We present OCR-Quality, a comprehensive human-annotated dataset designed for evaluating and developing OCR quality assessment methods. The dataset consists of 1,000 PDF pages converted to PNG images at 300 DPI, sampled from diverse real-world scenarios, including academic papers, textbooks, e-books, and multilingual documents. Each document has been processed using state-of-the-art Vision-Language Models (VLMs) and manually annotated with quality scores using a 4-level scoring system (1: Excellent, 2: Good, 3: Fair, 4: Poor). The dataset includes detailed source information, annotation guidelines, and representative cases across various difficulty levels. OCR-Quality addresses the critical need for reliable OCR quality assessment in real-world applications and provides a valuable benchmark for training and evaluating OCR verification systems. The dataset is publicly available at https://huggingface.co/datasets/Aslan-mingye/OCR-Quality .

We introduce J-ORA, a novel multimodal dataset that bridges the gap in robot perception by providing detailed object attribute annotations within Japanese human-robot dialogue scenarios. J-ORA is designed to support three critical perception tasks, object identification, reference resolution, and next-action prediction, by leveraging a comprehensive template of attributes (e.g., category, color, shape, size, material, and spatial relations). Extensive evaluations with both proprietary and open-source Vision Language Models (VLMs) reveal that incorporating detailed object attributes substantially improves multimodal perception performance compared to without object attributes. Despite the improvement, we find that there still exists a gap between proprietary and open-source VLMs. In addition, our analysis of object affordances demonstrates varying abilities in understanding object functionality and contextual relationships across different VLMs. These findings underscore the importance of rich, context-sensitive attribute annotations in advancing robot perception in dynamic environments. See project page at https://jatuhurrra.github.io/J-ORA/.

We propose Avi, a novel 3D Vision-Language-Action (VLA) architecture that reframes robotic action generation as a problem of 3D perception and spatial reasoning, rather than low-level policy learning. While existing VLA models primarily operate on 2D visual inputs and are trained end-to-end on task-specific action policies, Avi leverages 3D point clouds and language-grounded scene understanding to compute actions through classical geometric transformations. Most notably, Avi does not train on previous action tokens, rather, we build upon a 3D Multi-modal Large Language Model (MLLM) to generate the next point cloud and explicitly calculate the actions through classical transformations. This approach enables generalizable behaviors that are robust to occlusions, camera pose variations, and changes in viewpoint. By treating the robotic decision-making process as a structured reasoning task over 3D representations, Avi bridges the gap between high-level language instructions and low-level actuation without requiring opaque policy learning. Our preliminary results highlight the potential of 3D vision-language reasoning as a foundation for scalable, robust robotic systems. Check it out at https://avi-3drobot.github.io/.

Long-horizon robot manipulation tasks remain challenging for Vision-Language-Action (VLA) policies due to drift and exposure bias, often denoise the entire trajectory with fixed hyperparameters, causing small geometric errors to compound across stages and offering no mechanism to allocate extra test-time compute where clearances are tight. To address these challenges, we introduce FORGE-Tree, a plug-in control layer that couples a stage-aligned Diffusion Forcing (DF) head with test-time Monte Carlo Tree Diffusion (MCTD). With a frozen VLA encoder, DF aligns timesteps to subtask stages; during inference we partially denoise only a target segment while keeping other tokens frozen, turning trajectory refinement into a sequence of local edits. We then apply Monte Carlo Tree Diffusion to select the next segment to refine. A scene graph supplies priors for expansion and geometry relation-aware scoring for rollouts, yielding tree-structured denoising whose performance scales with search budget while preserving the executed prefix. Evaluation on LIBERO, FORGE-Tree improves success rate by 13.4 to 17.2 pp over the native VLA baselines with both OpenVLA and Octo-Base. Gains remain consistent under comparable compute budgets, especially on long-horizon variants. Videos available at: https://taco-group.github.io/FORGE-Tree/

Abstract--With the rapid advancement of Large Language Models (LLMs), their capabilities in various automation domains, particularly Unmanned Aerial V ehicle (UA V) operations, have garnered increasing attention. Current research remains predominantly constrained to small-scale UA V applications, with most studies focusing on isolated components such as path planning for toy drones, while lacking comprehensive investigation of medium-and long-range UA V systems in real-world operational contexts. Larger UA V platforms introduce distinct challenges, including stringent requirements for airport-based take-off and landing procedures, adherence to complex regulatory frameworks, and specialized operational capabilities with elevated mission expectations. LV system processes natural language instructions to orchestrate short-, medium-, and long-range UA V missions through five key technical components: (i) LLM-as-Parser for instruction interpretation, (ii) Route Planner for Points of Interest (POI) determination, (iii) Path Planner for waypoint generation, (iv) Control Platform for executable trajectory implementation, and (v) UA V monitoring. We demonstrate the system's feasibility through three representative use cases spanning different operational scales: multi-UA V patrol, multi-POI delivery, and multi-hop relocation. Beyond the current implementation, we establish a five-level automation taxonomy that charts the evolution from current LLM-as-Parser capabilities (Level 1) to fully autonomous LLMas-Autopilot systems (Level 5), identifying technical prerequisites and research challenges at each stage. The rise of Large Language Models (LLMs) has transformed numerous domains, such as mobile services, vehicles, and robotics [1]-[3]. These fields have become increasingly intelligent and user-friendly through LLM integration, enabling command and control through natural language. Equal contribution L. Y uan and C. G. Brinton are with the School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA. C. Deng and I. Hwang are with the School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN 47907, USA. Han is with the Department of Computer Science and Engineering, Y onsei University, Seoul, South Korea. E-mail: djh@yonsei.ac.kr S. Brunswicker is with the Polytechnic Institute, Purdue University, West Lafayette, IN 47907, USA. LLMs fulfill diverse roles within these systems. LLM-as-Router can orchestrate task allocation and model selection for human pilots, LLM-as-Agent can execute actions on behalf of humans, and LLM-as-Judge can conduct evaluations in place of human judgment.

Underwater activities like scuba diving enable millions annually to explore marine environments for recreation and scientific research. Maintaining situational awareness and effective communication are essential for diver safety. Traditional underwater communication systems are often bulky and expensive, limiting their accessibility to divers of all levels. While recent systems leverage lightweight smartphones and support text messaging, the messages are predefined and thus restrict context-specific communication. In this paper, we present AquaVLM, a tap-and-send underwater communication system that automatically generates context-aware messages and transmits them using ubiquitous smartphones. Our system features a mobile vision-language model (VLM) fine-tuned on an auto-generated underwater conversation dataset and employs a hierarchical message generation pipeline. We co-design the VLM and transmission, incorporating error-resilient fine-tuning to improve the system's robustness to transmission errors. We develop a VR simulator to enable users to experience AquaVLM in a realistic underwater environment and create a fully functional prototype on the iOS platform for real-world experiments. Both subjective and objective evaluations validate the effectiveness of AquaVLM and highlight its potential for personal underwater communication as well as broader mobile VLM applications.

While recent advances in Large Language Models (LLMs) have improved the quality of creative text generation, significant challenges remain in producing personalized stories that reflect individual user preferences. Conventional approaches rely on explicit feedback or fine-tuning, which presents practical issues regarding user burden, data collection, computational costs, and privacy. In this work, we propose PREFINE (Persona-and-Rubric Guided Critique-and-Refine), a novel framework that extends the Critique-and-Refine paradigm to personalization. PREFINE constructs a pseudo-user agent from a user's interaction history and generates user-specific rubrics (evaluation criteria). By having this agent critique and refine outputs on the user's behalf based on these tailored rubrics, our method achieves personalized generation without requiring parameter updates or direct user feedback. We conducted a comprehensive evaluation on the PerDOC and PerMPST story datasets. We designed three baseline methods and several model variants to verify the contribution of each component of our framework. In automatic evaluations (LLM-as-a-Judge), PREFINE achieved higher win rates and statistically significant scores than the baselines, without compromising general story quality. Analysis of the model variants confirmed that both the pseudo-user agent and the user-specific rubrics are crucial for enhancing personalization performance. Beyond story generation, our approach holds potential for enabling efficient personalization in broader applications, such as dialogue systems, education, and recommendation.

As generative AI increasingly outperforms students in producing academic writing, a critical question arises: how can we preserve the motivation, creativity, and intellectual growth of novice researchers in an age of automated academic achievement? This paper introduces GAMER PAT (GAme MastER, Paper Authoring Tutor), a prompt-engineered AI chatbot that reframes research paper writing as a serious game. Through role-playing mechanics, users interact with a co-author NPC and anonymous reviewer NPCs, turning feedback into "missions" and advancing through a narrative-driven writing process. Our study reports on 26+ gameplay chat logs, including both autoethnography and use by graduate students under supervision. Using qualitative log analysis with SCAT (Steps for Coding and Theorization), we identified an emergent four-phase scaffolding pattern: (1) question posing, (2) meta-perspective, (3) structuring, and (4) recursive reflection. These results suggest that GAMER PAT supports not only the structural development of research writing but also reflective and motivational aspects. We present this work as a descriptive account of concept and process, not a causal evaluation. We also include a speculative outlook envisioning how humans may continue to cultivate curiosity and agency alongside AI-driven research. This arXiv version thus provides both a descriptive report of design and usage, and a forward-looking provocation for future empirical studies.

Widespread frustration with rigid touch-tone Interactive Voice Response (IVR) systems for customer service underscores the need for more direct and intuitive language interaction. While speech technologies are necessary, the key challenge lies in routing intents from user phrasings to IVR menu paths, a task where Large Language Models (LLMs) show strong potential. Progress, however, is limited by data scarcity, as real IVR structures and interactions are often proprietary. We present a novel LLM-based methodology to address this gap. Using three distinct models, we synthesized a realistic 23-node IVR structure, generated 920 user intents (230 base and 690 augmented), and performed the routing task. We evaluate two prompt designs: descriptive hierarchical menus and flattened path representations, across both base and augmented datasets. Results show that flattened paths consistently yield higher accuracy, reaching 89.13% on the base dataset compared to 81.30% with the descriptive format, while augmentation introduces linguistic noise that slightly reduces performance. Confusion matrix analysis further suggests that low-performing routes may reflect not only model limitations but also redundancies in menu design. Overall, our findings demonstrate proof-of-concept that LLMs can enable IVR routing through a smoother, more seamless user experience -- moving customer service one step ahead of touch-tone menus.

In the area of commercial auto sales system, high-quality lead score sequencing determines the priority of a sale's work and is essential for optimizing the efficiency of the sales system. Since CRM (Customer Relationship Management) system contains plenty of textual interaction features between sales and customers, traditional techniques such as Click Through Rate (CTR) prediction struggle with processing the complex information inherent in natural language features, which limits their effectiveness in sales lead ranking. Bridging this gap is critical for enhancing business intelligence and decision-making. Recently, the emergence of large language models (LLMs) has opened new avenues for improving recommendation systems, this study introduces asLLR (LLM-based Leads Ranking in Auto Sales), which integrates CTR loss and Question Answering (QA) loss within a decoder-only large language model architecture. This integration enables the simultaneous modeling of both tabular and natural language features. To verify the efficacy of asLLR, we constructed an innovative dataset derived from the customer lead pool of a prominent new energy vehicle brand, with 300,000 training samples and 40,000 testing samples. Our experimental results demonstrate that asLLR effectively models intricate patterns in commercial datasets, achieving the AUC of 0.8127, surpassing traditional CTR estimation methods by 0.0231. Moreover, asLLR enhances CTR models when used for extracting text features by 0.0058. In real-world sales scenarios, after rigorous online A/B testing, asLLR increased the sales volume by about 9.5% compared to the traditional method, providing a valuable tool for business intelligence and operational decision-making.