CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Reward 1 st Zhiqiang Wang Florida Atlantic University Boca Raton, USA zwang2022@fau.edu 2 nd Pengbin Feng University of Southern California Los Angeles, USA fengpengbin.apply@gmail.com Abstract--We propose CrowdVLM-R1, which expands the R1 base model for accurate crowd counting, using a novel framework that integrates the fuzzy group relative policy optimization reward function (FGRPR) to enhance learning efficiency. Unlike the conventional binary (0/1) accuracy reward, our fuzzy reward model, FGRPR, which contains both format and precision rewards, provides nuanced incentives to encourage the R1 model to learn to adjust policies towards precise outputs. Supervised fine-tuning (SFT) is also integrated for the CrowdVLM-R1 model to learn from a handful of inputs to enable both in-domain and out-of-domain counting. Experimental results demonstrate that GRPO with a standard binary accuracy reward underperforms compared to SFT . In contrast, FGRPR, applied to Qwen2.5-VL-(3B/7B), surpasses all baseline models, including GPT -4o, LLaMA2-70B and SFT, in five domain datasets. For out-of-domain datasets, FGRPR achieves performance comparable to SFT but excels when target values are larger, as its fuzzy reward function assigns higher rewards to closer approximations. This approach is broadly applicable to tasks where the precision of the answer is critical. I. INTRODUCTION Recently, DeepSeek R1 [1] has drawn much attention among advances in large language models (LLMs), as it demonstrates how reinforcement learning (RL) can be the primary driver of reasoning.

The rapid escalation from elementary school-level to frontier problems of the difficulty for LLM benchmarks in recent years have weaved a miracle for researchers that we are only inches away from surpassing human intelligence. However, is the LLMs' remarkable reasoning ability indeed comes from true intelligence by human standards, or are they simply reciting solutions witnessed during training at an Internet level? To study this problem, we propose RoR-Bench, a novel, multi-modal benchmark for detecting LLM's recitation behavior when asked simple reasoning problems but with conditions subtly shifted, and conduct empirical analysis on our benchmark. Surprisingly, we found existing cutting-edge LLMs unanimously exhibits extremely severe recitation behavior; by changing one phrase in the condition, top models such as OpenAI-o1 and DeepSeek-R1 can suffer 60 percent performance loss on elementary school-level arithmetic and reasoning problems. Such findings are a wake-up call to the LLM community that compels us to re-evaluate the true intelligence level of cutting-edge LLMs.

Large Language Models (LLMs) are increasingly used to simulate human users in interactive settings such as therapy, education, and social role-play. While these simulations enable scalable training and evaluation of AI agents, off-the-shelf LLMs often drift from their assigned personas, contradict earlier statements, or abandon role-appropriate behavior. We introduce a unified framework for evaluating and improving persona consistency in LLM-generated dialogue. We define three automatic metrics: prompt-to-line consistency, line-to-line consistency, and Q&A consistency, that capture different types of persona drift and validate each against human annotations. Using these metrics as reward signals, we apply multi-turn reinforcement learning to fine-tune LLMs for three user roles: a patient, a student, and a social chat partner. Our method reduces inconsistency by over 55%, resulting in more coherent and faithful simulated users.

The vision community is undergoing the unprecedented progress with the emergence of Vision-Language Pretrain-ing Models (VLMs). Prompt learning plays as the holy grail of accessing VLMs since it enables their fast adaptation to downstream tasks with limited resources. Whereas existing researches milling around single-prompt paradigms, rarely investigate the technical potential behind their multi-prompt learning counterparts. This paper aims to provide a principled retrospect for vision-language multi-prompt learning. W e extend the recent constant modality gap phenomenon to learnable prompts and then, justify the superiority of vision-language transfer with multi-prompt augmentation, empirically and theoretically. In terms of this observation, we propose an Energy-based Multi-prompt Learning (EMPL) to generate multiple prompt embeddings by drawing instances from an energy-based distribution, which is implicitly defined by VLMs. So our EMPL is not only parameter-efficient but also rigorously lead to the balance between in-domain and out-of-domain open-vocabulary generalization. Comprehensive experiments have been conducted to justify our claims and the excellence of EMPL.

Imitation learning from human demonstrations offers a promising approach for robot skill acquisition, but egocentric human data introduces fundamental challenges due to the embodiment gap. During manipulation, humans actively coordinate head and hand movements, continuously reposition their viewpoint and use pre-action visual fixation search strategies to locate relevant objects. These behaviors create dynamic, task-driven head motions that static robot sensing systems cannot replicate, leading to a significant distribution shift that degrades policy performance. We present EgoMI (Egocentric Manipulation Interface), a framework that captures synchronized end-effector and active head trajectories during manipulation tasks, resulting in data that can be retargeted to compatible semi-humanoid robot embodiments. To handle rapid and wide-spanning head viewpoint changes, we introduce a memory-augmented policy that selectively incorporates historical observations. We evaluate our approach on a bimanual robot equipped with an actuated camera head and find that policies with explicit head-motion modeling consistently outperform baseline methods. Results suggest that coordinated hand-eye learning with EgoMI effectively bridges the human-robot embodiment gap for robust imitation learning on semi-humanoid embodiments. Project page: https://egocentric-manipulation-interface.github.io

In this paper, we demonstrate how studying the rhetorics of ChatGPT prompt writing on social media can promote critical AI literacies. Prompt writing is the process of writing instructions for generative AI tools like ChatGPT to elicit desired outputs and there has been an upsurge of conversations about it on social media. To study this rhetorical activity, we build on four overlapping traditions of digital writing research in computers and composition that inform how we frame literacies, how we study social media rhetorics, how we engage iteratively and reflexively with methodologies and technologies, and how we blend computational methods with qualitative methods. Drawing on these four traditions, our paper shows our iterative research process through which we gathered and analyzed a dataset of 32,000 posts (formerly known as tweets) from X (formerly Twitter) about prompt writing posted between November 2022 to May 2023. We present five themes about these emerging AI literacy practices: (1) areas of communication impacted by prompt writing, (2) micro-literacy resources shared for prompt writing, (3) market rhetoric shaping prompt writing, (4) rhetorical characteristics of prompts, and (5) definitions of prompt writing. In discussing these themes and our methodologies, we highlight takeaways for digital writing teachers and researchers who are teaching and analyzing critical AI literacies.

Large language models are now integrated into many scientific workflows, accelerating data analysis, hypothesis generation, and design space exploration. In parallel with this growth, there is a growing need to carefully evaluate whether models accurately capture domain-specific knowledge and notation, since general-purpose benchmarks rarely reflect these requirements. This gap is especially clear in quantum science, which features non-intuitive phenomena and requires advanced mathematics. In this study, we introduce QuantumBench, a benchmark for the quantum domain that systematically examine how well LLMs understand and can be applied to this non-intuitive field. Using publicly available materials, we compiled approximately 800 questions with their answers spanning nine areas related to quantum science and organized them into an eight-option multiple-choice dataset. With this benchmark, we evaluate several existing LLMs and analyze their performance in the quantum domain, including sensitivity to changes in question format. QuantumBench is the first LLM evaluation dataset built for the quantum domain, and it is intended to guide the effective use of LLMs in quantum research.

Supervised fine-tuning (SFT) has become the de facto post-training strategy for large vision-language-action (VLA) models, but its reliance on costly human demonstrations limits scalability and generalization. We propose Probe, Learn, Distill (PLD), a three-stage plug-and-play framework that improves VLAs through residual reinforcement learning (RL) and distribution-aware data collection. In Stage 1, we train lightweight residual actors to probe failure regions of the VLA generalist. In Stage 2, we use a hybrid rollout scheme that aligns collected trajectories with the generalist's deployment distribution while capturing recovery behaviors. In Stage 3, we distill the curated trajectories back into the generalist with standard SFT. PLD achieves near-saturated 99% task success on LIBERO, over 50% gains in SimplerEnv, and 100% success on real-world Franka and YAM arm manipulation tasks. Ablations show that residual probing and distribution-aware replay are key to collecting deployment-aligned data that improves both seen and unseen tasks, offering a scalable path toward self-improving VLA models.

Drone fleets equipped with onboard cameras, computer vision, and Deep Neural Network (DNN) models present a powerful paradigm for real-time spatio-temporal decision-making. In wildfire response, such drones play a pivotal role in monitoring fire dynamics, supporting firefighter coordination, and facilitating safe evacuation. In this paper, we introduce AeroResQ, an edge-accelerated UAV framework designed for scalable, resilient, and collaborative escape route planning during wildfire scenarios. AeroResQ adopts a multi-layer orchestration architecture comprising service drones (SDs) and coordinator drones (CDs), each performing specialized roles. SDs survey fire-affected areas, detect stranded individuals using onboard edge accelerators running fire detection and human pose identification DNN models, and issue requests for assistance. CDs, equipped with lightweight data stores such as Apache IoTDB, dynamically generate optimal ground escape routes and monitor firefighter movements along these routes. The framework proposes a collaborative path-planning approach based on a weighted A* search algorithm, where CDs compute context-aware escape paths. AeroResQ further incorporates intelligent load-balancing and resilience mechanisms: CD failures trigger automated data redistribution across IoTDB replicas, while SD failures initiate geo-fenced re-partitioning and reassignment of spatial workloads to operational SDs. We evaluate AeroResQ using realistic wildfire emulated setup modeled on recent Southern California wildfires. Experimental results demonstrate that AeroResQ achieves a nominal end-to-end latency of <=500ms, much below the 2s request interval, while maintaining over 98% successful task reassignment and completion, underscoring its feasibility for real-time, on-field deployment in emergency response and firefighter safety operations.

In the context of global sustainability mandates, corporate carbon disclosure has emerged as a critical mechanism for aligning business strategy with environmental responsibility. The Carbon Disclosure Project (CDP) hosts the world's largest longitudinal dataset of climate-related survey responses, combining structured indicators with open-ended narratives, but the heterogeneity and free-form nature of these disclosures present significant analytical challenges for benchmarking, compliance monitoring, and investment screening. This paper proposes a novel decision-support framework that leverages large language models (LLMs) to assess corporate climate disclosure quality at scale. It develops a master rubric that harmonizes narrative scoring across 11 years of CDP data (2010-2020), enabling cross-sector and cross-country benchmarking. By integrating rubric-guided scoring with percentile-based normalization, our method identifies temporal trends, strategic alignment patterns, and inconsistencies in disclosure across industries and regions. Results reveal that sectors such as technology and countries like Germany consistently demonstrate higher rubric alignment, while others exhibit volatility or superficial engagement, offering insights that inform key decision-making processes for investors, regulators, and corporate environmental, social, and governance (ESG) strategists. The proposed LLM-based approach transforms unstructured disclosures into quantifiable, interpretable, comparable, and actionable intelligence, advancing the capabilities of AI-enabled decision support systems (DSSs) in the domain of climate governance.