On the Horizon: Interactive and Compositional Deepfakes

Horvitz, Eric

doi:10.1145/3536221.3558175

Cited by 11 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If we do not develop effective ways to distinguish credible text from outright lies, we will likely lose faith in many things written on the Internet. This is related to the problem with the so-called deepfakes affecting images, audio, and video content, which at worst can lead to a “post-epistemic world where it is difficult or impossible to distinguish fact from fiction” (Horvitz, 2022 ).…”

Section: How the Usage Of Llms Will Affect Writingmentioning

confidence: 99%

AI and its consequences for the written word

Hellström

2024

Front. Artif. Intell.

View full text Add to dashboard Cite

The latest developments of chatbots driven by Large Language Models (LLMs), more specifically ChatGPT, have shaken the foundations of how text is created, and may drastically reduce and change the need, ability, and valuation of human writing. Furthermore, our trust in the written word is likely to decrease, as an increasing proportion of all written text will be AI-generated – and potentially incorrect. In this essay, I discuss these implications and possible scenarios for us humans, and for AI itself.

show abstract

Section: How the Usage Of Llms Will Affect Writingmentioning

confidence: 99%

AI and its consequences for the written word

Hellström

2024

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…Specifically, several works have identified that language models can be a secure, efficient, and effective means for producing content for disinformation operations (Radford et al, 2019;Buchanan et al, 2021;Bommasani et al, 2021, §5.2). Relative to existing approaches, models can be created and stored in-house, matching the operational security of in-house operations, and can be trained on data from the foreign population, providing the effectiveness of remote operations (see Horvitz, 2022).…”

Section: Disinformationmentioning

confidence: 99%

Holistic Evaluation of Language Models

Liang¹,

Bommasani²,

Lee³

et al. 2022

Preprint

View full text Add to dashboard Cite

Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models. First, we taxonomize the vast space of potential scenarios (i.e. use cases) and metrics (i.e. desiderata) that are of interest for LMs. Then we select a broad subset based on coverage and feasibility, noting what's missing or underrepresented (e.g. question answering for neglected English dialects, metrics for trustworthiness). Second, we adopt a multi-metric approach: We measure 7 metrics (accuracy, calibration, robustness, fairness, bias, toxicity, and efficiency) for each of 16 core scenarios to the extent possible (87.5% of the time), ensuring that metrics beyond accuracy don't fall to the wayside, and that trade-offs across models and metrics are clearly exposed. We also perform 7 targeted evaluations, based on 26 targeted scenarios, to more deeply analyze specific aspects (e.g. knowledge, reasoning, memorization/copyright, disinformation). Third, we conduct a large-scale evaluation of 30 prominent language models (spanning open, limited-access, and closed models) on all 42 scenarios, including 21 scenarios that were not previously used in mainstream LM evaluation. Prior to HELM, models on average were evaluated on just 17.9% of the core HELM scenarios, with some prominent models not sharing a single scenario in common. We improve this to 96.0%: now all 30 models have been densely benchmarked on a set of core scenarios and metrics under standardized conditions. Our evaluation surfaces 25 top-level findings concerning the interplay between different scenarios, metrics, and models. For full transparency, we release all raw model prompts and completions publicly 3 for further analysis, as well as a general modular toolkit for easily adding new scenarios, models, metrics, and prompting strategies. 4 We intend for HELM to be a living benchmark for the community, continuously updated with new scenarios, metrics, and models.

show abstract

“…If they entrain to synthetic models they may interact with, does this have any impact on their own behavior? It is important for both researchers and developers of this technology to devise ways to mitigate these risks, such as those suggested in [Hor22].…”

Section: Broader Impactmentioning

confidence: 99%

A Comprehensive Review of Data‐Driven Co‐Speech Gesture Generation

Nyatsanga

Kucherenko²,

Ahuja³

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

Gestures that accompany speech are an essential part of natural and efficient embodied human communication. The automatic generation of such co‐speech gestures is a long‐standing problem in computer animation and is considered an enabling technology for creating believable characters in film, games, and virtual social spaces, as well as for interaction with social robots. The problem is made challenging by the idiosyncratic and non‐periodic nature of human co‐speech gesture motion, and by the great diversity of communicative functions that gestures encompass. The field of gesture generation has seen surging interest in the last few years, owing to the emergence of more and larger datasets of human gesture motion, combined with strides in deep‐learning‐based generative models that benefit from the growing availability of data. This review article summarizes co‐speech gesture generation research, with a particular focus on deep generative models. First, we articulate the theory describing human gesticulation and how it complements speech. Next, we briefly discuss rule‐based and classical statistical gesture synthesis, before delving into deep learning approaches. We employ the choice of input modalities as an organizing principle, examining systems that generate gestures from audio, text and non‐linguistic input. Concurrent with the exposition of deep learning approaches, we chronicle the evolution of the related training data sets in terms of size, diversity, motion quality, and collection method (e.g., optical motion capture or pose estimation from video). Finally, we identify key research challenges in gesture generation, including data availability and quality; producing human‐like motion; grounding the gesture in the co‐occurring speech in interaction with other speakers, and in the environment; performing gesture evaluation; and integration of gesture synthesis into applications. We highlight recent approaches to tackling the various key challenges, as well as the limitations of these approaches, and point toward areas of future development.

show abstract

On the Horizon: Interactive and Compositional Deepfakes

Cited by 11 publications

References 18 publications

AI and its consequences for the written word

AI and its consequences for the written word

Holistic Evaluation of Language Models

A Comprehensive Review of Data‐Driven Co‐Speech Gesture Generation

Contact Info

Product

Resources

About