5 citations · 12 across the 23 of their papers we have counts for
23 papers
Long-term Measurements: Towards a Longitudinal Understanding of Human-AI Interactions
Nicole Mitchell, Dhruv Agarwal, Maty Bohacek +2
Language models have taken on the role of a very new type of technology, by virtue of their "human-ness" and rapid integration into users' daily lives. This combination of features…
Detecting and Controlling Sycophancy with Cascading Linear Features
Maty Bohacek, Rishub Jain, Nicholas Dufour +3
Interpreting and controlling model behaviors through activation steering methods requires many pairs of contrastive samples that clearly exhibit desired or undesired behavior. Thes…
Positive Alignment: Artificial Intelligence for Human Flourishing
Ruben Laukkonen, Seb Krier, Chloé Bakalar +13
Existing alignment research is dominated by concerns about safety and preventing harm: safeguards, controllability, and compliance. This paradigm of alignment parallels early psych…
The DeepSpeak-Agentic Dataset
Sarah Barrington, Maty Bohacek, Hany Farid
We present DeepSpeak-Agentic, a dataset of videos comprising over 37 hours of semi-structured conversations between a human and an embodied AI agent. We use this dataset to evaluat…
Unsteady Metrics and Benchmarking Cultures of AI Model Builders
Stefan Baack, Christo Buschek, Maty Bohacek
The primary way to establish and compare competencies in foundation and generative AI models has shifted from peer-reviewed literature to press releases and company blog posts, whe…
The Impact of AI-Generated Text on the Internet
Jonas Dolezal, Sawood Alam, Mark Graham +1
The proliferation of AI-generated and AI-assisted text on the internet is feared to contribute to a degradation in semantic and stylistic diversity, factual accuracy, and other neg…
Compliance Rating Scheme: A Data Provenance Framework for Generative AI Datasets
Matyas Bohacek, Ignacio Vilanova Echavarri
Generative Artificial Intelligence (GAI) has experienced exponential growth in recent years, partly facilitated by the abundance of large-scale open-source datasets. These datasets…
LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer
Raina Panda, Daniel Fein, Arpita Singhal +3
Artistic style transfer in generative models remains a significant challenge, as existing methods often introduce style only via model fine-tuning, additional adapters, or prompt e…
Uncovering Competency Gaps in Large Language Models and Their Benchmarks
Maty Bohacek, Nino Scherrer, Nicholas Dufour +3
The evaluation of large language models relies heavily on standardized benchmarks. These benchmarks provide useful aggregated metrics, but can obscure (i) particular sub-areas wher…
Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders
Matyas Bohacek, Thomas Fel, Maneesh Agrawala +1
Despite their impressive performance, generative image models trained on large-scale datasets frequently fail to produce images with seemingly simple concepts -- e.g., human hands…
Dataset of News Articles with Provenance Metadata for Media Relevance Assessment
Tomas Peterka, Matyas Bohacek
Out-of-context and misattributed imagery is the leading form of media manipulation in today's misinformation and disinformation landscape. The existing methods attempting to detect…
Synthetic Human Action Video Data Generation with Pose Transfer
Vaclav Knapp, Matyas Bohacek
In video understanding tasks, particularly those involving human motion, synthetic data generation often suffers from uncanny features, diminishing its effectiveness for training.…
Towards an AI-Driven Video-Based American Sign Language Dictionary: Exploring Design and Usage Experience with Learners
Saad Hassan, Matyas Bohacek, Chaelin Kim +1
Searching for unfamiliar American Sign Language (ASL) signs is challenging for learners because, unlike spoken languages, they cannot type a text-based query to look up an unfamili…
Large Language Models and Provenance Metadata for Determining the Relevance of Images and Videos in News Stories
Tomas Peterka, Matyas Bohacek
The most effective misinformation campaigns are multimodal, often combining text with images and videos taken out of context -- or fabricating them entirely -- to support a given n…
Can Pose Transfer Models Generate Realistic Human Motion?
Vaclav Knapp, Matyas Bohacek
Recent pose-transfer methods aim to generate temporally consistent and fully controllable videos of human action where the motion from a reference video is reenacted by a new ident…
GenAI Confessions: Black-box Membership Inference for Generative Image Models
Matyas Bohacek, Hany Farid
From a simple text prompt, generative-AI image models can create stunningly realistic and creative images bounded, it seems, by only our imagination. These models have achieved thi…
Human Action CLIPs: Detecting AI-generated Human Motion
Matyas Bohacek, Hany Farid
AI-generated video generation continues its journey through the uncanny valley to produce content that is increasingly perceptually indistinguishable from reality. To better protec…
The DeepSpeak Dataset
Sarah Barrington, Maty Bohacek, Hany Farid
Deepfakes represent a growing concern across domains such as disinformation, fraud, and non-consensual media. In particular, the rise of video conference and identity-driven attack…
Nepotistically Trained Generative-AI Models Collapse
Matyas Bohacek, Hany Farid
Trained on massive amounts of human-generated content, AI-generated image synthesis is capable of reproducing semantically coherent images that match the visual appearance of its t…
Learning from What is Already Out There: Few-shot Sign Language Recognition with Online Dictionaries
Matyáš Boháček, Marek Hrúz
Today's sign language recognition models require large training corpora of laboratory-like videos, whose collection involves an extensive workforce and financial resources. As a re…
Fine-grained Czech News Article Dataset: An Interdisciplinary Approach to Trustworthiness Analysis
Matyáš Boháček, Michal Bravanský, Filip Trhlík +1
We present the Verifee Dataset: a novel dataset of news articles with fine-grained trustworthiness annotations. We develop a detailed methodology that assesses the texts based on t…
Combining Efficient and Precise Sign Language Recognition: Good pose estimation library is all you need
Matyáš Boháček, Zhuo Cao, Marek Hrúz
Sign language recognition could significantly improve the user experience for d/Deaf people with the general consumer technology, such as IoT devices or videoconferencing. However,…
Protecting President Zelenskyy against Deep Fakes
Matyáš Boháček, Hany Farid
The 2022 Russian invasion of Ukraine is being fought on two fronts: a brutal ground war and a duplicitous disinformation campaign designed to conceal and justify Russia's actions.…