadwicke Jenkins

Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step information-seeking tasks remain challenging for agents backed by…

Artificial Intelligence · Computer Science 2025-11-25 Jaewoo Lee , Archiki Prasad , Justin Chih-Yao Chen , Zaid Khan , Elias Stengel-Eskin , Mohit Bansal

We study reward models for long-horizon manipulation tasks by learning from action-free videos and language instructions, which we term the visual-instruction correlation (VIC) problem. Recent advancements in cross-modality modeling have…

Robotics · Computer Science 2025-02-21 Kuo-Han Hung , Pang-Chi Lo , Jia-Fong Yeh , Han-Yuan Hsu , Yi-Ting Chen , Winston H. Hsu

The rapid advancement of Large Vision Language Models (LVLMs) has demonstrated excellent abilities in various visual tasks. Building upon these developments, the thinking with images paradigm has emerged, enabling models to dynamically edit…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Yujin Zhou , Pengcheng Wen , Jiale Chen , Boqin Yin , Han Zhu , Jiaming Ji , Juntao Dai , Chi-Min Chan , Sirui Han

Long-horizon precision manipulation in laboratory automation, such as pipette tip attachment and liquid transfer, requires policies that respect strict procedural logic while operating in continuous, high-dimensional state spaces. However,…

Robotics · Computer Science 2026-03-03 Yibo Qiu , Shu'ang Sun , Haoliang Ye , Ronald X Xu , Mingzhai Sun

Enabling robots to perform diverse tasks across varied environments is a central challenge in robot learning. While vision-language-action (VLA) models have shown promise for generalizable robot skills, realizing their full potential…

Robotics · Computer Science 2025-08-12 Junjie Wen , Yichen Zhu , Jinming Li , Zhibin Tang , Chaomin Shen , Feifei Feng

Most existing approaches formulate action quality assessment and skill proficiency estimation as discriminative prediction tasks, typically producing discrete labels or scores without explicitly modeling the reasoning process underlying the…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Edoardo Bianchi , Jacopo Staiano , Antonio Liotta

Recent years have seen considerable advancements in multi-step reasoning with Large Language Models (LLMs). The previous studies have elucidated the merits of integrating feedback or search mechanisms during model inference to improve the…

Computation and Language · Computer Science 2023-10-17 Qianli Ma , Haotian Zhou , Tingkai Liu , Jianbo Yuan , Pengfei Liu , Yang You , Hongxia Yang

A well-designed reward is critical for effective reinforcement learning-based policy improvement. In real-world robotics, obtaining such rewards typically requires either labor-intensive human labeling or brittle, handcrafted objectives.…

Robotics · Computer Science 2026-01-09 Tony Lee , Andrew Wagenmaker , Karl Pertsch , Percy Liang , Sergey Levine , Chelsea Finn

Embodied Vision-Language Models (VLMs) have demonstrated impressive performance and generalization in robotics, particularly within Vision-Language-Action frameworks. However, a significant gap remains between the high-level semantic focus…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Ruowen Zhao , Bangguo Li , Zuyan Liu , Yinan Liang , Junliang Ye , Fangfu Liu , Diankun Wu , Zhengyi Wang , Xumin Yu , Yongming Rao , Han Hu , Jun Zhu

Recent advances in large multimodal models (LMMs) have enabled impressive reasoning and perception abilities, yet most existing training pipelines still depend on human-curated data or externally verified reward models, limiting their…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Omkar Thawakar , Shravan Venkatraman , Ritesh Thawkar , Abdelrahman Shaker , Hisham Cholakkal , Rao Muhammad Anwer , Salman Khan , Fahad Khan

Process Reward Model (PRM) is widely used in the post-training of Large Language Model (LLM) because it can perform fine-grained evaluation of the reasoning steps of generated content. However, most PRMs lack long-term reasoning and deep…

Machine Learning · Computer Science 2026-05-22 Xinquan Chen , Chongying Yue , Bangwei Liu , Xuhong Wang , Yingchun Wang , Chaochao Lu

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

Improving the multi-step reasoning ability of Large Language Models (LLMs) is a critical yet challenging task. The dominant paradigm, outcome-supervised reinforcement learning (RLVR), rewards only correct final answers, often propagating…

Artificial Intelligence · Computer Science 2025-10-14 Beining Wang , Weihang Su , Hongtao Tian , Tao Yang , Yujia Zhou , Ting Yao , Qingyao Ai , Yiqun Liu

Automating radiology report generation with Large Vision-Language Models (LVLMs) holds great potential, yet these models often produce clinically critical hallucinations, posing serious risks. Existing hallucination detection methods…

Computation and Language · Computer Science 2025-10-28 Alois Thomas , Maya Varma , Jean-Benoit Delbrouck , Curtis P. Langlotz