Paper Plaza - AcademicHub

01.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2606.14806

Semiclassical Gravity Efficiently Solves $\mathsf{NP}$-Complete Problems

Authors:

Matthew Fox ↗Chaitanya Karamchedu ↗Sotirios Mygdalas ↗

arXiv:2606.14806v1 Announce Type: cross Abstract: Assuming the gravitational field is classical and that it couples to quantum fields via the semiclassical Einstein field equations, we show that the weak-field dynamics of a massive and non-relativistic qubit can in principle be used to solve an $\mathsf{NP}$-complete problem in polynomial time. We attribute this vast computational power to the non-linear dynamics afforded by the semiclassical Einstein field equations. Consequently, the above two assumptions entail a violation of the Physical Extended Church–Turing Thesis, which we regard as evidence for the quantization of gravity.

Read & Discuss → View Source →

02.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.19145

OrthoReg: Orthogonal Regularization for Hybrid Symbolic-Neural Dynamical Systems

Authors:

Till Richter ↗Niki Kilbertus ↗

arXiv:2606.19145v1 Announce Type: cross Abstract: Dynamical systems are fundamental to modeling the natural world, yet modeling them involves a persistent trade-off: manually prescribed mechanistic models are interpretable by design but often overly simplistic and misspecified; in contrast, flexible data-driven neural methods lack physical insight. Hybrid modeling aims for the best of both worlds by combining a prescribed or symbolic, physics-based component with a flexible neural network. A critical challenge, however, is that the neural component may relearn mechanistic parts, yielding redundant and uninterpretable models, especially when the symbolic structure itself is discovered from data. Existing methods based on standard $L^2$ regularization rely on a projection argument that breaks when the symbolic component is learned through sparse discovery, allowing the neural augmentation to overlap with symbolic structure. We introduce OrthoReg (Orthogonal Regularization), which directly penalizes overlap between the symbolic and neural components, preventing symbolic structure from being absorbed by the neural residual. This yields a complementary decomposition: the symbolic part captures what the library can express, and the neural part captures what remains. On benchmark dynamical systems with partial library mismatch, OrthoReg improves symbolic recovery and out-of-distribution behavior.

Read & Discuss → View Source →

03.

arXiv (quant-ph) 2026-06-24 DOI: arXiv:2606.24334

Wigner's Phase Space Current for Variable Beam Splitters – Phase Space Rotations and Newtonian Trajectories

Authors:

Ole Steuernagel ↗Hsien-Yi Hsieh ↗Hua-Li Chen ↗Ray-Kuang Lee ↗

arXiv:2606.24334v1 Announce Type: new Abstract: Beam splitters allow us to superpose two continuous single mode quantum systems. To study the behaviour of beam splitters' strongly mode mixing dynamics we consider variable beam splitters acting on Wigner's phase space distribution, W , the evolution of which is governed by the continuity-equation {\partial \tau} W = - {\nabla} J. We derive the form of the corresponding Wigner current, J. J's form allows us to use a classical trajectories-approach to analyze the influence of the two modes on each other. We show that the dynamics for variable beam splitters amounts to a rotation confined within the plane of the two positions together with the same simultaneous rotation confined within the plane of the two momenta. In this way explicit and very transparent expressions for the rotated Wigner distributions and Wigner currents can be given in terms of classical trajectories. This helps us to gain deeper insights and perform geometrical analyses of the mixing of modes at beam splitters.

Read & Discuss → View Source →

04.

Nature (Science) 2026-06-10 DOI: HASH:056fae0968baea5f0e928496ff9a9b19

Structural basis for chaperone-guided assembly of RNA-induced silencing complex

Authors:

Young-Yoon Lee ↗

The RNA-induced silencing complex (RISC), comprising an Argonaute (AGO) protein and a small RNA, is the central effector in RNA silencing. Small RNAs are loaded onto AGO as bulky duplexes in an HSP70- and HSP90-dependent process1–3, but the molecular mechanism remains poorly understood. Here we identify the human AGO–HSP90–p23 complex, which captures AGO in an RNA-free state, termed the AGO maturation complex (AMC). The purified AMC enables RNA loading and AGO folding, faithfully recapitulating de novo RISC assembly. Using cryogenic electron microscopy, we determined the structure of AMC bound to a microRNA duplex. In contrast to its conformation in the RISC, AGO adopts a highly open conformation in the AMC: the N domain and the RNA-binding module (PAZ–MID–PIWI) are fully detached and anchored to opposite sides of the HSP90 dimer, connected solely by the unfolded L1 linker. This arrangement exposes a positively charged cleft that accommodates an RNA duplex. AGO folding is facilitated by a small RNA duplex containing a 5′-terminal phosphate—but not by single-stranded RNAs—revealing a role for the RNA duplex as a chaperone-like cofactor that directs AGO domain assembly. These findings elucidate the RISC assembly mechanism and establish the AMC as a molecular tool for probing optimal RNA features and chemical modifications for the rational design of small interfering RNA therapeutics. Our study also sheds light on how chaperones, together with ligands, can guide the folding of client proteins. Structures of the AGO maturation complex reveal how chaperones and an RNA duplex drive assembly of the RNA-induced silencing complex.

Read & Discuss → View Source →

05.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18853

Kernel of Partition Paths: A Unified Representation for Tree Ensembles

Authors:

Nicolas Mahler ↗

arXiv:2606.18853v1 Announce Type: cross Abstract: A recent line of work has reframed individual decision trees as linear models on engineered features associated with their splits, opening routes for oracle inequalities and feature-importance reinterpretation, but leaving open the question of what unified geometric object a forest induces when one indexes its feature map by nodes rather than by splits. The present paper studies that object. KPP indexes the feature map by the nodes of the forest, weighted by a path metric that turns each coordinate into a component of a squared-Euclidean path-isometric embedding. KPP unifies four pillars under a single non-diagonal Gram that carries a metric: prediction, exact additive attribution, deterministic Lipschitz robust radius in the KPP metric, and uniform Rademacher risk bounds for regression and classification under fixed, honest, or cross-fit conditioning. All probabilistic guarantees are conditional on the representation and are stated under three explicit conditioning regimes; the robust-radius guarantee is deterministic in the KPP metric rather than in a norm on the raw input. Conjectured fast-rate refinements for both regression and classification are stated as open problems and are not claimed as theorems.

Read & Discuss → View Source →

06.

arXiv (CS.AI) 2026-06-25 DOI: arXiv:2606.25181

Phoneme-Level Mispronunciation Screening in Polish-Speaking Children with an Explainable Assistant

Authors:

arXiv:2606.25181v1 Announce Type: cross Abstract: Early identification of speech sound errors in children is often limited by access to specialists, motivating lightweight screening tools that can operate outside the clinic. We present a screening pipeline for Polish-speaking children focused on sibilant substitutions, coupling a wav2vec2-based CTC token recognizer with alignment-based error typing and a template-grounded caregiver assistant for screening, not diagnosis. On a held-out test set of 10 unseen children comprising 559 utterances, the recognizer achieves 88.7 percent exact sequence match. As a conservative screening proxy, we flag a mismatch when the system emits substitution-evidence bracketed tokens at the target segment, yielding 72.9 percent precision, 61.4 percent recall, F1 = 0.67, and a 2.7 percent false-alarm rate on target-correct items. We describe the assistant's safety boundaries and outline a clinician-in-the-loop validation plan for future deployment.

Read & Discuss → View Source →

07.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16974

The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers

Authors:

Kevin L Coakley ↗Thijs Snelleman ↗Holger Hoos ↗Odd Erik Gundersen ↗

arXiv:2606.16974v1 Announce Type: new Abstract: The reproducibility crisis has directed the AI research community toward improving documentation practices. Several studies have identified methodological issues, and in response, the most impactful venues in the field have introduced reproducibility checklists. We seek to understand whether documentation practices have changed over time by assessing all published papers at five leading AI conferences over the past decade. Seven reproducibility variables were identified, quality-assured and used to analyse 56 800 publications. Our analysis reveals that in the period 2014 to 2024, documentation practices have improved; papers sharing both code and data increased nearly sixfold, from 11% to 64% Building on empirical reproducibility rates from a prior study, we estimate - inferred from documentation practices, not direct testing - that reproducibility increased from 28% in 2014 to 64% in 2024. Improvements in documentation practices predate the introduction of reproducibility checklists, suggesting these changes reflect a broader movement toward open science rather than a direct response to formal requirements.

Read & Discuss → View Source →

08.

medRxiv (Medicine) 2026-06-22 DOI: HASH:1e7879d832d4cffaf496156082807a77

Toward less intrusive pubertal assessment: longitudinal evaluation of tanner and non-tanner metrics in East African adolescents

Authors:

Anok ↗J. J ↗Prodger ↗J. L ↗White ↗Yang ↗Park ↗D. E ↗Bukenya ↗S. P ↗Kiboneka ↗Agaba ↗…

Background: Accurate pubertal assessment is essential in pediatric endocrinology and adolescent health research. While Tanner staging remains the gold standard, its subjective nature and invasive genital examination limit feasibility and acceptability, especially in longitudinal studies and culturally sensitive settings. This study evaluated less intrusive pubertal assessment combinations that maintain discriminative accuracy. Methods: We conducted a longitudinal study among 200 uncircumcised, sexually naive males aged 15-17 years in Southwestern Uganda, with quarterly follow-up over three years. Clinicians assessed Tanner staging metrics (pubic hair, testicular volume, penile length, scrotal color), axillary hair, and serum testosterone. Markov transition models estimated Tanner stage progression. Ordinal logistic regression and area under the receiver operating characteristic curve (AUC) analyses quantified discriminative performance of individual and combined metrics. Results: At baseline, participants were distributed across Tanner stages II (6.0%), III (13.5%), IV (55.0%), and V (25.5%). Among individual metrics, pubic hair distribution best predicted overall Tanner stage (AUC=0.867), while penile length was least predictive (AUC=0.833). The full four-metric Tanner model achieved high discrimination (AUC=0.993). However, a less intrusive combination of pubic hair and scrotal color achieved comparable discrimination (AUC=0.942), improving to AUC=0.953 with axillary hair and age. Markov modeling demonstrated frequent bidirectional transitions between Tanner stages IV and V, reflecting variability in longitudinal staging. Conclusions: A minimally intrusive assessment combining pubic hair, scrotal color, axillary hair, and age reliably predicts pubertal stage, offering an acceptable alternative to traditional Tanner staging for research and surveillance contexts where genital manipulation is impractical or unethical.

Read & Discuss → View Source →

09.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18509

Concept Modulation Models: A Unified Framework for Identifiability and Extrapolation

Authors:

Soheun Yi ↗Yizhou Lu ↗Chandler Squires ↗Pradeep Ravikumar ↗

arXiv:2606.18509v1 Announce Type: new Abstract: Reliable generalization in conditional latent variable models requires understanding both identifiability and extrapolation: how observed variation across attributes determines latent structure, and how that structure determines distributions at unseen attributes. However, existing identifiability and extrapolation guarantees are largely model-specific, with separate analyses in nonlinear ICA, causal representation learning, perturbation modeling, and related conditional latent variable models. We introduce concept modulation models (CMMs), an attribute-indexed class of conditional generative models with structure $A\to \Lambda \to C\to X$, where attributes select modulators, modulators induce latent concept laws, and concepts generate observed features. CMMs lift transition-based identifiability to conditional settings by showing that feature agreement on observed attributes induces a latent concept transition constrained by the CMM class. We express these constraints through attribute potentials, log-density ratios between attribute-conditioned concept laws, separating the generic lifting step from model-specific rigidity arguments. The same potentials control extrapolation: agreement at unseen attributes holds exactly when the transported attribute-potential identities extend to those attributes. This yields algebraic extrapolation criteria, identifies the common potential-based proof objects behind several existing identifiability and extrapolation results, and, when combined with the model-specific rigidity arguments in those works, recovers their stated conclusions.

Read & Discuss → View Source →

10.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2512.20014

Bring My Cup! Personalizing Vision-Language-Action Models with Visual Attentive Prompting

Authors:

Sangoh Lee ↗Sangwoo Mo ↗Wook-Shin Han ↗

arXiv:2512.20014v3 Announce Type: replace-cross Abstract: While Vision-Language-Action (VLA) models generalize well to generic instructions, they struggle with personalized commands such as "bring my cup," where the robot must act on one specific instance among visually similar objects. We study this setting of manipulating personal objects, in which a VLA must identify and control a user-specific object unseen during training using only a few reference images. To address this challenge, we propose Visual Attentive Prompting (VAP), a simple-yet-effective training-free perceptual adapter that equips frozen VLAs with top-down selective attention. VAP treats the reference images as a non-parametric visual memory, grounds the personal object in the scene through open-vocabulary detection and embedding-based matching, and then injects this grounding as a visual prompt by highlighting the object and rewriting the instruction. We construct two simulation benchmarks, Personalized-SIMPLER and Personalized-VLABench, and a real-world tabletop benchmark to evaluate personalized manipulation across multiple robots and tasks. Experiments show that VAP consistently outperforms generic policies and token-learning baselines in both success rate and correct-object manipulation, helping to bridge the gap between semantic understanding and instance-level control.

Read & Discuss → View Source →

11.

arXiv (quant-ph) 2026-06-25 DOI: arXiv:2510.24439

Fundamental limit on the heralded single photons' spectral brightness

Authors:

Tse-Yu Lin ↗Wei-Kai Huang ↗Pei-Yu Tu ↗Yong-Fan Chen ↗Ite A. Yu ↗

arXiv:2510.24439v3 Announce Type: replace Abstract: Heralded single photons (HSPs) are the versatile flying qubits in quantum communication and networks due to their ability to remove the randomness of arrival time and enhance the transmission reliability. As the generation rate of HSPs increases or their linewidth narrows, both of which are desirable for quantum information processing, the fundamental limit of spectral brightness (SB), defined as the generation rate per unit linewidth, remains unclear. To examine the existence and value of such a limit, we systematically studied the SB together with the cross-correlation function, or equivalently, the signal-to-background ratio (SBR). We ultimately derive an upper bound on SB that applies universally to all types of HSP sources. A newly defined quantity governs this limit, the quality factor, which is the product of SBR and effective SB. The quality factor indicates how closely an HSP source approaches an ideal noise-free source. Furthermore, by employing an HSP source based on hot atomic vapor, we achieved an SB of $(8.5\pm0.3)$$\times$$10^5$ pairs/s/MHz and a quality factor of $0.73\pm0.02$ under the single-photon criterion. Both values represent the highest reported performance to date among all HSP platforms. These results provide a unified benchmark for evaluating and optimizing HSP sources.

Read & Discuss → View Source →

12.

arXiv (CS.CL) 2026-06-24 DOI: arXiv:2606.24162

BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks

Authors:

Jin Huang ↗Yutong Xie ↗Wanli Song ↗Xingjian Zhang ↗Walter Yuan ↗Matthew O. Jackson ↗Qiaozhu Mei ↗

Foundation models have been increasingly applied to behavioral science domains such as psychology, sociology, and economics. While these models show promise in individual tasks such as survey response prediction and human-subject experiment simulation, there remains no systematic understanding of how well they perform across diverse behavioral science tasks, contexts, and populations. We introduce BehaviorBench, a comprehensive benchmark that evaluates foundation models along four core capabilities: (1) behavior prediction and simulation, (2) strategic decision-making, (3) subject-trait inference, and (4) behavioral knowledge application. Crucially, BehaviorBench evaluates model outputs at both the individual and distributional levels, capturing not only per-subject accuracy but also population-level alignment, an essential requirement for behavioral validity. Leveraging the tasks in BehaviorBench, we further develop Be.FM-1.5, extending the Be.FM family of behavioral foundation models fine-tuned on behavioral data. Our results reveal a considerable gap: proprietary general-purpose models excel at individual-level prediction and knowledge-intensive tasks, whereas behavioral foundation models, fine-tuned on behavioral data, achieve substantially stronger distributional alignment. Notably, Be.FM-1.5 leads on distributional metrics and remains competitive on individual-level metrics, suggesting that proper behavioral adaptation can close the gap. Our results highlight the importance of distributional evaluation, establish BehaviorBench as a foundation for developing and assessing behaviorally aligned AI systems, and demonstrate Be.FM-1.5's potential for a broad range of behavioral science studies. Our BehaviorBench and Be.FM-1.5 models can be accessed via https://umich-foreseer.github.io/behaviorbench/.

Read & Discuss → View Source →

13.

medRxiv (Medicine) 2026-06-23 DOI: HASH:f821999419a5105ad61a665bfb946841

Multivariate Echocardiographic Phenotyping of Hypertensive Heart Failure Using Unsupervised Machine Learning: A Pilot Study

Authors:

Onyemachi ↗Maduka ↗C. J ↗

Background Heart failure in hypertensive patients is heterogeneous and poorly captured by traditional left ventricular ejection fraction (LVEF) based classification. Multivariate echocardiographic data combined with unsupervised machine learning may provide a more precise phenotypic characterization. This pilot study evaluated the feasibility of unsupervised clustering of routine transthoracic echocardiographic data to identify phenotypic subgroups of hypertensive heart failure. Methods This retrospective pilot study analyzed transthoracic echocardiography reports from hypertensive patients with clinical heart failure. After data cleaning and exclusion of incomplete records, 102 patients with 11 echocardiographic variables were included. Variables describing left ventricular geometry, systolic function, and diastolic performance were standardized and subjected to K-means clustering. Optimal cluster number was determined using the elbow method and silhouette analysis. Cluster characteristics were assessed using descriptive statistics and Kruskal Wallis testing. Concordance with LVEF based heart failure categories was evaluated. Results Three distinct echocardiographic phenotypes were identified. Cluster 0 (n = 50) demonstrated preserved LVEF with concentric remodeling, consistent with heart failure with preserved ejection fraction (HFpEF) phenotype. Cluster 1 (n = 37) showed marked ventricular dilation and reduced systolic function, consistent with heart failure with reduced ejection fraction (HFrEF). Cluster 2 (n = 15) exhibited concentric hypertrophy with intermediate LVEF, consistent with heart failure with mildly reduced ejection fraction (HFmrEF) like phenotype. All echocardiographic variables differed significantly across clusters (p < 0.001). While Cluster 0 showed strong concordance with HFpEF (96%), Clusters 1 and 2 demonstrated substantial overlap across LVEF categories, indicating partial discordance between structural phenotypes and LVEF based classification. Conclusion Application of unsupervised machine learning to routine echocardiographic data identifies distinct heart failure phenotypes in hypertensive patients. These phenotypes demonstrate significant structural heterogeneity beyond LVEF based classification, supporting the utility of data-driven approaches for refined cardiac phenotyping. This pilot study provides a foundation for larger prospective studies.

Read & Discuss → View Source →

14.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2304.13836

On Pitfalls of $RemOve-And-Retrain$: Data Processing Inequality Perspective

Authors:

Junhwa Song ↗Keumgang Cha ↗Junghoon Seo ↗

The RemOve-And-Retrain (ROAR) benchmark is widely used to evaluate feature attribution methods, yet its validity remains underexplored from an information-theoretic perspective. We show that model- and data-agnostic post-processing of attribution maps (transformations that, by the data processing inequality, cannot add information about the decision function) can often improve ROAR scores. This means that an improved ROAR ranking is not, by itself, evidence that an attribution map carries more information about the model. We trace this failure mode to a bias toward spatially blurry masks. Experiments on CIFAR-10, SVHN, and CUB-200 show a consistent association between blurriness and ROAR performance, a pattern that also appears in the ROAD variant. We provide guidelines for more cautious removal-based benchmarking, with implications for validating mechanistic understanding of neural network internals.

Read & Discuss → View Source →

15.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14306

Thinking Outside the [Chat]Box: Bridging Computer Science and Industrial Design for Cognitive-Inclusive Generative AI

Authors:

Virginia Francisco ↗Daniel Guasch ↗Raquel Herv\'as ↗

arXiv:2606.14306v1 Announce Type: cross Abstract: Current Generative AI (GenAI) interfaces remain largely constrained to chatbox interaction, which can impose high cognitive demands on users and create substantial barriers for people with intellectual disabilities (ID), including prompt formulation difficulties, response overload, and limited mechanisms to assess information reliability. To explore alternative interaction models for cognitive accessibility, we conducted a cross-disciplinary co-design challenge in which two student cohorts (Computer Science and Industrial Design) developed interface concepts from the same set of functional requirements (e.g., prompt scaffolding, structured output, GUI-based refinement, transparency, and personalization). Comparing the resulting proposals reveals both convergence on foundational requirements (notably initial calibration, proactive prompting, and direct manipulation of response fragments) and complementary contributions that outline a multi-layered support system. Computer Science teams primarily produced structural scaffolding, emphasizing predictability, navigability, and trust through mechanisms such as reliability indicators, explicit sources, and context management for long conversations. Industrial Design teams emphasized experiential scaffolding, focusing on pacing, attention guidance, multimodality, and proactive agency, including step-by-step response flows, focus modes, and assistant-like integrations. We synthesize these findings into a dual-layer scaffolding framework that expands the design space for cognitively accessible GenAI interaction beyond chat-centric models and motivates future work on expert refinement, technical feasibility, and empirical validation with users with ID.

Read & Discuss → View Source →

16.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2507.00875

TransLaw: A Large-Scale Dataset and Multi-Agent Benchmark Simulating Professional Translation of Hong Kong Case Law

Authors:

Xi Xuan ↗Chunyu Kit ↗

Translating Hong Kong Court Judgments from English to Traditional Chinese is mandated by Articles 8-9 of the Basic Law, yet remains constrained by a shortage of parallel resources and rigorous demands on legal terminology, citation format, and judicial style. We introduce HKCFA Judgment 97-22, the first large-scale sentence-aligned parallel corpus for HK case law, comprising 344 professionally translated judgments (11,099 sentence pairs; 2.1M tokens) spanning 1997-2022. Building on this resource, we propose TransLaw, a multi-agent framework that decomposes translation into word-level expression, sentence-level translation, and multidimensional review, integrating a specialized Hong Kong legal glossary database, Retrieval-Augmented Generation, and iterative feedback, with four-dimensional expert review covering semantic alignment, terminology, citation, and style. Benchmarking 13 open-source and commercial LLMs, we demonstrate that TransLaw significantly outperforms single-agent baselines across all evaluated models, with convergence within 3 iterations. Human evaluation by 10 certified legal translators using our proposed Legal ACS metric confirms gains in legal-semantic accuracy, while showing that TransLaw still trails human experts in stylistic naturalness. The dataset and benchmark code are available at https://github.com/xuanxixi/TransLaw.

Read & Discuss → View Source →

17.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2605.20795

What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing

Authors:

Hangyu Lin ↗Chao Wen ↗Chengming Xu ↗Jianxiong Gao ↗Jiangning Zhang ↗Xiaobin Hu ↗Yanwei Fu ↗

Flow matching based video generative models have been increasingly relying on prepended Vision-Language Models (VLMs) to handle complex, instruction-based video editing. The prevailing assumption underlying this paradigm is that a connector module can seamlessly align the VLM's rich multi-modal reasoning with the original text embedding space of DiTs. However, we hypothesize that this alignment acts as a severe semantic bottleneck, degrading fine-grained structural variables. Verifying this is challenging, as end-to-end evaluations conflate alignment failures with generation errors, and natural datasets lack disentangled annotations. To rigorously investigate this, we propose a controlled data processing pipeline based on video composition that results in TRACE-Edit, a diagnostic dataset focusing on relation-based editing. Leveraging this dataset, we propose a comprehensive diagnostic protocol to analyze two important designs of meta-query and connector in the existing video editing models. Systematic evaluation of four representative model cases reveals that fine-grained structural semantics can be severely degraded during alignment. Our findings overturn the assumption of lossless semantic transfer, identifying the VLM-to-DiT alignment as a major bottleneck and providing a new diagnostic foundation for future multi-modal alignment architectures.

Read & Discuss → View Source →

18.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2606.23740

Weight-Space Geometry of Offline Reasoning Training

Authors:

Aleksandr Nikolich ↗Igor Kiselev ↗Vladimir Platonov ↗Karina Romanova ↗

arXiv:2606.23740v1 Announce Type: cross Abstract: Offline reinforcement-learning losses (RFT, RIFT, DFT, Offline GRPO, DPO) are widely used to distill reasoning from large teachers into smaller students, and are typically compared on downstream accuracy alone. We ask whether they are mechanistically distinct or converge to a similar weight update. Training six methods (SFT, RFT, DFT, RIFT, Offline GRPO, DPO) on identical math rollouts from a single base model (Qwen3-4B) with attention-only LoRA, we analyze the resulting deltas via cosine similarity, principal-angle subspace analysis, linear mode connectivity, and CKA. We observe: (i) SFT, RFT, and RIFT have nearly colinear weight deltas (cosine >= 0.97, top-1 principal angle ~7 deg median over 144 modules) and comparable GSM8K accuracy (87-88%, n=1319; pairwise McNemar p >= 0.15); (ii) DFT diverges further in direction than any reward-weighted method despite using the same data; (iii) Offline GRPO adds a substantial component orthogonal to the SFT direction (~67% globally, up to ~86% in late layers) while staying in the SFT loss basin; (iv) DPO sits in a near-orthogonal subspace, shows a mode-connectivity barrier, and collapses late-layer CKA to ~0.46. DPO also reaches the highest accuracy in our protocol on both GSM8K (93.5%, McNemar p < 10^-9 vs. each other method) and AIME26 (30.0% vs. 3.3-10.0%); its training uses a 10x smaller learning rate than the others (the standard convention), so the update-norm and accuracy gaps reflect loss-function and optimizer choices jointly, and a learning-rate-matched DPO comparison is left for future work.

Read & Discuss → View Source →

19.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14620

Neither Parallel Nor Sequential: How DiffusionGemma Actually Commits Tokens

Authors:

Ali Asaria ↗Tony Salomone ↗Deep Gandhi ↗

arXiv:2606.14620v1 Announce Type: new Abstract: Open diffusion language models are marketed as parallel, non-autoregressive decoders, yet the order in which a shipped checkpoint actually commits its tokens is almost never measured. We instrument DiffusionGemma 26B, a masked discrete-diffusion mixture-of-experts model built on Gemma 4, hooking its sampler's accept step to record which canvas positions commit, when, and at what confidence. Across a 686-prompt, six-regime probe suite we find that its decoding is neither parallel nor block-autoregressive: it follows a partial left-to-right commit bias whose apparent strength depends almost entirely on the granularity at which you look. Order is weak token by token and strengthens smoothly as the analysis is coarsened, so the model's "block size" turns out to be an artifact of the measuring ruler rather than the architecture. The model commits in large simultaneous batches, leaving much of the within-batch order genuinely undefined rather than merely unobserved. The behaviour is regime-dependent: structured JSON is committed in essentially arbitrary order, and a position's commit confidence tracks correctness on mathematical reasoning but carries no signal on factual recall. Commitment is aggressive, finishing in a short late burst well inside the step budget, while task accuracy matches the model's autoregressive Gemma-4 sibling. Beyond these findings, our central contribution is methodological: measuring decoding order honestly demands handling trailing-EOS padding, within-regime confounding, commit non-monotonicity, block-size sensitivity, and large commit-batch ties, each of which can otherwise manufacture a decoding-order result that is not really there.

Read & Discuss → View Source →

20.

arXiv (CS.CL) 2026-06-25 DOI: arXiv:2605.29682

Scaling Laws for Agent Harnesses via Effective Feedback Compute

Authors:

Xuanliang Zhang ↗Dingzirui Wang ↗Keyan Xu ↗Qingfu Zhu ↗Wanxiang Che ↗

Agent harnesses shape language-model performance by controlling tool use, feedback, verification, memory, and repair. Yet raw test-time expenditure, such as tokens, tool calls, wall time, or cost, cannot distinguish useful feedback from redundant or unstable interaction. We introduce Effective Feedback Compute (EFC), a trace-level scaling coordinate for informative, valid, non-redundant, and retained feedback. We further define Estimated-EFC, NRS-EFC, harness efficiency $\eta$, and task-demand normalization for realistic traces and heterogeneous tasks. Across synthetic, real, held-out, and prospective evaluations, EFC-based coordinates outperform raw-compute baselines and SAS. Oracle-EFC/$D_{\mathrm{task}}$ reaches $R^2=0.99$ in controlled scaling, and NRS-EFC/$D_{\mathrm{task}}$ reaches $R^2=0.93$ on real traces where raw compute has near-zero or negative fit. Finally, \ours uses EFC as a companion control layer for existing harnesses, improving mean pass rate from $61.2\%$ to $68.2\%$ while reducing mean raw cost from $213.8$ to $85.1$ under matched settings. These results suggest that harness scaling depends on durable, task-sufficient feedback rather than raw computation alone.

Read & Discuss → View Source →

21.

arXiv (CS.LG) 2026-06-24 DOI: arXiv:2606.24769

Dirac-Frenkel dynamics with inertia for nonlinearly parametrized solutions of evolution problems

Authors:

Matteo Raviola ↗Benjamin Peherstorfer ↗

arXiv:2606.24769v1 Announce Type: cross Abstract: Even when Dirac-Frenkel dynamics determine a well-defined evolution in function space, the corresponding parameter dynamics can be non-unique or ill-conditioned for redundant nonlinear parametrizations such as neural networks or mixture models. We propose to add inertia to the Dirac-Frenkel dynamics and show that this allows useful parameter velocity information to persist from the past trajectory in directions that are weakly informed, while well-informed parameter velocity directions continue to follow the Dirac-Frenkel dynamics. We prove that the inertial formulation yields well-posed parameter dynamics and provide a posteriori error bounds. After time discretization, the method requires the solution of the same type of regularized linear least-squares problem as standard Dirac-Frenkel dynamics, but with the previous velocity appearing as an anchor. Numerical experiments demonstrate the increased robustness obtained with inertia.

Read & Discuss → View Source →

22.

PLOS Medicine 2026-05-26 DOI: HASH:7f406689d6b83c002181d9d5c56bb6c1

Requiring code sharing to strengthen transparency and trust in research

Authors:

Helen Lumbard ↗

by Helen Lumbard, Lauren Cadwallader, Devin Soper, on behalf of the PLOS Medicine Staff Editors PLOS Medicine has always championed open science and data transparency. Now, recognizing that code is as essential a research artifact as the data it analyzes, we are strengthening our code sharing policy to further ensure reproducibility and trust in the scientific record. Recognizing that code is as essential a research artifact as the data it analyzes, this Editorial outlines how PLOS Medicine is strengthening its code sharing policy to further ensure reproducibility and trust in the scientific record.

Read & Discuss → View Source →

23.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17099

Software Delegation Contracts: Measuring Reviewability in AI Coding-Agent Work

Authors:

Vincent Schmalbach ↗

arXiv:2606.17099v1 Announce Type: cross Abstract: AI coding agents increasingly accept assigned software tasks, modify repositories under bounded authority, and return work packages for review. Prior work proposed the software delegation contract, covering the task, authority, returned work package, and acceptance context, as the unit of analysis for delegated coding work, but did not measure its effects. This paper reports a controlled pilot study of explicit delegation contracts for coding agents. We built a dependency-free TypeScript API task environment with seeded defects and documentation gaps, authored ten tasks across five families, and ran 64 agent executions across two model tiers under three conditions: a realistic issue-style prompt, an explicit delegation contract, and a contract with a required evidence bundle. Each run was scored with hidden acceptance tests, mutation checks, and scope analysis, then reviewed by three independent condition-blinded model-based reviewers using a fixed rubric, for 192 reviews. Explicit contracts did not improve objective task outcomes: all 64 runs passed hidden acceptance checks, with zero scope violations. They did improve reviewability. Evidence sufficiency improved in 22 of 30 paired comparisons and worsened in none (+0.83 on a 5-point scale, p < 0.0001, Cliff's delta = 0.66); reviewer ambiguity decreased (p = 0.035); changed-file lists, known-limitations sections, residual-risk sections, and reviewer checklists appeared mostly or only when demanded by the contract. Contracts cost +13% agent tokens and +38% wall-clock time, with larger effects for the weaker model tier. On these small tasks, delegation contracts bought reviewability rather than correctness.

Read & Discuss → View Source →

24.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2606.03070

ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without Behavior Information

Authors:

Zehua Liu ↗Yuxuan Yao ↗Xiaojin Fu ↗Tao Zhong ↗Mingxuan Yuan ↗

arXiv:2606.03070v3 Announce Type: replace-cross Abstract: Asynchronous reinforcement learning can improve language-model post-training throughput by decoupling response generation from policy optimization, but stale responses introduce distribution drift. Standard behavior-corrected methods control this drift with behavior-policy probabilities, importance ratios, or clipping, which requires token-aligned, versioned, and numerically consistent behavior log-probabilities across rollout and learner systems. We ask whether asynchronous group-relative RL can instead be stabilized using only current-policy probabilities. We identify a scale-imbalance failure mode: when stale responses are evaluated under the current policy, positive and negative loss terms can appear at different negative log-probability scales, so zero-sum advantages no longer imply balanced loss contributions. We propose Asymmetric-Scale Policy Optimization (ASymPO), which normalizes each response's token loss by its current average token negative log-probability. ASymPO requires no behavior-policy probabilities, restores response-level zero-sum balance, and preserves a nonzero learning signal. We also introduce Scaled Policy Optimization (SPO), a fixed negative-scaling baseline, and evaluate both current-policy-only objectives in asynchronous mathematical reasoning post-training.

Read & Discuss → View Source →

25.

arXiv (CS.LG) 2026-06-25 DOI: arXiv:2601.02193

Learning with Monotone Adversarial Corruptions

Authors:

Kasper Green Larsen ↗Chirag Pabbaraju ↗Abhishek Shetty ↗

arXiv:2601.02193v2 Announce Type: replace Abstract: We study the extent to which standard machine learning algorithms rely on exchangeability and independence of data by introducing a monotone adversarial corruption model. In this model, an adversary, upon looking at a "clean" i.i.d. dataset, inserts additional "corrupted" points of their choice into the dataset. These added points are constrained to be monotone corruptions, in that they get labeled according to the ground-truth target function. Perhaps surprisingly, we demonstrate that in this setting, all known optimal learning algorithms for binary classification can be made to achieve suboptimal expected error on a new independent test point drawn from the same distribution as the clean dataset. On the other hand, we show that uniform convergence-based algorithms do not degrade in their guarantees. Our results showcase how optimal learning algorithms break down in the face of seemingly helpful monotone corruptions, exposing their overreliance on exchangeability.

Read & Discuss → View Source →

Explore the Frontier of Global Academia