BS
Bernhard Schölkopf
cs.LGstat.MLcs.AIcs.CLcs.CVcs.ROstat.MEastro-ph.IMmath.STstat.TH
On Valency
published · living versionsW_7bwbnhgy·v1 · currentpublished
ARENA: Active Region attENtion Aggregation for interpretable solar flare prediction
with Luis Bauer, Annalena Kofler, Andrés Asensio Ramos, Aparna Venkataramanasastry +1
1 version
W_a5vmwnms·v1published
Preprints & journals
635 papers in the corpus · 1998–2026Binary Discrete Diffusion: Candidate-Set Diffusion for Logic and Planning Tasks2610.28543v1 · Rodrigo Casado Noguerales, Dimitri von Rutte, Bernhard Scholkopf et al.2026 · 0 citationsarXivon Valency
AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment2610.24264v3 · Eric Zhang, Terry Jingchen Zhang, Chijioke Ugwuanyi et al.2026 · 0 citationsarXiv
Declarative Reactive Robot Behaviors from Imperative Language Models2610.17083v1 · Vincent Berenz, Tasha Kim, Bernhard Scholkopf2026 · 0 citationsarXiv
DSReg: Provably Recovering Individual World Latents without Reconstruction2610.09457v1 · Yujia Zheng, David Klindt, Randall Balestriero et al.2026 · 0 citationsarXiv
When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting2610.08718v1 · Vedant Palit, Florent Draye, Nicolas Zucchet et al.2026 · 0 citationsarXiv
WAMJET: A Harness for World Action Model Acceleration2610.03797v3 · Le Chen, Lixin Liu, Jan Schneider et al.2026 · 0 citationsarXiv
CIDER-FM: Foundation Models for Causal Inference from Diverse Experimental Regimes2609.39523v1 · Yuche Gao, Arik Reuter, Siyuan Guo et al.2026 · 0 citationsarXiv
ABC: Advantage-Based Control Variates for Reinforcement Learning with Verifiable Rewards2609.36058v1 · Hsiao-Ru Pan, Florent Draye, Bernhard Scholkopf2026 · 0 citationsarXiv
TabPFN-3.5: Technical Report2609.17895v2 · Benjamin Jager, Nick Erickson, L'eo Grinsztajn et al.2026 · 0 citationsarXiv
RAPTOR: Role-Aware Private Training for Mixture-of-Experts2609.05770v1 · Duc Dm, Khai Le-Duc, Nguyen Do et al.2026 · 0 citationsarXiv
How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution2608.27510v1 · Vedant Palit, Florent Draye, Terry Jingchen Zhang et al.2026 · 0 citationsarXiv
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training2608.24845v1 · Andreas Hochlehnert, Marianna Nezhurina, Mehdi Cherti et al.2026 · 0 citationsarXiv
Advancing Open and Reproducible Relational Learning: RelArena-, TabPFN-Rel and RPI2608.16319v2 · Adrian Hayler, Klemens Floge, Alan Arazi et al.2026 · 0 citationsarXiv
Where Does Generative Difficulty Reside? An Empirical Study of Target Representations2608.00626v1 · Marcel Plocher, Bernhard Scholkopf, Andreas Geiger et al.2026 · 0 citationsarXiv
How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs?2607.18114v2 · Prakhar Gupta, Terry Jingchen Zhang, Florent Draye et al.2026 · 0 citationsarXiv
From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery2607.12474v2 · Ingmar Posner, Anson Lei, Bernhard Scholkopf2026 · 0 citationsarXiv
When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games2607.05132v2 · Jerick Shi, Terry Jingcheng Zhang, Bernhard Scholkopf et al.2026 · 0 citationsarXiv
What Does a Discrete Diffusion Model Learn? One Reverse Process in Three Coordinates2607.05381v2 · Rodrigo Casado Noguerales, Bernhard Scholkopf, Thomas Hofmann et al.2026 · 0 citationsarXiv
PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding2606.31148v3 · Duc Cao Dinh, Khai Le-Duc, Florent Draye et al.2026 · 0 citationsarXiv
Flexible Gravitational-Wave Parameter Estimation with Transformers.42430626 · Kofler, Annalena, Dax, Maximilian, Green, Stephen R et al.2026 · 1 citationPhysical review letters. 2026;136(25):251401
Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR2606.25178v2 · Yongjin Yang, Jiarui Liu, Yinghui He et al.2026 · 0 citationsarXiv
Direct Imaging Discovery of Giant Exoplanet Pictoris d: A Decade-Long Game of Hide-and-Seek2606.23801v2 · Ben J. Sutlieff, Markus J. Bonse, Valentin Christiaens et al.2026 · 3 citationsApJL 1006 L10 (2026)
Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories2606.22527v1 · Merve Kocabas, Gege Gao, Bernhard Scholkopf et al.2026 · 0 citationsProceedings of the European Conference on Computer Vision (ECCV), 2026
Sensorimotor World Models: Perception for Action via Inverse Dynamics2606.20104v1 · Petr Ivashkov, Randall Balestriero, Bernhard Scholkopf2026 · 0 citationsarXiv
On the Variance of Temporal Difference Learning and its Reduction Using Control Variates2606.20357v1 · Hsiao-Ru Pan, Bernhard Scholkopf2026 · 0 citationsarXiv
Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning2606.20411v1 · Hsiao-Ru Pan, Bernhard Scholkopf2026 · 0 citationsarXiv
Slots, Transitions, Loops: Learning Composable World Models for ARC2606.12316v1 · Gege Gao, Bernhard Scholkopf, Andreas Geiger2026 · 0 citationsarXiv
Echoes of the Prior: A Computational Phenomenology of Forgetting2606.12340v1 · Gege Gao, Bernhard Scholkopf, Andreas Geiger2026 · 0 citationsProc. ACM Comput. Graph. Interact. Tech, ACM SIGGRAPH, 2026
PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf2606.08857v1 · Jiarui Liu, Terry Jingchen Zhang, Ryan Faulkner et al.2026 · 0 citationsarXiv
STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations2606.05165v1 · Rishit Dagli, Abir Harrasse, Luke Zhang et al.2026 · 0 citationsarXiv
A critical perspective on finite sample conformal prediction theory in medical applications.42224800 · Kladny, Klaus-Rudolf, Schölkopf, Bernhard, Koch, Lisa et al.2026 · 3 citationsArtificial intelligence in medicine. 2026;180:103462
PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective2605.28819v1 · Yangyi Huang, Ruotian Peng, Zeju Qiu et al.2026 · 0 citationsarXiv
Learning to Reason Efficiently with A* Post-Training2605.24597v1 · Andreas Opedal, Francesco Ignazio Re, Abulhair Saparov et al.2026 · 0 citationsarXiv
Riemannian Networks over Full-Rank Correlation Matrices2605.19073v1 · Ziheng Chen, Xiaojun Wu, Bernhard Scholkopf et al.2026 · 0 citationsarXiv
Learning POMDP World Models from Observations with Language-Model Priors2605.13740v1 · Valentin Six, Frederik Panse, Mathis Fajeau et al.2026 · 0 citationsarXiv
TabPFN-3: Technical Report2605.13986v2 · L'eo Grinsztajn, Klemens Floge, Oscar Key et al.2026 · 3 citationsarXiv
Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AI2605.08426v3 · Xuanqiang Angelo Huang, Charlie Tharas, Samuele Marro et al.2026 · 0 citationsarXiv
Adaptive Inverted-Index Routing for Granular Mixtures-of-Experts2605.04952v2 · Klaus-Rudolf Kladny, Maximilian Mordig, Bernhard Scholkopf et al.2026 · 0 citationsarXiv
Neural Posterior Estimation of Terrain Parameters from Radar Sounder Data2605.08179v2 · Jordy Dal Corso, Annalena Kofler, Marco Cortellazzi et al.2026 · 0 citationsarXiv
Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution2605.02640v2 · Ruta Binkyte, Ivaxi Sheth, Zhijing Jin et al.2026 · 1 citationProceedings of the 43rd International Conference on Machine Learning, Seoul, South Korea. PMLR 306, 2026
Bounded Ratio Reinforcement Learning2604.18578v3 · Yunke Ao, Le Chen, Bruce D. Lee et al.2026 · 0 citationsarXiv
Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints2604.15664v2 · Xinge Liu, Terry Jingchen Zhang, Bernhard Scholkopf et al.2026 · 0 citationsarXiv
Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks2604.09487v4 · Jan Schneider, Mridul Mahajan, Le Chen et al.2026 · 0 citationsarXiv
Drifting Fields are not Conservative2604.06333v3 · Leonard T. Franz, Sebastian Hoffmann, Tim Weiland et al.2026 · 0 citationsarXiv
Eccentricity constraints disfavor single-single capture in nuclear star clusters as the origin of all LIGO-Virgo-KAGRA binary black holes2603.29019v2 · Nihar Gupte, M. Coleman Miller, Rhiannon Udall et al.2026 · 0 citationsarXiv
Rethinking Easy-to-Hard: Limits of Curriculum Learning in Post-Training for Deductive Reasoning2603.27226v1 · Maximilian Mordig, Andreas Opedal, Weiyang Liu et al.2026 · 0 citationsarXiv
Computational Arbitrage in AI Model Markets2603.22404v1 · Ricardo Olmedo, Bernhard Scholkopf, Moritz Hardt2026 · 0 citationsarXiv
CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs2603.21014v2 · Florent Draye, Vedant Palit, Abir Harrasse et al.2026 · 0 citationsarXiv
Deriving Hyperparameter Scaling Laws via Modern Optimization Theory2603.15958v1 · Egor Shulgin, Dimitri von Rutte, Tianyue H. Zhang et al.2026 · 0 citationsarXiv
When Do Language Models Endorse Limitations on Human Rights Principles?2603.04217v1 · Keenan Samway, Nicole Miu Takagi, Rada Mihalcea et al.2026 · 0 citationsarXiv
Career total: at least 1891 works. 635 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.