PulseAugur
LIVE 09:45:52
research · [14 sources] ·
0
research

Using Language Models as Closed-Loop High-Level Planners for Robotics Applications: A Brief Overview and…

Researchers have developed a novel framework for measuring student engagement using vision-language models (VLMs) and large language models (LLMs). This approach adapts VLMs for action recognition with limited data and uses LLMs to classify sequences of actions, considering peer context. Separately, new research explores using LLMs as closed-loop planners for robots, investigating strategies to improve their reliability and reduce errors in embodied planning tasks. Another study introduces an LLM-driven framework for robots to autonomously learn and adapt to new tasks in open environments, reducing reliance on repeated LLM interactions. AI

Summary written by None from 14 sources. How we write summaries →

IMPACT New frameworks for student engagement measurement, robot planning, and autonomous learning promise more adaptable and efficient AI systems.

RANK_REASON The cluster contains multiple research papers detailing novel AI methodologies and frameworks, primarily from arXiv.

Read on arXiv cs.AI →

COVERAGE [14]

  1. arXiv cs.CL TIER_1 · Xuemei Tang, Xufeng Duan, Zhenguang G. Cai ·

    Do Large Language Models Plan Answer Positions? Position Bias in Multiple-Choice Question Generation

    arXiv:2605.01846v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to generate multiple-choice questions (MCQs), where correct answers should ideally be uniformly distributed across options. However, we observe that LLMs exhibit systematic position…

  2. arXiv cs.CL TIER_1 · Zhenguang G. Cai ·

    Do Large Language Models Plan Answer Positions? Position Bias in Multiple-Choice Question Generation

    Large language models (LLMs) are increasingly used to generate multiple-choice questions (MCQs), where correct answers should ideally be uniformly distributed across options. However, we observe that LLMs exhibit systematic position biases during generation. Through extensive exp…

  3. arXiv cs.AI TIER_1 · Ahmed Abdelkawy, Ahmed Elsayed, Asem Ali, Aly Farag, Thomas Tretter, Michael McIntyre ·

    Context Matters: Peer-Aware Student Behavioral Engagement Measurement via VLM Action Parsing and LLM Sequence Classification

    arXiv:2601.06394v4 Announce Type: replace-cross Abstract: Understanding student behavior in the classroom is essential to improve both pedagogical quality and student engagement. Existing methods for predicting student engagement typically require substantial annotated data to mo…

  4. arXiv cs.AI TIER_1 · Hao Wang, Sathwik Karnik, Bea Lim, Somil Bansal ·

    Using Language Models as Closed-Loop High-Level Planners for Robotics Applications: A Brief Overview and Benchmarks

    arXiv:2511.07410v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Vision Language Models (VLMs) have become popular tools for embodied high-level planning. However, their deployment in black-box settings often leads to unpredictable or costly errors. To h…

  5. arXiv cs.AI TIER_1 · Hong Su ·

    An LLM-Driven Closed-Loop Autonomous Learning Framework for Robots Facing Uncovered Tasks in Open Environments

    arXiv:2604.22199v1 Announce Type: cross Abstract: Autonomous robots operating in open environments need the ability to continuously handle tasks that are not covered by predefined local methods. However, existing approaches often rely on repeated large-language-model (LLM) intera…

  6. arXiv cs.AI TIER_1 · Hong Su ·

    An LLM-Driven Closed-Loop Autonomous Learning Framework for Robots Facing Uncovered Tasks in Open Environments

    Autonomous robots operating in open environments need the ability to continuously handle tasks that are not covered by predefined local methods. However, existing approaches often rely on repeated large-language-model (LLM) interaction for uncovered tasks, and even successful exe…

  7. arXiv cs.CV TIER_1 · Dahua Gao, Yubo Dong, Anqi Li, Zhenyuan Lin, Ang Gao, Danhua Liu, Guangming Shi ·

    FUN: A Focal U-Net Combining Reconstruction and Object Detection for Snapshot Spectral Imaging

    arXiv:2604.27653v1 Announce Type: new Abstract: Conventional push-broom hyperspectral imaging suffers from slow acquisition speeds, precluding real-time object detection; in contrast, snapshot spectral imaging enables instantaneous hyperspectral images (HSIs) capture, making real…

  8. arXiv cs.CV TIER_1 · Shuokun Cheng, Jinghao Shi, Kun Sun ·

    UHR-Net: An Uncertainty-Aware Hypergraph Refinement Network for Medical Image Segmentation

    arXiv:2604.28095v1 Announce Type: new Abstract: Accurate lesion segmentation is crucial for clinical diagnosis and treatment planning. However, lesions often resemble surrounding tissues and exhibit ill-defined boundaries, leading to unstable predictions in boundary/transition re…

  9. arXiv cs.CV TIER_1 · Kun Sun ·

    UHR-Net: An Uncertainty-Aware Hypergraph Refinement Network for Medical Image Segmentation

    Accurate lesion segmentation is crucial for clinical diagnosis and treatment planning. However, lesions often resemble surrounding tissues and exhibit ill-defined boundaries, leading to unstable predictions in boundary/transition regions. Moreover, small-lesion cues can be dilute…

  10. arXiv cs.CV TIER_1 · Guangming Shi ·

    FUN: A Focal U-Net Combining Reconstruction and Object Detection for Snapshot Spectral Imaging

    Conventional push-broom hyperspectral imaging suffers from slow acquisition speeds, precluding real-time object detection; in contrast, snapshot spectral imaging enables instantaneous hyperspectral images (HSIs) capture, making real-time object detection feasible, yet its potenti…

  11. arXiv cs.CV TIER_1 · Yuqing Cao, Shuo Zhu, Rongzhou Chen, Jingyan Chen, Ni Chen, Edmund Y. Lam ·

    Rapid tracking through strongly scattering media with physics-informed neuromorphic speckle analysis

    arXiv:2604.25310v1 Announce Type: new Abstract: This work addresses the critical problem of tracking fast-moving objects through strongly scattering media in a low-light environment. Different from existing approaches that use frame-based cameras with fixed exposure times, which …

  12. arXiv cs.CV TIER_1 · Edmund Y. Lam ·

    Rapid tracking through strongly scattering media with physics-informed neuromorphic speckle analysis

    This work addresses the critical problem of tracking fast-moving objects through strongly scattering media in a low-light environment. Different from existing approaches that use frame-based cameras with fixed exposure times, which trade off signal-to-noise ratio for temporal res…

  13. arXiv cs.CV TIER_1 · Jui-Cheng Chiu, Yu-Chao Wang, Shengyang Luo, Tongyan Wang, Qi Yang, Nabin Khanal, Yingjie Victor Chen ·

    MIRAGE: A Micro-Interaction Relational Architecture for Grounded Exploration in Multi-Figure Artworks

    arXiv:2604.23788v1 Announce Type: new Abstract: Appreciating multi-figure paintings requires understanding how characters relate through subtle cues like gaze alignment, gesture, and spatial arrangement. We present MIRAGE, an evidence-centric framework designed to scaffold the ex…

  14. arXiv cs.CV TIER_1 · Ruiqing Sun, Xingshan Yao, Zhijing Wu, Tian Lan, Chenhao Cui, Huiyang Zhao, Jialing Shi, Chen Yang, Xianling Mao ·

    Do Protective Perturbations Really Protect Portrait Privacy under Real-world Image Transformations?

    arXiv:2604.23688v1 Announce Type: new Abstract: Proactive defense methods protect portrait images from unauthorized editing or talking face generation (TFG) by introducing pixel-level protective perturbations, and have already attracted increasing attention for privacy protection…