YB
Yoshua Bengio
cs.LGstat.MLcs.AIcs.NEcs.CLcs.CVcs.CYeess.AScs.SDNeural Networks, Computer
On Valency
published · living versionsW_hbk3npz9·v1 · currentpublished
W_rjz3mxgb·v1published
Preprints & journals
719 papers in the corpus · 1990–2026Distribution-Based Regularization for Reward Fine-Tuning Diffusion and Flow Models2610.24897v1 · Romeo Passaro, Jeongjae Lee, Jong Chul Ye et al.2026 · 0 citationsarXiv
Evaluating Predictor-Corrector Dependence in Hard-Constrained Climate Emulators2610.23561v1 · Tianyu Zhang, Xinyu Wang, Zhenghan Tai et al.2026 · 0 citationsarXiv
GCAM-Gym: A Benchmark for Agent-Based Climate Policy Search2610.23569v1 · Tianyu Zhang, Zhenghan Tai, Xinyu Wang et al.2026 · 0 citationsarXiv
Defining and Generating Compositional Structure2610.20922v1 · Eric Elmoznino, Tejas Kasetty, Blaise Aguera y Arcas et al.2026 · 0 citationsarXiv
The Smart Buildings Challenge: Learning Foundation Models for Real-World Optimization at Scale2610.18511v1 · Judah Goldfeder, Ayush Rai, Philippe M. Wyder et al.2026 · 0 citationsarXiv
Multi-Objective Amortized CDRH3 Sequence Sampling Diversifies Promising Antibody Candidates2610.16920v1 · Joseph D. Viviano, Almer van der Sloot, Quentin Fournier et al.2026 · 0 citationsarXiv
Mixture of GFlowNets2610.17007v1 · Omar G. Younis, Joseph D. Viviano, Chirayu Anant Haryan et al.2026 · 0 citationsarXiv
PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution2610.04737v2 · Pierre-Luc St-Charles, Alessandro Palmas, Damiano Fornasiere et al.2026 · 0 citationsarXiv
What if automating AI R&D triggers an intelligence explosion?2609.36054v2 · Alan Chan, Christoph Winter, Andrew Barto et al.2026 · 0 citationsarXiv
AI Safety: Not Optional, Not Later2609.10630v1 · Qinghua Lu, Yoshua Bengio2026 · 0 citationsarXiv
Reducing Catastrophic Risk from AI with Systematic Monitoring and Evaluation of Rogue AI Progression2609.03189v2 · T. Bauer, W.P. Kegelmeyer, E. Begoli et al.2026 · 0 citationsarXiv
How to Verify Probabilistic Consistency of Predictive Models2608.11181v2 · Orr Paradise, Oliver Richardson, Yoshua Bengio et al.2026 · 0 citationsarXiv
Bayesian Symbolic Regression with Entropic Reinforcement Learning2608.09617v2 · Oussama Boussif, Mohammed Mahfoud, Younesse Kaddar et al.2026 · 0 citationsarXiv
The 2026 Singapore Consensus on Global AI Safety Research Priorities2608.14611v1 · Stephen Casper, Oskar Galeev, Yoshua Bengio et al.2026 · 0 citationsarXiv
Open Technical Problems in Open-Weight AI Model Risk Management2608.07514v1 · Stephen Casper, Kyle O'Brien, Shayne Longpre et al.2026 · 1 citationarXiv
Publisher Correction: Deep-learning-based virtual screening of antibacterial compounds.41203993 · Scalia, Gabriele, Rutherford, Steven T, Lu, Ziqing et al.2026 · 0 citationsNature biotechnology. 2026;44(7):1237
Safety from Honesty in a Disinterested AI Predictor2606.29657v2 · Yoshua Bengio, Oliver Richardson, Tom'as Gavenciak et al.2026 · 0 citationsarXiv
Autoregressive Boltzmann Generators2606.27361v1 · Danyal Rehman, Charlie B. Tan, Yoshua Bengio et al.2026 · 0 citationsarXiv
CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs2606.11063v2 · Joachim Schaeffer, Alexander Panfilov, Thomas Jiralerspong et al.2026 · 0 citationsarXiv
Adaptive Order Policies for Masked Diffusion2606.00295v3 · Jama Hussein Mohamud, Mohsin Hasan, Mirco Ravanelli et al.2026 · 0 citationsarXiv
Generative Recursive Reasoning2605.19376v4 · Junyeob Baek, Mingyu Jo, Minsu Kim et al.2026 · 0 citationsarXiv
When 2D Tasks Meet 1D Serialization: On Serialization Friction in Structured Tasks2604.27272v2 · Chung-Hsiang Lo, Lu Li, Diji Yang et al.2026 · 0 citationsarXiv
Language models recognize dropout and Gaussian noise applied to their activations2604.17465v3 · Damiano Fornasiere, Mirko Bronzi, Spencer Kitts et al.2026 · 0 citationsarXiv
Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models2604.17140v1 · Oliver E. Richardson, Mandana Samiei, Mehran Shakerinava et al.2026 · 0 citationsProceedings of the The 29th International Conference on Artificial Intelligence and Statistics, 2026
General Multimodal Protein Design Enables DNA-Encoding of Chemistry2604.05181v1 · Jarrid Rector-Brooks, Th'eophile Lambert, Marta Skreta et al.2026 · 5 citationsarXiv
A Comparative Study of Molecular Dynamics Approaches for Simulating Ionic Conductivity in Solid Lithium Electrolytes2603.28012v1 · Dounia Shaaban Kabakibo, F'elix Therrien, Yoshua Bengio et al.2026 · 0 citationsarXiv
The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning2603.17837v5 · Donghang Wu, Tianyu Zhang, Yuxin Li et al.2026 · 0 citationsarXiv
Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback2603.16928v1 · Thomas Jiralerspong, Flemming Kondrup, Yoshua Bengio2026 · 0 citationsarXiv
Imagining and building wise machines: the centrality of AI metacognition.41760502 · Johnson, Samuel G B, Karimi, Amir-Hossein, Bengio, Yoshua et al.2026 · 12 citationsTrends in cognitive sciences. 2026;30(10):854-868
International AI Safety Report 20262602.21012v1 · Yoshua Bengio, Stephen Clare, Carina Prunkl et al.2026 · 3 citationsarXiv
Navigating Ternary Doping in Li-ion Cathodes With Closed-Loop Multi-Objective Bayesian Optimization.41677075 · Zeinali Galabi, Nooshin, Liu, Cheng-Hao, Jain, Moksh et al.2026 · 3 citationsAdvanced materials (Deerfield Beach, Fla.). 2026;38(16):e19790
When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents2602.08235v2 · Jaylen Jones, Zhehao Zhang, Yuting Ning et al.2026 · 0 citationsarXiv
Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priors2602.04119v2 · Hyeonah Kim, Minsu Kim, Celine Roget et al.2026 · 0 citationsarXiv
Divergent creativity in humans and large language models.41565675 · Bellemare-Pepin, Antoine, Lespinasse, François, Thölke, Philipp et al.2026 · 48 citationsScientific reports. 2026;16(1):1279
Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies2601.11699v4 · Miles Brundage, Noemi Dreksler, Aidan Homewood et al.2026 · 1 citationarXiv
Discrete Feynman-Kac Correctors2601.10403v1 · Mohsin Hasan, Viktor Ohanesian, Artem Gazizov et al.2026 · 0 citationsarXiv
In-Context Reinforcement Learning through Bayesian Fusion of Context and Value Prior2601.03015v1 · Anais Berkes, Vincent Taboga, Donna Vakalis et al.2026 · 0 citationsarXiv
A Comedy of Estimators: On KL Regularization in RL Training of LLMs2512.21852v4 · Vedant Shah, Johan Obando-Ceron, Vineet Jain et al.2025 · 0 citationsarXiv
Hidden sampling biases inflate performance in gene regulatory network inference10.64898/2025.12.19.695616v2 · Stock, M., Ratajczak, F., Bertin, P. et al.2025 · 0 citationsbioRxiv
The Future of the AI Summit Series2601.02383v1 · Lucia Velasco, Charles Martinet, Henry de Zoete et al.2025 · 0 citationsarXiv
Sliding Window Recurrences for Sequence Models2512.13921v1 · Dragos Secrieru, Garyk Brixi, Yoshua Bengio et al.2025 · 0 citationsarXiv
FALCON: Few-step Accurate Likelihoods for Continuous Flows2512.09914v1 · Danyal Rehman, Tara Akhound-Sadegh, Artem Gazizov et al.2025 · 0 citationsarXiv
Adsorption energies are necessary but not sufficient to identify good catalysts2512.05938v1 · Shahana Chatterjee, Alexander Davis, Lena Podina et al.2025 · 0 citationsarXiv
International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management2511.19863v1 · Yoshua Bengio, Stephen Clare, Carina Prunkl et al.2025 · 2 citationsarXiv
Identifying indicators of consciousness in AI systems.41219038 · Butlin, Patrick, Long, Robert, Bayne, Tim et al.2026 · 54 citationsTrends in cognitive sciences. 2026;30(6):488-501
Scaling Latent Reasoning via Looped Language Models2510.25741v6 · Rui-Jie Zhu, Zixuan Wang, Kai Hua et al.2025 · 1 citationarXiv
Interpretable epistemic uncertainty decomposition in sequential generative models via polynomial chaos surrogates2510.21523v2 · Ram'on Nartallo-Kaluarachchi, Shashanka Ubaru, Ma\lgorzata J Zimo'n et al.2025 · 0 citationsarXiv
Deep-learning-based virtual screening of antibacterial compounds.41136774 · Scalia, Gabriele, Rutherford, Steven T, Lu, Ziqing et al.2026 · 17 citationsNature biotechnology. 2026;44(7):1154-1167
A Definition of AGI2510.18212v3 · Dan Hendrycks, Dawn Song, Christian Szegedy et al.2025 · 3 citationsarXiv
International AI Safety Report 2025: First Key Update: Capabilities and Risk Implications2510.13653v1 · Yoshua Bengio, Stephen Clare, Carina Prunkl et al.2025 · 3 citationsarXiv
Career total: 1490 works. 719 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.