Month: January 2025

Abstract

In this chapter, we focus on speculation that engages with the present. We characterize this as a revealing of everyday conditions that (could) generate alternatives. We discuss approaches like Alternative Presents, breaching experiments, material speculations, situated retellings and biographical prototypes to draw out qualities of speculative reasoning. We also highlight the experiential alternative of things that work otherwise as a common method to critically unpack the present. Like the previous chapter, we apply our framework of leaps of imaginations, diverse epistemologies, ethical reflexivity and experiential alternatives to draw out how these speculations work. Lastly, we underscore speculation’s importance to broader research in design by exploring aspects of speculation in a wide range of investigations including repair, feminist and ethnographic theories in HCI, and ethnomethodological techniques like breaching experiments.

Abstract

In this chapter, we will review the advances that are being made in this new field of multimodal content generation and also discuss several challenges associated with this emerging technology. First, we will understand the machine learning techniques that drive this technology–most notably, the concept of adversarial learning and diffusion modeling. Then we will learn about how these techniques are applied to several input-to-output mappings, most notably, text-to-image generation, and the current state-of-the-art in image generation under these various input-to-output settings. Finally, we will discuss challenges in the evaluation and benchmarking of various dimensions of multimodal content generation, as well as the risks posed by malicious use of such technology.

Abstract

In this chapter, we will review the advances that are being made in this new field of multimodal content generation and also discuss several challenges associated with this emerging technology. First, we will understand the machine learning techniques that drive this technology–most notably, the concept of adversarial learning and diffusion modeling. Then we will learn about how these techniques are applied to several input-to-output mappings, most notably, text-to-image generation, and the current state-of-the-art in image generation under these various input-to-output settings. Finally, we will discuss challenges in the evaluation and benchmarking of various dimensions of multimodal content generation, as well as the risks posed by malicious use of such technology.