Stable Diffusion is a Natural Cross-Modal Decoder for Layered AI-generated Image Compression

Recent advances in Artificial Intelligence Generated Content (AIGC) have garnered significant interest, accompanied by an increasing need to transmit and compress the vast number of AI-generated images (AIGIs). However, there is a noticeable deficiency in research focused on compression methods for AIGIs. To address this critical gap, we introduce a scalable cross-modal compression framework that incorporates multiple human-comprehensible modalities, designed to efficiently capture and relay essential visual information for AIGIs. In particular, our framework encodes images into a layered bitstream consisting of a semantic layer that delivers high-level semantic information through text prompts; a structural layer that captures spatial details using edge or skeleton maps; and a texture layer that preserves local textures via a colormap. Utilizing Stable Diffusion as the backend, the framework effectively leverages these multimodal priors for image generation, effectively functioning as a decoder when these priors are encoded. Qualitative and quantitative results show that our method proficiently restores both semantic and visual details, competing against baseline approaches at extremely low bitrates ( <0.02 bpp). Additionally, our framework facilitates downstream editing applications without requiring full decoding, thereby paving a new direction for future research in AIGI compression.

Equity in the Use of ChatGPT for the Classroom: A Comparison of the Accuracy and Precision of ChatGPT 3.5 vs. ChatGPT4 with Respect to Statistics and Data Science Exams

A college education historically has been seen as method of moving upward with regards to income brackets and social status. Indeed, many colleges recognize this connection and seek to enroll talented low income students. While these students might have their education, books, room, and board paid; there are other items that they might be expected to use that are not part of most college scholarship packages. One of those items that has recently surfaced is access to generative AI platforms. The most popular of these platforms is ChatGPT, and it has a paid version (ChatGPT4) and a free version (ChatGPT3.5). We seek to explore differences in the free and paid versions in the context of homework questions and data analyses as might be seen in a typical introductory statistics course. We determine the extent to which students who cannot afford newer and faster versions of generative AI programs would be disadvantaged in terms of writing such projects and learning these methods.

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration

Artificial intelligence generative models exhibit remarkable capabilities in content creation, particularly in face image generation, customization, and restoration. However, current AI-generated faces (AIGFs) often fall short of human preferences due to unique distortions, unrealistic details, and unexpected identity shifts, underscoring the need for a comprehensive quality evaluation framework for AIGFs. To address this need, we introduce FaceQ, a large-scale, comprehensive database of AI-generated Face images with fine-grained Quality annotations reflecting human preferences. The FaceQ database comprises 12,255 images generated by 29 models across three tasks: (1) face generation, (2) face customization, and (3) face restoration. It includes 32,742 mean opinion scores (MOSs) from 180 annotators, assessed across multiple dimensions: quality, authenticity, identity (ID) fidelity, and text-image correspondence. Using the FaceQ database, we establish F-Bench, a benchmark for comparing and evaluating face generation, customization, and restoration models, highlighting strengths and weaknesses across various prompts and evaluation dimensions. Additionally, we assess the performance of existing image quality assessment (IQA), face quality assessment (FQA), AI-generated content image quality assessment (AIGCIQA), and preference evaluation metrics, manifesting that these standard metrics are relatively ineffective in evaluating authenticity, ID fidelity, and text-image correspondence. The FaceQ database will be publicly available upon publication.

Invisible Watermarks: Attacks and Robustness

As Generative AI continues to become more accessible, the case for robust detection of generated images in order to combat misinformation is stronger than ever. Invisible watermarking methods act as identifiers of generated content, embedding image- and latent-space messages that are robust to many forms of perturbations. The majority of current research investigates full-image attacks against images with a single watermarking method applied. We introduce novel improvements to watermarking robustness as well as minimizing degradation on image quality during attack. Firstly, we examine the application of both image-space and latent-space watermarking methods on a single image, where we propose a custom watermark remover network which preserves one of the watermarking modalities while completely removing the other during decoding. Then, we investigate localized blurring attacks (LBA) on watermarked images based on the GradCAM heatmap acquired from the watermark decoder in order to reduce the amount of degradation to the target image. Our evaluation suggests that 1) implementing the watermark remover model to preserve one of the watermark modalities when decoding the other modality slightly improves on the baseline performance, and that 2) LBA degrades the image significantly less compared to uniform blurring of the entire image. Code is available at: https://github.com/tomputer-g/IDL_WAR

VersaGen: Unleashing Versatile Visual Control for Text-to-Image Synthesis

Despite the rapid advancements in text-to-image (T2I) synthesis, enabling precise visual control remains a significant challenge. Existing works attempted to incorporate multi-facet controls (text and sketch), aiming to enhance the creative control over generated images. However, our pilot study reveals that the expressive power of humans far surpasses the capabilities of current methods. Users desire a more versatile approach that can accommodate their diverse creative intents, ranging from controlling individual subjects to manipulating the entire scene composition. We present VersaGen, a generative AI agent that enables versatile visual control in T2I synthesis. VersaGen admits four types of visual controls: i) single visual subject; ii) multiple visual subjects; iii) scene background; iv) any combination of the three above or merely no control at all. We train an adaptor upon a frozen T2I model to accommodate the visual information into the text-dominated diffusion process. We introduce three optimization strategies during the inference phase of VersaGen to improve generation results and enhance user experience. Comprehensive experiments on COCO and Sketchy validate the effectiveness and flexibility of VersaGen, as evidenced by both qualitative and quantitative results.

Subversion Strategy Eval: Evaluating AI's stateless strategic capabilities against control protocols

AI control protocols are plans for usefully deploying AI systems in a way that is safe, even if the AI intends to subvert the protocol. Previous work evaluated protocols by subverting them with a human-AI red team, where an AI follows the human-written strategy. This paper investigates how well AI systems can generate and act on strategies for subverting control protocols whilst operating without private memory. Usually, decision-makers only need the ability to generate optimal plans. However, to subvert a protocol, an AI system must be able to reliably generate optimal plans in each context; coordinate plans with other instances of itself without communicating; and take actions with well-calibrated probabilities. We develop evaluations for a model's ability to generate subversion strategies and develop affordance experiments that help isolate component capabilities. Our initial evaluations with Claude-3.5-sonnet highlight reasons why statelessly strategizing to subvert control protocols might be hard. We hope that our work can serve as a starting point for evaluations aimed at assessing whether a model is capable of strategizing to subvert control protocols.

Agentic AI-Driven Technical Troubleshooting for Enterprise Systems: A Novel Weighted Retrieval-Augmented Generation Paradigm

Technical troubleshooting in enterprise environments often involves navigating diverse, heterogeneous data sources to resolve complex issues effectively. This paper presents a novel agentic AI solution built on a Weighted Retrieval-Augmented Generation (RAG) Framework tailored for enterprise technical troubleshooting. By dynamically weighting retrieval sources such as product manuals, internal knowledge bases, FAQs, and troubleshooting guides based on query context, the framework prioritizes the most relevant data. For instance, it gives precedence to product manuals for SKU-specific queries while incorporating general FAQs for broader issues. The system employs FAISS for efficient dense vector search, coupled with a dynamic aggregation mechanism to seamlessly integrate results from multiple sources. A Llama-based self-evaluator ensures the contextual accuracy and confidence of the generated responses before delivering them. This iterative cycle of retrieval and validation enhances precision, diversity, and reliability in response generation. Preliminary evaluations on large enterprise datasets demonstrate the framework's efficacy in improving troubleshooting accuracy, reducing resolution times, and adapting to varied technical challenges. Future research aims to enhance the framework by integrating advanced conversational AI capabilities, enabling more interactive and intuitive troubleshooting experiences. Efforts will also focus on refining the dynamic weighting mechanism through reinforcement learning to further optimize the relevance and precision of retrieved information. By incorporating these advancements, the proposed framework is poised to evolve into a comprehensive, autonomous AI solution, redefining technical service workflows across enterprise settings.

Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challenges

Scientific discovery is a complex cognitive process that has driven human knowledge and technological progress for centuries. While artificial intelligence (AI) has made significant advances in automating aspects of scientific reasoning, simulation, and experimentation, we still lack integrated AI systems capable of performing autonomous long-term scientific research and discovery. This paper examines the current state of AI for scientific discovery, highlighting recent progress in large language models and other AI techniques applied to scientific tasks. We then outline key challenges and promising research directions toward developing more comprehensive AI systems for scientific discovery, including the need for science-focused AI agents, improved benchmarks and evaluation metrics, multimodal scientific representations, and unified frameworks combining reasoning, theorem proving, and data-driven modeling. Addressing these challenges could lead to transformative AI tools to accelerate progress across disciplines towards scientific discovery.

Everyday AR through AI-in-the-Loop

This workshop brings together experts and practitioners from augmented reality (AR) and artificial intelligence (AI) to shape the future of AI-in-the-loop everyday AR experiences. With recent advancements in both AR hardware and AI capabilities, we envision that everyday AR -- always-available and seamlessly integrated into users' daily environments -- is becoming increasingly feasible. This workshop will explore how AI can drive such everyday AR experiences. We discuss a range of topics, including adaptive and context-aware AR, generative AR content creation, always-on AI assistants, AI-driven accessible design, and real-world-oriented AI agents. Our goal is to identify the opportunities and challenges in AI-enabled AR, focusing on creating novel AR experiences that seamlessly blend the digital and physical worlds. Through the workshop, we aim to foster collaboration, inspire future research, and build a community to advance the research field of AI-enhanced AR.

The Impact of AI Assistance on Radiology Reporting: A Pilot Study Using Simulated AI Draft Reports

Radiologists face increasing workload pressures amid growing imaging volumes, creating risks of burnout and delayed reporting times. While artificial intelligence (AI) based automated radiology report generation shows promise for reporting workflow optimization, evidence of its real-world impact on clinical accuracy and efficiency remains limited. This study evaluated the effect of draft reports on radiology reporting workflows by conducting a three reader multi-case study comparing standard versus AI-assisted reporting workflows. In both workflows, radiologists reviewed the cases and modified either a standard template (standard workflow) or an AI-generated draft report (AI-assisted workflow) to create the final report. For controlled evaluation, we used GPT-4 to generate simulated AI drafts and deliberately introduced 1-3 errors in half the cases to mimic real AI system performance. The AI-assisted workflow significantly reduced average reporting time from 573 to 435 seconds (p=0.003), without a statistically significant difference in clinically significant errors between workflows. These findings suggest that AI-generated drafts can meaningfully accelerate radiology reporting while maintaining diagnostic accuracy, offering a practical solution to address mounting workload challenges in clinical practice.