JF
Jakob Foerster
cs.LGcs.AIcs.MAcs.CLstat.MLcs.GTcs.NEcs.ROq-fin.TRcs.HC
On Valency
published · living versionsW_ar5nxgt6·v1 · currentpublished
LOB-Impact Benchmark: Emergent Market Impact in Generative Limit Order Book Models
with George Nigmatulin, Valentin Mohl, Sascha Frey, Kang Li +4
1 version
W_xbqgstd3·v1published
W_59hqxrjv·v1published
Preprints & journals
163 papers in the corpus · 2011–2026Adversarial Post-Training of Foundation Models for High-Frequency Trading2610.25604v1 · Alexandre Bismuth, Kang Li, Aramis Marti-Shahandeh et al.2026 · 0 citationsarXivon Valency
LOB-Impact Benchmark: Emergent Market Impact in Generative Limit Order Book Models2610.27100v1 · George Nigmatulin, Valentin Mohl, Sascha Frey et al.2026 · 0 citationsarXivon Valency
GitSwarm: Decentralized Compounding Inference2610.04862v1 · Vedant Shah, Ankur Samanta, Paras Dahal et al.2026 · 0 citationsarXiv
Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details2608.03644v1 · Maksymilian Wolski, Nicholas Hoernle, Johannes Forkel et al.2026 · 0 citationsarXiv
Autodata: An agentic data scientist to create high quality synthetic data2606.25996v3 · Ilia Kulikov, Chenxi Whitehouse, Tianhao Wu et al.2026 · 0 citationsarXiv
Modelling Opinion Dynamics at Scale with Deep MARL2606.07487v1 · Lukas Seier, Brandon Kaplowitz, Sebastian Towers et al.2026 · 0 citationsarXiv
Goal-Conditioned Agents that Learn Everything All at Once2605.23551v1 · Michael Matthews, Matthew Jackson, Michael Beukman et al.2026 · 0 citationsarXiv
Abstraction for Offline Goal-Conditioned Reinforcement Learning2605.22711v1 · Clarisse Wibault, Alexander Goldie, Antonio Villares et al.2026 · 0 citationsarXiv
Hierarchical Behaviour Spaces2604.24558v1 · Michael Tryfan Matthews, Anssi Kanervisto, Jakob Foerster et al.2026 · 0 citationsarXiv
Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training2604.11248v2 · Uljad Berdica, Jakob Foerster, Frank Hutter et al.2026 · 0 citationsarXiv
AIRA_2: Overcoming Bottlenecks in AI Research Agents2603.26499v2 · Karen Hambardzumyan, Nicolas Baldwin, Edan Toledo et al.2026 · 0 citationsarXiv
Evaluating AI-based Scientific Knowledge Synthesis with Epidemiological Systematic Reviews2603.22327v2 · Shreyansh Padarha, Ryan Othniel Kearns, Tristan Naidoo et al.2026 · 0 citationsarXiv
Measuring Progress in Reasoning Toward Mathematical Discovery with Automatic Verification2603.15617v2 · Erik Y. Wang, Sumeet R. Motwani, James V. Roggeveen et al.2026 · 0 citationsarXiv
Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments2603.06009v2 · Michael Beukman, Khimya Khetarpal, Zeyu Zheng et al.2026 · 0 citationsarXiv
Towards end-to-end automation of AI research.41882133 · Lu, Chris, Lu, Cong, Lange, Robert Tjarko et al.2026 · 110 citationsNature. 2026;651(8107):914-919
Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions2602.09987v5 · J Rosser, Robert Kirk, Edward Grefenstette et al.2026 · 0 citationsarXiv
An Empirical Study on Noisy Data and LLM Pretraining Loss Divergence2602.02400v1 · Qizhen Zhang, Ankush Garg, Jakob Foerster et al.2026 · 0 citationsarXiv
DéjàQ: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems2601.01931v1 · Willem Ropke, Samuel Coward, Andrei Lupu et al.2026 · 0 citationsarXiv
AI & Human Co-Improvement for Safer Co-Superintelligence2512.05356v2 · Jason Weston, Jakob Foerster2025 · 0 citationsarXiv
Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value2512.03399v1 · Joe Edelman, Tan Zhi-Xuan, Ryan Lowe et al.2025 · 0 citationsarXiv
Evolution Strategies at the Hyperscale2511.16652v2 · Bidipta Sarkar, Mattie Fellows, Juan Agustin Duque et al.2025 · 0 citationsarXiv
JaxMARL-HFT: GPU-Accelerated Large-Scale Multi-Agent Reinforcement Learning for High-Frequency Trading2511.02136v1 · Valentin Mohl, Sascha Frey, Reuben Leyland et al.2025 · 2 citations6th ACM International Conference on AI in Finance (ICAIF '25), November 15-18, 2025, Singapore, Singapore. ACM, New York, NY, USA, 9 pages
Measuring what Matters: Construct Validity in Large Language Model Benchmarks2511.04703v1 · Andrew M. Bean, Ryan Othniel Kearns, Angelika Romanou et al.2025 · 7 citationsarXiv
HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworks2510.04898v1 · Zheng Xiong, Kang Li, Zilin Wang et al.2025 · 0 citationsarXiv
Imagined Autocurricula2509.13341v2 · Ahmet H. Guzel, Matthew Thomas Jackson, Jarek Luca Liesen et al.2025 · 0 citationsarXiv
Painting the market: generative diffusion models for financial limit order book simulation and forecasting2509.05107v1 · Alfred Backhouse, Kang Li, Jakob Foerster et al.2025 · 0 citationsarXiv
How Should We Meta-Learn Reinforcement Learning Algorithms?2507.17668v2 · Alexander David Goldie, Zilin Wang, Jaron Cohen et al.2025 · 0 citationsarXiv
The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements2506.22419v2 · Bingchen Zhao, Despoina Magka, Minqi Jiang et al.2025 · 0 citationsarXiv
Ad-Hoc Human-AI Coordination Challenge2506.21490v2 · Tin Dizdarevi'c, Ravi Hammond, Tobias Gessler et al.2025 · 0 citationsarXiv
The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind2506.20664v1 · Andrei Lupu, Timon Willi, Jakob Foerster2025 · 0 citationsarXiv
Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs2506.18777v2 · Jonathan Cook, Silvia Sapora, Arash Ahmadian et al.2025 · 0 citationsarXiv
Intent Factored Generation: Unleashing the Diversity in Your Language Model2506.09659v1 · Eltayeb Ahmed, Uljad Berdica, Martha Elliott et al.2025 · 0 citationsarXiv
High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning2506.04051v2 · Tim Franzmeyer, Archie Sravankumar, Lijuan Liu et al.2025 · 0 citationsarXiv
StochasTok: Improving Fine-Grained Subword Understanding in LLMs2506.01687v3 · Anya Sims, Thom Foster, Klara Kaleb et al.2025 · 0 citationsarXiv
An Optimisation Framework for Unsupervised Environment Design2505.20659v2 · Nathan Monette, Alistair Letcher, Michael Beukman et al.2025 · 0 citationsarXiv
A Clean Slate for Offline Reinforcement Learning2504.11453v1 · Matthew Thomas Jackson, Uljad Berdica, Jarek Liesen et al.2025 · 0 citationsarXiv
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search2504.08066v1 · Yutaro Yamada, Robert Tjarko Lange, Cong Lu et al.2025 · 32 citationsarXiv
Meta-learning characteristics and dynamics of quantum systems2503.10492v1 · Lucas Schorling, Pranav Vaidhyanathan, Jonas Schuff et al.2025 · 0 citationsarXiv
MLGym: A New Framework and Benchmark for Advancing AI Research Agents2502.14499v1 · Deepak Nathani, Lovish Madaan, Nicholas Roberts et al.2025 · 5 citationsarXiv
Multi-Agent Risks from Advanced AI2502.14143v1 · Lewis Hammond, Alan Chan, Jesse Clifton et al.2025 · 12 citationsarXiv
LOB-Bench: Benchmarking Generative AI for Finance -- an Application to Limit Order Book Data2502.09172v2 · Peer Nagy, Sascha Frey, Kang Li et al.2025 · 0 citationsProceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada. PMLR 267, 2025
Expected Return Symmetries2502.01711v3 · Darius Muglich, Johannes Forkel, Elise van der Pol et al.2025 · 0 citationsarXiv
BTS: Harmonizing Specialized Experts into a Generalist LLM2502.00075v1 · Qizhen Zhang, Prajjwal Bhargava, Chloe Bi et al.2025 · 0 citationsarXiv
Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps2412.17113v1 · Benjamin Ellis, Matthew T. Jackson, Andrei Lupu et al.2024 · 3 citationsarXiv
Optimisation strategies for directed evolution without sequencing.39700257 · James, Jessica, Towers, Sebastian, Foerster, Jakob et al.2025 · 10 citationsPLoS computational biology. 2024;20(12):e1012695
The Complexity Dynamics of Grokking2412.09810v2 · Branton DeMoss, Silvia Sapora, Jakob Foerster et al.2024 · 3 citationsPhysica D: Nonlinear Phenomena 482 (2025) 134859
BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games2411.13543v2 · Davide Paglieri, Bart\lomiej Cupiał, Samuel Coward et al.2024 · 2 citationsarXiv
Noisy Zero-Shot Coordination: Breaking The Common Knowledge Assumption In Zero-Shot Coordination Games2411.04976v1 · Usman Anwar, Ashish Pandian, Jia Wan et al.2024 · 0 citationsarXiv
Beyond the Boundaries of Proximal Policy Optimization2411.00666v1 · Charlie B. Tan, Edan Toledo, Benjamin Ellis et al.2024 · 0 citationsarXiv
Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks2410.23208v2 · Michael Matthews, Michael Beukman, Chris Lu et al.2024 · 1 citationarXiv
Career total: at least 215 works. 163 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.