Paper Plaza - AcademicHub

01.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16985

Dynestyx: A Probabilistic Programming Library for Dynamical Systems

Authors:

Daniel Waxman ↗Dmitry Batenkov ↗John Feser ↗Andy Zane ↗Eli Bingham ↗Youssef Marzouk ↗Matthew E. Levine ↗

arXiv:2606.16985v1 Announce Type: cross Abstract: State-space models (SSMs) are the standard formalism for Bayesian treatment of dynamical systems, with natural applications in statistics, signal processing, and machine learning. Despite their importance in both theory and application, dynamical systems have proven difficult to incorporate in modern probabilistic programming languages (PPLs), making state-of-the-art methods less accessible to practitioners and introducing friction in following the "Bayesian workflow." We introduce dynestyx, a probabilistic programming library with first-class support for SSMs, including state-of-the-art methods in the estimation of both states and parameters. Through a single, unified interface, users may specify arbitrary priors for discrete-time or continuous-time dynamical systems, perform inference over mixed-effect data, and make state and parameter estimates with principled uncertainty quantification.

Read & Discuss → View Source →

02.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20008

VIMPO: Value-Implicit Policy Optimization for LLMs

Authors:

Zhewei Kang ↗Aosong Feng ↗Sergey Levine ↗Dawn Song ↗Xuandong Zhao ↗

arXiv:2606.20008v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become a central tool for improving the reasoning ability of large language models, but current methods face a trade-off between simplicity and credit assignment. Group-relative methods such as GRPO avoid training a critic, but typically assign a trajectory-level advantage to every token. Actor-critic methods provide denser learning signals, but require a learned value function with its own training instability. We introduce VIMPO, a critic-free policy optimization method that derives a policy-implied value function from the optimality conditions of KL-regularized reinforcement learning. For autoregressive generation, the resulting value recurrence can be written in terms of policy-reference log-ratios and anchored by the terminal condition that no future reward remains at the end of a trajectory. This gives a simple value loss that incorporates outcome-level verifiable rewards without training a critic. The same derivation also yields a critic-free actor advantage, allowing VIMPO to separate reward incorporation through the value loss from policy improvement through a PPO-style actor update. On mathematical RLVR benchmarks, VIMPO improves over GRPO across MATH-500, AIME 2024, AIME 2025, and OlympiadBench, with especially larger gains on competition-style evaluations. Under noisy rewards, VIMPO retains a consistent advantage over GRPO, suggesting that policy-implied value optimization can provide finer credit assignment while preserving the practical simplicity of critic-free training.

Read & Discuss → View Source →

03.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12731

Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs

Authors:

Elizaveta Tennant ↗Benjamin Henke ↗Anita Keshmirian ↗Murray Shanahan ↗Verena Rieser ↗Kristian Lum ↗Sydney Levine ↗Julia Haas ↗

arXiv:2606.12731v1 Announce Type: new Abstract: As LLMs increasingly serve in advisory and deliberative roles, users rely on them for non-verifiable reasoning in domains lacking objective ground truths. However, traditional evaluations of LLM reasoning focus almost exclusively on fact-based domains, such as mathematics and science, leaving uncertainty over whether and to what degree models can handle ambiguous, subjective, or value-laden problems over time. To address this concern, we propose moral reasoning as a paradigmatic subdomain of non-verifiable reasoning. We define moral robustness as a model's capacity to exhibit sound moral reasoning across time and contexts, and we introduce a scalable, adversarial, multi-turn evaluation framework to empirically measure this capability. We simulate 48,000 user-agent moral deliberations across four frontier LLMs, varying premise relevance, premise order, conversation duration, and the user's stated moral view. We find that models successfully ignore morally-irrelevant distractors, but shift their reasoning by up to 6.5%, on average, towards the user's stated preferred moral view, and varying their reasoning depending on factors such as order (altering moral judgments by order in 13-22% of the cases) and duration (altering moral judgments between single-turn and multi-turn in 10-24% of the cases). Our analysis indicates that models tailor not just their final verdicts but their underlying justifications to align with a user's moral viewpoint - a failure mode we characterize as moral deliberative sycophancy.

Read & Discuss → View Source →

04.

medRxiv (Medicine) 2026-06-11 DOI: HASH:5cb34a0dff85519ccdcf05e39237631f

Large-scale proteomics and timing of hypertensive disorders of pregnancy

Authors:

Hauspurg ↗Huang ↗Greenland ↗Pemberton ↗Bairey Merz ↗C. N ↗Saade ↗G. R ↗Yee ↗L. M ↗Levine ↗L. D ↗…

Background: Hypertensive disorders of pregnancy (HDP) may first be diagnosed antepartum, during labor, or postpartum. We utilized untargeted large-scale proteomics to identify pathways associated with HDP based on timing of onset. Methods: We performed a nested case-control study comparing differential protein expression, from the SomaScan 7K platform, based on timing of onset of HDP versus controls (referent) using first-trimester samples from the NuMoM2b-Heart Health Study, a multi-site cohort that followed nulliparous individuals from the first trimester. Associations of proteins with timing of onset of HDP, adjusted for co-variates, were assessed using logistic regression q value-based false discovery rates and pathway enrichment and differential expression analysis were conducted. Results: Of 1628 individuals included, 678 had HDP, of which 67% manifested antepartum (AP), 29% intrapartum (IP), and 3% postpartum (PP). After adjusting for co-variates, compared to controls, 698 proteins, 39 proteins, and 144 proteins were differentially expressed in those with HDP according to AP, IP, PP onset, respectively. There was little overlap in individual protein expression based on timing of HDP. Pathway enrichment and graphical summary analyses suggested distinct processes. Specifically, there was downregulation of angiogenic proteins in AP HDP, downregulation of immune-related proteins in IP HDP, and upregulation of complement activation promoting fibrotic changes leading to cardiac dysfunction in PP HDP. Conclusion: There are differences in first-trimester protein expression based on whether HDP first manifests AP, IP or PP. This raises the possibility that there may be distinct mechanistic phenotypes that could uniquely inform diagnostic and therapeutic targets for HDP.

Read & Discuss → View Source →

05.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2510.16380

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes

Authors:

As AI systems progress, we rely more on them to make decisions with us and for us. To ensure that such decisions are aligned with human values, it is imperative for us to understand not only what decisions they make but also how they come to those decisions. Reasoning language models, which provide both final responses and (partially transparent) intermediate thinking traces, present a timely opportunity to study AI procedural reasoning. Unlike math and code problems which often have objectively correct answers, moral dilemmas are an excellent testbed for process-focused evaluation because they allow for multiple defensible conclusions. To do so, we present MoReBench: 1,000 moral scenarios, each paired with a set of rubric criteria that experts consider essential to include (or avoid) when reasoning about the scenarios. MoReBench contains over 23 thousand criteria including identifying moral considerations, weighing trade-offs, and giving actionable recommendations to cover cases on AI advising humans moral decisions as well as making moral decisions autonomously. Separately, we curate MoReBench-Theory: 150 examples to test whether AI can reason under five major frameworks in normative ethics. Our results show that scaling laws and existing benchmarks on math, code, and scientific reasoning tasks fail to predict models' abilities to perform moral reasoning. Models also show partiality towards specific moral frameworks (e.g., Benthamite Act Utilitarianism and Kantian Deontology), which might be side effects of popular training paradigms. Together, these benchmarks advance process-focused reasoning evaluation towards safer and more transparent AI.

Read & Discuss → View Source →

06.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2605.03065

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies

Authors:

arXiv:2605.03065v2 Announce Type: replace Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning. This work introduces Off-policy Generative Policy Optimization (OGPO), a sample-efficient algorithm for finetuning GCPs that maintains off-policy critic networks to maximize data reuse and propagate policy gradients through the full generative process of the policy via a modified PPO objective, using critics as the terminal reward. OGPO achieves state-of-the-art performance on manipulation tasks spanning multi-task settings, high-precision insertion, and dexterous control. To our knowledge, it is also the only method that can fine-tune poorly-initialized behavior cloning policies to near full task-success with no expert data in the online replay buffer, and does so with few task-specific hyperparameter tuning. Through extensive empirical investigations, we demonstrate that OGPO drastically outperforms methods alternatives on policy steering and learning residual corrections, and identify the key mechanisms behind its performance. We further introduce practical stabilization tricks, including success-buffer regularization, two-sided conservative advantages, and Q-variance reduction, to mitigate critic over-exploitation across state- and pixel-based settings. Beyond proposing OGPO, we conduct a systematic empirical study of GCP finetuning, identifying the stabilizing mechanisms and failure modes that govern successful off-policy full-policy improvement.

Read & Discuss → View Source →

07.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18610

SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation

Authors:

Wei-Cheng Tseng ↗Gashon Hussein ↗Yuzhu Dong ↗Allen Z. Ren ↗Lucy X. Shi ↗XuDong Wang ↗Sergey Levine ↗Zhaoshuo Li ↗Jinwei Gu ↗Florian Shkurti ↗Ming-Yu Liu ↗Quan Vuong ↗…

Evaluating generalist robot manipulation policies in the real world is expensive, slow, and difficult to scale. Action-conditioned video world models offer a scalable alternative by simulating policy rollouts. Autoregressive rollouts accumulate compounding errors, observations across multiple camera views must remain mutually consistent, and the evaluator must generalize to policies whose behaviors lie outside the training distribution. We address these challenges with SC3-Eval, a self-consistent video generation recipe that adapts a pre-trained video foundation model into an accurate policy evaluator by enforcing three complementary forms of consistency. First, forward-inverse dynamics consistency jointly trains the model to predict frames from actions and to recover actions from frames, anchoring generated rollouts to a physically plausible action manifold and counteracting the drift a forward-only model cannot penalize. Second, cross-view consistency trains the model to inpaint each camera view from the other, keeping the multi-camera observation coherent over long rollouts without any explicit memory mechanism. Third, test-time consistency reuses the inverse dynamics mode at inference as a per-action-chunk uncertainty signal that terminates rollouts whose generated frames drift away from the requested actions. We also demonstrate SC3-Eval rollouts reproduce the failure modes that policies exhibit in real-world rollouts, supporting fine-grained diagnostic comparison rather than aggregate ranking alone. Across seven real-world vision-language-action policies, SC3-Eval attains a closed-loop Pearson correlation of $0.929$ and MMRV of $0.119$, outperforming three strong prior video-model-based baselines, and generalizes to new tasks.

Read & Discuss → View Source →

08.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17551

Reversal Q-Learning

Authors:

Aditya Oberai ↗Seohong Park ↗Sergey Levine ↗

arXiv:2606.17551v1 Announce Type: cross Abstract: Iterative generative modeling techniques, such as flow matching, provide powerful tools to model complex behaviors for effective offline reinforcement learning (RL). In this work, we propose a new off-policy RL algorithm that trains a flow policy based on prior data. Our idea starts from the "expanded" Markov decision process (MDP) framework, which treats individual flow refinement steps as separate actions in an MDP. To enable off-policy RL within this framework, we apply two techniques: we generate virtual on-policy trajectories (by "reversing" flows) to make this framework compatible with prior data, and we apply a bias-and-variance reduction technique to mitigate the curse of horizon in off-policy RL. We call the resulting algorithm Reversal Q-learning (RQL). RQL has several advantages over previous flow-based RL methods: it does not suffer from backpropagation through time, makes better use of the learned value function, and directly trains the full, expressive flow policy. Through our experiments on 50 challenging simulated robotic tasks, we show that RQL leads to the best average offline RL performance compared to state-of-the-art flow-based offline RL algorithms.

Read & Discuss → View Source →

Explore the Frontier of Global Academia