| Scalable and transferable black-box jailbreaks for language models via persona modulation R Shah*, FM Quentin*, S Pour*, A Tagade*, S Casper, J Rando SoLaR Workshop at NeurIPS '23, 2023 | 198 | 2023 |
| The SaTML'24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability S Casper, J Yun, J Baek, Y Jung, M Kim, K Kwon, S Park, H Moore, ... SaTML 2024 Competition Track, 2024 | 4 | 2024 |
| Prototype Generation: Robust Feature Visualisation for Data Independent Interpretability A Tagade, J Rumbelow ATTRIB Workshop at NeurIPS '23, 2023 | 2 | 2023 |
| Towards Data-Driven Scientific Discovery A Tagade, L Mckee-Reid, R Mccorkell, A Cusick, S Sosa, M Platre, ... AI 4 X 2025, 2025 | 1 | 2025 |
| Why do CNNs excel at feature extraction? A mathematical explanation V Nandakumar, A Tagade, T Liu arXiv preprint arXiv:2307.00919, 2023 | 1 | 2023 |
| LLM Assertiveness can be Mechanistically Decomposed into Emotional and Logical Components H Tsujimura, A Tagade arXiv preprint arXiv:2508.17182, 2025 | | 2025 |
| Growth Cost and Transport Efficiency Tradeoffs Define Root System Optimization Across Varying Developmental Stages and Environments in Arabidopsis K Faizi, P Mehta, A Maida, T Humphreys, E Berrigan, LMK Reid, ... bioRxiv, 2025 | | 2025 |
| Explaining Surface Layer Theory Departures in Marine Flux Profiles with Data-Driven Discovery J Foxabbott, L Mckee-Reid, A Cusick, R McCorkell, J Patel, J Rumbelow, ... arXiv preprint arXiv:2507.06425, 2025 | | 2025 |
| Benchmarking the Discovery Engine J Foxabbott, A Tagade, A Cusick, R McCorkell, L McKee-Reid, J Patel, ... arXiv preprint arXiv:2507.00964, 2025 | | 2025 |
| Strengthening LLM Identity Mitigates and Reverses Emergent Misalignment A Tagade, S Zhou, S Feng EurIPS 2025 Workshop on Metacognition in Generative AI, 2025 | | 2025 |
| Jailbreaking Language Models at Scale via Persona Modulation R Shah, QF Montixi, S Pour, A Tagade, J Rando | | 2024 |
| Towards Data-Driven Scientific Discovery Z Shams, A Cusick, S Sosa, JM Rumbelow, R McCorkell, A Tagade, ... AI4X 2025 International Conference, 0 | | |
| Revisiting the expressiveness of CNNs: a mathematical framework for feature extraction V Nandakumar, A Tagade, T Liu | | |
Javier RandoAnthropicVerified email at anthropic.com
