Publications
Explore a selection of our recent research on some of the most complex and interesting challenges in AI.
259 publications
-
- 10 July 2026
- Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety Alignment
-
- 6 July 2026
- The Case for Globally Beneficial Technology
-
- 2 July 2026
- Towards Structural Understanding of LLM Overthinking
-
- 26 June 2026
- Bridging the Scale Gap: Augmenting Human Red-Teaming to Uncover Latent Risks in T2I Models
-
- 26 June 2026
- Real-Time Group Dynamics with LLM Facilitation: Evidence from a Charity Allocation Task
-
- 25 June 2026
- Going PLACES: Participatory Localized Red Teaming forText-to-Image Safety in the Global South
-
- 15 June 2026
- Artificial Minds, Human Disagreement: The Politics of AI Consciousness
-
- 12 June 2026
- From AGI to ASI
-
- 4 June 2026
- Solipsistic superintelligence is unlikely to be cooperative
-
- 28 May 2026
- Gram: Assessing sabotage propensities via automated alignment auditing
-
- 28 May 2026
- Realistic honeypot evaluations for scheming propensity
-
- 6 May 2026
- Did US Worker Retraining Reduce Participant Automation Exposure?
-
- 25 April 2026
- ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation
-
- 23 April 2026
- Dynamic Reflections: Probing Video Representations with Text Alignment
-
- 22 April 2026
- Image Generators are Generalist Vision Learners
-
- 22 March 2026
- Strategic Tradeoffs Between Humans and AI in Multi-Agent Bargaining
-
- 10 March 2026
- The Abstraction Fallacy: Why AI Can Simulate But Not Instantiate Consciousness
-
- 15 February 2026
- Simplicity and Complexity in Combinatorial Optimization
-
- 12 February 2026
- Decoding Safety Feedback from Diverse Raters: A Data-driven Lens on Responsiveness to Severity
-
- 5 February 2026
- Hybrid neural–cognitive models reveal how memory shapes human reward learning
-
- 9 January 2026
- TRecViT: A Recurrent Video Transformer
-
- 3 December 2025
- Capturing Human Preferences with Reward Features
-
- 21 November 2025
- Imitation Learning is Probably Existentially Safe
-
- 4 November 2025
- To Mask or to Mirror: Human-AI Alignment in Collective Reasoning
-
- 30 October 2025
- A Pragmatic View of AI Personhood
-
- 29 September 2025
- AI-Generated Video Detection via Perceptual Straightening
-
- 24 September 2025
- EmbeddingGemma: Powerful and Lightweight Text Representations
-
- 24 September 2025
- Video models are zero-shot learners and reasoners
-
- 18 September 2025
- Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models
-
- 4 September 2025
- Improving cosmological reach of LIGO usingDeep Loop Shaping