Sketchify: An AI-Powered Visual Website Builder using Large Language Models and Canvas-based Wireframe Interpretation

Tact: A Zero-Cost, Browser-Based Pipeline for On-Demand Tactile Braille Storybooks

Braille literacy among blind school-age children has fallen sharply, in part because producing illustrated braille pages still requires specialized software and trained labor. We present Tact, a browser-based pipeline that converts a spoken or typed story idea into printable braille with a matching raised tactile illustration, without an account or mandatory cost and with an offline-capable path. The paper documents the engineering history of the system: its sighted-operator ethical model; hardware rationale for consumer fused-deposition modeling; physical braille geometry and printer calibration; local, hosted, and fallback language-model paths; a deterministic Grade 1 braille translator; verified page layout and pagination; a 93-shape hand-drawn tactile illustration library; and synthesized sound design for a voice-first interface. We report engineering verification, ethical commitments, limitations, and the work required before the system is ready for real blind and low-vision readers.

Chat2Map: A ReAct-based Agent Framework for Automated Web Map Generation from Natural Language Instructions

Chat2Map is presented, an agent framework for automated web map generation from natural-language instructions that integrates skill and tool grounding, runtime schema construction for uploaded GeoJSON and JSON files, and an iterative generate-execute- diagnose-repair loop based on runtime and visual feedback.

Remesher: Automate Character Pipelines with ComfyUI's API, Docker, and Agents

Remesher is a hands-on course about turning visual generative AI workflows into programmable character-production tools. Participants begin with a cloud-deployed ComfyUI environment, then build Remesher as a Python Typer CLI and agent-operable utility that submits workflows through ComfyUI’s API, monitors long-running jobs, and passes generated assets between image generation, image-to-3D reconstruction, texturing, and rigging stages. The course emphasizes a practical translation layer between artist-authored node graphs and production-oriented software: workflow JSON inspection, parameter overrides, artifact validation, failure recovery, and repeatable command-line execution. Building on prior SIGGRAPH work in ComfyUI education, cloud GPU deployment, and generative 3D integration, Remesher shifts attention from running visual workflows to packaging them as inspectable systems that humans and coding agents can operate. A central lesson is the path from CLI to agent skill: once a pipeline is exposed through clear commands, typed options, and observable outputs, agents can be taught to run, debug, and extend it without hiding the underlying workflow. Attendees leave with Remesher, a hands-on CLI and agent-operable utility, a reusable deployment pattern, and a model for making rapidly changing generative AI pipelines easier to reproduce, debug, and extend.

Smart Campus Assistant using RAG-based AI

This paper presents the design and implementation of intelligent chatbots using Retrieval-Augmented Generation architecture to derive accurate, context-based responses from domain-specific knowledge sources such as PDFs and CSV files. The proposed system integrates information retrieval mechanisms with large language models to overcome crucial limitations of traditional chatbots: hallucination, knowledge cut-off, and inability to access private organizational data. The proposed architecture uses a six-stage pipeline consisting of document ingestion, text splitting, and embedding generation with sentence transformers, semantic retrieval, and response generation via Large Language Models (LLMs). By preprocessing the PDF and CSV documents using a RecursiveCharacterTextSplitter and converting them into 384-dimensional semantic embeddings, the system works via a similarity-based retrieval of document chunks. For implementation, the LlamaIndex framework was used for data indexing and query orchestration, and HuggingFace Transformers for language modeling. Experimental validation conducted on the smart campus chatbot system demonstrated significant improvements in the accuracy, relevance and transparency of responses across education, student services, and administrative support domains compared with a standalone language model. Because of its modular design, it supports a wide range of domain-specific topics without the combinatorial costs of re-training. This is another important application for systems that require regular updates and accurate information. Overall, the proposed framework provides a simple and practical approach for easily implementing domain-aware chatbots.

A Typography Benchmark for Co-Creative Graphic-Design Agents

From Visual Widgets to UI Code: Efficient Tool-Grounded Generation

Existing screenshot-to-code systems face a trade-off between flexibility and controllability. Direct multimodal generation can hallucinate visible details, whereas structured pipelines reduce such errors through component-wise decomposition, predefined templates, and customized intermediate representations. These structures, however, introduce additional generative orchestration and restrict outputs to designs covered by the representation. We investigate whether selective tool grounding can improve the fidelity--efficiency trade-off of direct widget-to-code generation. We introduce \textbf{WidgetGen}, a lightweight tool-grounded framework that extracts observable text and color evidence, performs high-level layout and optional chart reasoning, and directly generates executable JavaScript XML (\emph{JSX}). This design reduces reliance on component-wise generation while avoiding a fixed UI schema. Across six multimodal models and \(1{,}000\) held-out widgets, WidgetGen outperforms direct prompting and the structured Widget2Code pipeline on most visual reconstruction metrics, with consistent gains in area, legibility, and style. Finally, reconstruction-derived image-code pairs improve six Qwen-family open-weight models across every reported metric through supervised fine-tuning. These results establish WidgetGen as a strong lightweight baseline and show that selective evidence grounding offers an effective alternative to extensive representation constraints.