探索全球前沿学术脉络

01.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13647

SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation

作者:

Marek \v{S}uppa↗Andrej Ridzik↗Daniel Hl\'adek↗Nat\'alia K\v{n}a\v{z}ekov\'a↗Vikt\'oria Ondrejov\'a↗

We introduce SkMTEB, the first comprehensive MTEB-style text embedding benchmark for Slovak, a low-resource West Slavic language, comprising 31 datasets across 7 task types – nearly 4$\times$ the depth of existing multilingual benchmark coverage for Slovak. Our evaluation of 31 embedding models reveals that large instruction-tuned multilingual models achieve the strongest performance, while existing Slovak-specific models trained for NLU tasks transfer poorly to embedding tasks. To address the need for efficient, locally-deployable Slovak embeddings, we develop \texttt{e5-sk-small} (45M parameters) and \texttt{e5-sk-large} (365M) by applying vocabulary trimming and fine-tuning to Multilingual E5 models. Despite size reductions of up to 62\%, our open-source models achieve competitive performance with proprietary APIs while remaining locally deployable for semantic search and retrieval-augmented generation (RAG). We release the benchmark, models, datasets, and code openly, hoping our approach offers a replicable path for other under-resourced languages.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.LG) 2026-06-25 DOI: arXiv:2604.23488

Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Trainig-Time Reward Hacking in Code Generation

作者:

Lichen Li↗Hengguang Zhou↗Yijun Liang↗Tianyi Zhou↗Cho-Jui Hsieh↗

arXiv:2604.23488v2 Announce Type: replace Abstract: Reward hacking in code generation, where models exploit evaluation loopholes to obtain high reward without correctly solving the intended task, poses a critical challenge for Reinforcement Learning (RL) and the deployment of reasoning models. Existing studies often rely on explicitly prompted hacking trajectories, but it remains unclear whether monitors trained on such data can detect reward hacks that arise without direct hacking instructions during RL training. In this work, we introduce Trace-and-Amplify, a framework for scalable curation of reward-hacking trajectories that arise during RL training without explicit hacking instructions. The framework uses unit-test tracers to identify hacking solutions when they occur and retains such trajectories for monitor training and evaluation. Through controlled comparisons between monitors trained on prompt-elicited hacking trajectories and training-time reward-hacking trajectories collected by Trace-and-Amplify, we find that (1) prompt-elicited-data-trained monitors often fail to generalize to trajectories curated by our framework, and (2) monitors trained on our Trace-and-Amplify trajectories demonstrate stronger generalizability to unseen hacking types. Our results indicate that prompted reward hacking data may not fully reflect training-time reward-hacking behaviors, and that relying solely on these data can lead to misleading conclusions. Codebase is available at https://github.com/LichenLillc/CoTMonitoring.git

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18947

Decoupling Search from Reasoning: A Vendor-Agnostic Grounding Architecture for LLM Agents

作者:

Emmanuel Aboah Boateng↗Kyle MacDonald↗Amardeep Kumar↗Siddharth Kodwani↗Sudeep Das↗

Production LLM agents increasingly depend on real-time search, yet native search grounding bundles retrieval policy, provider choice, evidence injection, cost, latency, and generation behavior behind a single model-provider boundary. This coupling makes grounding hard to inspect, tune, reuse, or port, and can trigger Search-Induced Verbosity that breaks strict output contracts. We present Decoupled Search Grounding (DSG), a vendor-agnostic boundary that moves grounding outside the reasoning model through an MCP-compatible gateway, exposing provider routing, source-aware context rendering, configured fallback, retrieval-depth control, and exact plus semantic caching as first-class controls. Across five frontier models on SimpleQA, FreshQA, and HotpotQA, native search leads on recency-sensitive FreshQA, but DSG exposes a stronger frontier when control matters: on SimpleQA it nearly matches native accuracy (86.1% vs. 87.7%) at 91% lower search cost, preserves concise answer contracts, and reaches a 99.4% warm-cache hit rate with 68% lower latency. Deployed as a shared production grounding layer for large-scale agentic workloads with interchangeable models, DSG matches or slightly exceeds native-search accuracy on an e-commerce query-understanding (QIU) workload while cutting search cost by over 98%. Real-time grounding is best treated as an optimizable interface boundary, not a fixed model feature.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13106

Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning

作者:

Jiayu Yang↗Chao Chen↗Shengen Wu↗Yinhong Liu↗Yuxuan Fan↗Lujundong Li↗Songning Lai↗Chengwei Qin↗Zhijiang Guo↗

Latent chain-of-thought compresses reasoning by replacing visible reasoning traces with continuous hidden-state recurrence, but existing formulations are difficult to optimize with standard on-policy reinforcement learning (RL) and hard to interpret causally. Our key insight is that a single pair of explicit boundary tokens can address both issues at once: discrete entry and exit anchors make the latent block compatible with standard on-policy RL, and the same anchors offer a natural foothold for mechanistic analysis. Motivated by this, we propose SWITCH, a switchable latent reasoning framework. The model emits to enter latent mode and to exit. Because the boundaries are ordinary discrete tokens, the GRPO policy ratio is well-defined at every decision point. The same anchors also expose the latent steps to direct probing and causal intervention. We train the model with a visible-to-latent curriculum and a Switch-GRPO objective that propagates gradients through recurrent latent computation. SWITCH consistently outperforms prior hidden-state-recurrence latent reasoning approaches at similar scale. Mechanistic analysis through the boundary tokens further reveals three findings: (i) is a sharply localised, learned switching policy rather than a stylistic artefact; (ii) the latent step it opens performs problem-specific, causally important computation rather than acting as an inert placeholder; and (iii) that computation is concentrated at a single hidden-state transition on entry. Together, these results show that hidden-state-recurrence latent reasoning is both RL-trainable and open to direct mechanistic analysis, including of how on-policy RL itself improves the model from the inside.

阅读与讨论 → 访问原文 →

05.

medRxiv (Medicine) 2026-06-23 DOI: HASH:54f0baf14de06326e663c95e5dc855f0

Differential Recovery Trajectories of Emergency Otolaryngologic Conditions across the COVID-19 Pandemic: A Six-year Longitudinal Study from an Urban Emergency Center

作者:

Ogawa↗

Objective: The COVID-19 pandemic markedly altered social activity patterns, healthcare utilization, and the epidemiology of infectious diseases. However, its long-term impact on emergency otolaryngologic conditions remains incompletely understood. This study investigated long-term trends in emergency otolaryngologic conditions before, during, and after the COVID-19 pandemic using comprehensive data from a large urban emergency clinic in Osaka, Japan. Methods: All new otolaryngologic outpatients who visited the Chuo Emergency Medical Clinic (CEMC) in Osaka City between 2019 and 2024were retrospectively analyzed. Annual trends in absolute numbers and relative proportions of emergency otolaryngologic conditions were examined by anatomical region and disease category, using 2019 as the pre-pandemic baseline. Results: A total of 99,324 new otolaryngologic outpatients were analyzed. Overall emergency visits declined sharply to approximately half of baseline in 2020, followed by a gradual but incomplete recovery toward pre-pandemic levels by 2024. Most anatomical categories declined to 45-61% of baseline in 2020 and exhibited gradual yet incomplete recovery through 2023; in stark contrast, laryngeal conditions diverged sharply, surging beyond pre-pandemic levels after 2022. Acute infectious otorhinolaryngologic diseases fell to 23-50% of baseline in 2020 and showed variable recovery (69-103%) by 2024. Notably, laryngitis exceeded the baseline, reaching 132% in 2023, whereas epiglottic edema exhibited only a transient increase approaching the baseline in 2021. Non-infectious emergency conditions generally showed only a marginal decrease in 2020 and remained relatively stable throughout the study period, except for sudden sensorineural hearing loss (SSNHL), which dropped sharply to 39% of the baseline in 2020 and remained persistently reduced through 2024. Traumatic emergencies declined variably to 53-81% of the baseline in 2020, followed by an incomplete recovery, reaching only 55-69% by 2024. Conclusion: Emergency otolaryngologic conditions demonstrated heterogeneous recovery trajectories following the COVID-19 pandemic. While most infectious and traumatic conditions gradually but incompletely normalized, laryngeal conditions showed a distinct post-pandemic surge, and SSNHL remained persistently suppressed. These findings reveal heterogeneous, condition-specific recovery trajectories that reflect both genuine shifts in community pathogen burden, true traumatic incidence, and persistent alterations in healthcare-seeking behaviors, insights essential for resource allocation during future public health emergencies.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16933

A Unified Causal-Origin Taxonomy of Distributional Shifts in Reinforcement Learning

作者:

Ardianto Wibowo↗Paulo E Santos↗Amer Baghdadi↗Matthew Stephenson↗Karl Sammut↗Jean-Philippe Diguet↗

arXiv:2606.16933v1 Announce Type: cross Abstract: Reinforcement learning (RL) systems often degrade when operating conditions differ from those previously encountered, reflecting distributional shifts in the underlying data-generating process. Such shifts may occur between training and evaluation, as in In-Distribution (ID) and Out-of-Distribution (OOD) generalization, or within non-stationary settings where environment dynamics evolve over time. However, the formal relationship between these views remains unclear, and existing work mainly focuses on mitigation rather than the causal origin of shift within the agent-environment interaction. This work develops a unified causal-origin taxonomy that characterizes sources of distributional shift in RL and relates ID/OOD generalization to non-stationary settings. We transfer the classical dataset-shift principle from supervised learning to RL by reformulating distributional shift in terms of the generative interaction process. Using a Partially Observable Markov Decision Process (POMDP), we decompose the interaction into structural components, including the state distribution, observation process, policy, reward, and transition dynamics, together with the shifted-time boundary. The proposed taxonomy distinguishes internal, agent-driven, and external, environment-driven, distributional shifts. The shifted-time boundary perspective further characterizes explicit, implicit, and hybrid shifts. This formulation unifies ID/OOD generalization and non-stationarity as structured changes in the underlying process. We also introduce an evaluation framework for measuring shift impact and adaptation through performance degradation and recovery metrics. By grounding distributional shift in the causal-origin structure of RL, this work supports systematic analysis of robustness under distributional shift.

阅读与讨论 → 访问原文 →

07.

arXiv (quant-ph) 2026-06-24 DOI: arXiv:2603.28827

Quantum Coherence and Giant Enhancement of Positron Channeling Radiation

作者:

Michael Shatnev↗

arXiv:2603.28827v2 Announce Type: replace Abstract: We present a quantum-mechanical treatment of positron channeling radiation in a planar harmonic potential that explicitly accounts for interference between transition amplitudes from different transverse energy levels. Because the planar channel potential for positrons in diamond~(110) is well approximated by a parabola, the transverse spectrum is equidistant, $\varepsilon_n = \Omega(n+\tfrac{1}{2})$, and all $n \to n{-}j$ transitions radiate at the same Doppler-shifted frequency. The sudden-approximation entry of the positron into the crystal produces a Glauber coherent state[Glauber1963] with Poisson-distributed level populations $|c_n|^2 = e^{-n_0}n_0^n/n!$ and mean occupation $n_0 \propto \theta_in^2$. Phase synchronization between the $c_n$ and the dipole matrix elements ensures constructive interference of all contributing amplitudes. Three exact scaling laws follow: (i)~$I_incoh\propto n_0\propto\theta_in^2$; (ii)~$I_coh\propto n_0^2\propto\theta_in^4$; (iii)~$\mathcal{G}\equiv I_coh/I_incoh\approx n_0 \propto\theta_in^2$. Numerically, $\mathcal{G} = 12–31$ for positron energies of $4–14$~GeV in diamond~(110) at $\theta_in=31\;\mu$rad, in agreement with the experimental first-harmonic peak positions of Avakyan et al.[Avakyan1982] to within 15\%. The transition from $N$- to $N^2$-scaling of radiated intensity, driven by quantum coherence, opens a route toward high-intensity monochromatic gamma-ray sources.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17835

Perceptual compensation for tonal context in self-supervised speech models

作者:

James Kirby↗Ioana Krehan↗Michele Gubian↗

This study examines the extent to which the wav2vec2.0 architecture exhibits evidence of compensation for phonological context. We conducted a pseudo-replication of a perceptional compensation experiment on Mandarin Chinese tones, and compared the embedding similarities and probing classifier outputs between a purely self-supervised pre-trained model and a model fine-tuned for Mandarin ASR. No evidence of compensation was found in the embedding similarities of the purely pre-trained model. Probing classifiers showed some evidence of compensation in addition to the expected layer-wise improvements in categorization, but failed to replicate human performance on isolated test syllables. Our findings contrast with previous reports of sensitivity to phonological structure emerging through pre-training alone, and suggest that supervised objectives may be necessary to encourage the abstraction of at least some types of phonological regularities.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.11521

Counterexample Guided Learning in the Large using Reasoning Agents

作者:

Hongyi Liu↗Frederic Sala↗Thomas Reps↗Adithya Murali↗

arXiv:2606.11521v1 Announce Type: new Abstract: LLMs and LLM agents should improve when given feedback, but identifying when they are able to do so is difficult: feedback is heterogeneous, domain-specific, and difficult to control. We approach this challenge by asking LLMs to perform regular-expression induction, a classical symbolic learning problem where precise mechanisms for feedback exist in the form of counterexamples. In counterexample-guided learning, a learner (LLM) proposes candidate regular expressions from positive/negative-labeled strings, and the teacher (verifier) returns counterexamples showcasing the difference between the candidate and target languages. We identify novel counterexample-guided refinement strategies that enable effective regex learning, such as regularization and symbolic counterexample clusters. We also explore agentic strategies such as reflection and repair loops. Empirically, we find that verifier feedback substantially improves sample efficiency on challenging regex-induction tasks, reducing the number of labeled examples required and enabling learning of complex target expressions where standard prompting fails. For example, on the hardest task groups, our counterexample-guided framework improves success from 3.2% to 38.1% and from 38.9% to 74.1% on two different regex domains. These results suggest that LLMs can benefit from rich feedback beyond treating it as additional data, opening the door for robust verifier-guided methods for LLM-based program synthesis and formal reasoning.

阅读与讨论 → 访问原文 →

10.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2603.12866

Nonlocal continuous-variable gates by amplified optical connections

作者:

Michele N. Notarnicola↗Radim Filip↗

arXiv:2603.12866v2 Announce Type: replace Abstract: Nonlocal quantum gates, coupling quantum systems located at a distance, are crucial for distributed quantum computing. To this aim, high-capacity optical noiseless connections between different processing units are essential for transmitting large amounts of information per mode. Simultaneously, optical quantum computing offers future high-speed multimode quantum processors. We propose a library of feasible protocols to implement a necessary nonlocal continuous-variable (CV) quantum nondemolition (QND) gate between two distant users sharing a quantum channel and exploiting classical communication. The users are endowed with a newly achieved high-fidelity and large-bandwith element - single-pass phase-sensitive optical parametric amplifier (OPA), that allows for both online squeezing and channel-loss compensation. The use of OPAs enhances quality of the resulting gate in terms of both excess noise and entangling capability. The proposed schemes are also applicable to CV cluster state fusion, providing a first step towards development of distributed CV measurement-based quantum computation.

阅读与讨论 → 访问原文 →

11.

medRxiv (Medicine) 2026-06-17 DOI: HASH:568264cbe9466b752a9aeeb4aff35e94

Method comparisons for differentiation of Schizophrenia and Bipolar based on rs-fMRI Intrinsic and Functional Networks

作者:

Janeva↗Breyton↗Markovska-Simoska↗Guilhaumou↗Petkoski↗Iraji↗Calhoun↗Gerazov↗

Psychosis as a symptom manifests in schizophenia and bipolar disorder, two highly heterogeneous psychiatric illnesses with overlapping clinical manifestations. Resting-state functional Magnetic Resonance Imaging (rsfMRI), represents a promising tool for identifying objective biomarkers of functional brain alterations to aid differential diagnosis. In this work, we comparatively evaluate multiple rs-fMRI representations for differentiating schizophrenia and bipolar disorder using intrinsic connectivity network (ICN) temporal profiles and several functional network connectivity (FNC) approaches, including static, dynamic, and high-order connectivity analyses. The study was conducted on a cohort of 371 subjects with psychosis, while evaluation was performed using a separate held-out cohort of 315 subjects. We investigated convolutional neural network architectures applied to ICN temporal profiles, spectrograms, and scalograms, alongside classical machine learning models trained on connectivity-derived features. Across the evaluated approaches, ICN temporal profiles provided the most consistent discriminative performance, with a 1D convolutional neural network achieving the strongest overall results under the benchmark protocol. Among connectivity-based methods, static functional connectivity generally outperformed dynamic and high-order representations, suggesting that increased representational complexity did not necessarily translate into improved generalization. Although the obtained classification performance remained modest, the results highlight the challenges of robust psychosis differentiation using rs-fMRI while emphasizing the relative stability of low-order connectivity representations and temporal ICN features. These findings contribute to ongoing efforts toward reproducible and interpretable neuroimaging biomarkers for psychiatric disorders.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.01365

Early Diagnosis of Wasted Computation in Multi-Agent LLM Systems via Failure-Aware Observability

作者:

Xianyou Li↗Weiran Yan↗Yichao Wu↗Penghao Liang↗Mengwei Yuan↗Jianan Liu↗Jing Yang↗

arXiv:2606.01365v2 Announce Type: replace Abstract: Failure-aware observability diagnoses wasted computation in multi-agent LLM systems before final-answer evaluation can explain what went wrong. We propose a trace-based framework for a three-agent architecture – orchestrator, search agent, and execution agent – that converts structured events into online signals for loops, budget pressure, low information gain, and tool instability, then adds offline semantic grounding metrics and selective LLM-as-judge evaluation. On 165 GAIA validation traces under identical caps, 98 runs produce usable final answers and 67 fail or stop without one. Among warned failed runs, 58.1% of tokens are spent after the first warning on average, indicating substantial opportunity for intervention. A 10-task Level-2 pilot uses warnings to diversify search or require evidence, reducing post-warning token fraction from 0.638 in the baseline to 0.304. The results support a layered design: cheap online signals help the orchestrator redirect or halt redundant behavior, while deeper semantic checks identify whether completed answers are grounded enough to trust.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2601.13836

FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs

作者:

Qian Chen↗Jinlan Fu↗Changsong Li↗Min Zhang↗See-Kiong Ng↗Xipeng Qiu↗

Although Multimodal Large Language Models (MLLMs) demonstrate strong omni-modal perception, their ability to forecast future events from audio-visual cues remains largely unexplored, as existing benchmarks focus mainly on retrospective understanding. To bridge this gap, we introduce FutureOmni, the first benchmark designed to evaluate omni-modal future forecasting from audio-visual environments. The evaluated models are required to perform cross-modal causal and temporal reasoning, as well as effectively leverage internal knowledge to predict future events. FutureOmni is constructed via a scalable LLM-assisted, human-in-the-loop pipeline and contains 919 videos and 1,034 multiple-choice QA pairs across 8 primary domains. Evaluations on 13 omni-modal and 7 video-only models show that current systems struggle with audio-visual future prediction, particularly in speech-heavy scenarios, with the best accuracy of 64.8% achieved by Gemini 3 Flash. To mitigate this limitation, we curate a 7K-sample instruction-tuning dataset and propose an Omni-Modal Future Forecasting (OFF) training strategy. Evaluations on FutureOmni and popular audio-visual and video-only benchmarks demonstrate that OFF enhances future forecasting and generalization. We publicly release all code (https://github.com/OpenMOSS/FutureOmni) and datasets (https://huggingface.co/datasets/OpenMOSS-Team/FutureOmni).

阅读与讨论 → 访问原文 →

14.

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

OrthoReg: Orthogonal Regularization for Hybrid Symbolic-Neural Dynamical Systems

作者:

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.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2512.24592

GH-ESD: Grounded Hypothesis-Driven Error Slice Discovery for Instance-Level Vision Tasks

作者:

Wei Zhang↗Chaoqun Wang↗Zixuan Guan↗Sam Kao↗Pengfei Zhao↗Peng Wu↗Sifeng He↗

Systematic failures of vision models on semantically coherent subsets, known as error slices, reveal limitations in robustness and evaluation. Existing slice discovery approaches largely model slices as clusters in representation space or combinations of predefined attributes. While effective for image-level classification, such formulations are insufficient for instance-level tasks such as object detection and segmentation, where failures often arise from contextual relational and spatially grounded visual patterns. We propose GH-ESD (Grounded Hypothesis-Driven Error Slice Discovery), a generate and verify framework that reformulates slice discovery as grounded hypothesis generation and statistical verification. GH-ESD constructs relational failure hypotheses using LLM priors and grounded visual evidence, discovers hypothesis slices at the instance level via Vision Language Models, and verifies them through statistical trend analysis over instance-level errors. We also introduce GESD (Grounded Error Slice Dataset), a new benchmark for instance-level error slice discovery, providing expert-defined and spatially grounded slices derived from detection and segmentation failures. Extensive experiments demonstrate that GH-ESD consistently outperforms baselines, improving Precision@10 by 0.10 (0.73 vs. 0.63) on the GESD benchmark for detection tasks, while also supporting segmentation scenarios. GH-ESD identifies interpretable slices that facilitate actionable model improvements. The GESD dataset will be made publicly available upon acceptance.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.10198

Density Ridge Selective Prediction for LLM and VLM Hallucination Detection under Calibration Label Scarcity

作者:

Nina I. Shamsi↗

Hallucination detection in large language and vision-language models is increasingly framed as selective prediction, where a detector assigns a confidence score and abstains when confidence is low. Unsupervised sampling detectors (Semantic Entropy) avoid labels but plateau in quality, while supervised probes attain stronger in-distribution scores yet degrade sharply when calibration labels are scarce. We recover the response manifold of an LLM as the density ridge of a kernel density estimate built on a six-dimensional kinematic feature map of hidden state generation trajectories. A test generation is scored by the negated Euclidean distance from its projected feature point to the nearest ridge vertex, yielding a low-dimensional geometric skeleton of the stochastic output distribution. We evaluate against Semantic Entropy, topological methods, and log-probability on six QA benchmarks (HaluEval-QA, TriviaQA, GSM8K, POPE, ScienceQA, A-OKVQA) using eight text and vision LLMs in a deliberately label-scarce protocol ($n_{cal}{=}200$ queries, $N{=}5$ generations). Our ridge-based score beats on AUROC with 5-20 points gain, while demonstrating tempered degradation under calibration-label scarcity.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12594

Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation

作者:

Joshua Ong Jun Leang↗Zheng Zhao↗Mihaela C\u{a}t\u{a}lina Stoian↗Qiyuan Xu↗Haonan Li↗Wenda Li↗Shay B. Cohen↗Eleonora Giunchiglia↗

arXiv:2606.12594v1 Announce Type: new Abstract: Modern Lean theorem provers achieve strong performance only with substantial training and inference compute, driven in part by scarce verified proof data and the long reasoning traces of formal proof search, making both supervised fine-tuning (SFT) and sampling expensive. We introduce Pythagoras-Prover, a compute-efficient open-source family of Lean theorem provers built for practical compute budgets. The family spans two generation paradigms: autoregressive models at 4B and 32B parameters, and a first proof-of-concept diffusion-based prover (4B) that iteratively refines Lean proofs at inference time. For training efficiency, we build a Lean-verified corpus stratified into easy, medium, and hard problems for curriculum SFT, so models acquire proof skills progressively from shorter, simpler proofs to longer, harder ones. During SFT, a dynamic proof-reasoning filtering scheme preserves informative proof traces while keeping each instance within an 8k-token context budget. We also introduce Augmented Lean Formalisation (ALF), which expands scarce verified corpora into variants of formal statements, populated via self-distillation for extra training signal without formally verifying every mutated instance. By perturbing known problems while preserving their formal character, ALF reduces reliance on any statement's surface form. Empirically, Pythagoras-Prover-4B surpasses DeepSeek-Prover-V2-671B at pass@32 on MiniF2F-Test (86.1% vs 82.4%) with ~167x fewer parameters, while Pythagoras-Prover-32B sets the open-source state of the art at 93.0% on MiniF2F-Test and solves 93 of 672 PutnamBench problems. We release MiniF2F-ALF, an ALF-mutated contamination-sensitive benchmark on which every evaluated model loses accuracy; here our 32B remains strongest and our 4B matches the prior state of the art, Goedel-Prover-V2-32B.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2602.21160

Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions

作者:

Mame Diarra Toure↗David A. Stephens↗

arXiv:2602.21160v3 Announce Type: replace-cross Abstract: In safety-critical classification, the cost of failure is often asymmetric, yet Bayesian deep learning summarises epistemic uncertainty with a single scalar, mutual information (MI), that cannot distinguish whether a model's ignorance involves a benign or safety-critical class. We decompose MI into a per-class vector $C_k(x)=\sigma_k^{2}/(2\mu_k)$, with $\mu_k{=}\mathbb{E}[p_k]$ and $\sigma_k^2{=}\mathrm{Var}[p_k]$ across posterior samples. The decomposition follows from a second-order Taylor expansion of the entropy; the $1/\mu_k$ weighting corrects boundary suppression and makes $C_k$ comparable across rare and common classes. By construction $\sum_k C_k \approx \mathrm{MI}$, and a companion skewness diagnostic flags inputs where the approximation degrades. After characterising the axiomatic properties of $C_k$, we validate it on three tasks: (i) selective prediction for diabetic retinopathy, where critical-class $C_k$ reduces selective risk by 34.7\% over MI and 56.2\% over variance baselines; (ii) out-of-distribution detection on clinical and image benchmarks, where $\sum_k C_k$ achieves the highest AUROC and the per-class view exposes asymmetric shifts invisible to MI; and (iii) a controlled label-noise study in which $\sum_k C_k$ shows less sensitivity to injected aleatoric noise than MI under end-to-end Bayesian training, while both metrics degrade under transfer learning. Across all tasks, the quality of the posterior approximation shapes uncertainty at least as strongly as the choice of metric, suggesting that how uncertainty is propagated through the network matters as much as how it is measured.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2605.15796

Cross-Modal Registration Between 3D and 2D Fingerprints via Pose-Aware Unwrapping and Point-Cloud Fusion

作者:

Xiongjun Guan↗Jianjiang Feng↗Jie Zhou↗

Three-dimensional (3D) fingerprints preserve global finger geometry and local ridge structure while avoiding contact-induced deformation, but they remain difficult to integrate with legacy two-dimensional (2D) fingerprint systems. This paper addresses the intermediate stage between 3D acquisition and cross-modal matching, and presents a unified framework for 3D fingerprint preprocessing and registration across contactless and contact-based 2D modalities. The framework combines four components: 1) a nonparametric visualization and unwrapping method that converts a 3D fingerprint point cloud into a rolled-equivalent 2D representation without relying on a global finger-shape model; 2) a point-cloud fusion pipeline that registers and mosaics multiple partial 3D captures into a more complete fingerprint model; 3) an ellipse-based pose normalization method for canonical finger alignment; and 4) a pose-aware cross-modal registration strategy that improves compatibility between 3D fingerprints and both contactless and contact-based 2D fingerprints. Experiments on a self-collected multimodal fingerprint database containing 150 fingers show that the proposed framework achieves ridge-level 3D registration accuracy, robust pose estimation, and consistent gains in 2D compatibility. In particular, the 3D fusion error is concentrated around 0.09 mm, contactless 2D–3D registration reaches ridge-scale projection accuracy, and pose-aware unwrapping improves genuine matching scores relative to generic 3D unwrapping. These results support the use of 3D fingerprints as an effective geometric bridge across heterogeneous fingerprint modalities. The baseline implementation has been publicly released at https://github.com/XiongjunGuan/3DFpVisual.

阅读与讨论 → 访问原文 →

20.

arXiv (quant-ph) 2026-06-25 DOI: arXiv:2606.25037

Arbitrarily Loss-Tolerant Quantum Position Verification in a Single Execution

作者:

Lloren\c{c} Escol\`a-Farr\`as↗Boris \v{S}kori\'c↗Florian Speelman↗

arXiv:2606.25037v1 Announce Type: new Abstract: Quantum position verification (QPV) seeks to certify the spatial location of an untrusted prover, but is challenged fundamentally by entanglement-based attacks and experimentally by photon loss. Both issues were addressed separately in different works and were simultaneously resolved for sequentially repeated protocols in Phys.\ Rev.\ Lett.\ 135,~260801 via a commitment-based modification that renders security independent of transmission losses. However, single-execution protocols are preferable in practice, and the original techniques do not extend to the parallel setting due to their reliance on sequential structure. We overcome this by utilizing different techniques based on no-signalling correlations, lifting the commitment modification to the parallel regime while preserving the security guarantees of the underlying QPV protocol. Applying this to a BB84-based QPV protocol suitable for near-term implementation and secure against bounded-entanglement adversaries, we prove that fixing a threshold~$k$ on the number of successfully committed qubits yields an adversarial acceptance probability that decays exponentially in~$k$. The resulting protocol maintains robustness to noise levels of up to~$3.7\%$ and remains secure under arbitrarily slow quantum communication, as does the original protocol. This yields the first fully loss-tolerant single-shot QPV protocol secure against entangled attackers, making QPV feasible over arbitrary distances. Finally, we refine the sequential analysis and obtain improved quantitative parameters for experimental implementations.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.19185

AGDN: Learning to Solve Traveling Salesman Problem with Anisotropic Graph Diffusion Network

作者:

Bolin Shen↗Ziwei Huang↗Zhiguang Cao↗Yushun Dong↗

arXiv:2606.19185v1 Announce Type: new Abstract: The Traveling Salesman Problem (TSP) is a cornerstone of combinatorial optimization and arises in many practical scenarios. Although graph-based learning approaches have been explored for TSP, the question of how to exploit graph structure more effectively remains open. We present the Anisotropic Graph Diffusion Network (AGDN), a new Graph Neural Network framework designed to solve TSP. Our method tackles two central difficulties: (1) the lack of informative topological prior in fully connected TSP graphs, and (2) losing connected nodes in the optimal solution after the commonly used graph sparsification techniques. To overcome these issues, we construct a MixScore transition matrix that merges node similarity with pairwise distance, and we develop an anisotropic graph diffusion strategy that supports efficient information exchange across multiple hops. Comprehensive experiments spanning diverse instance sizes and node distributions show that AGDN consistently outperforms existing methods while keeping computation time competitive. Furthermore, AGDN generalizes well to problem sizes and distributions beyond those seen during training. The implementation is publicly available at: https://github.com/LabRAI/AGDN.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CL) 2026-06-25 DOI: arXiv:2605.31220

Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models

作者:

Athina Kyriakou↗Dennis Ulmer↗Ivan Titov↗

Confidence estimation (CE), i.e., quantifying the reliability of a model's prediction, has attracted great interest in the context of large language models (LLMs). However, most studies focus on English, ignoring the multilingual reality of LLM usage, while many CE methods degrade or require retraining across languages. To address this gap, we investigate whether multilingual LLMs encode shared, language-transferable confidence features in open-ended question answering. We use a lightweight linear probe that predicts answer correctness directly from intermediate representations. Trained monolingually, the probe generalizes zero-shot to unseen, typologically diverse languages without target-language supervision. Learned layer weights and multiple ablations reveal that confidence features concentrate in middle layers across languages, suggesting a shared confidence subspace. While zero-shot cross-lingual performance depends on similarity to the source language, the probe provides a strong baseline without any retraining and compares favorably to other popular confidence estimation methods.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CL) 2026-06-24 DOI: arXiv:2606.24714

CN-NewsTTS Bench: a target-level automatic benchmark for raw-input Chinese news TTS pronunciation

作者:

Shijun Luo↗

Chinese news text contains dense written forms such as scores, hyphenated model names, ranges, unit symbols, percentages, English abbreviations, and mixed Chinese-Latin-digit names. These forms are frequent in real listening workflows, and a text-to-speech (TTS) system can preserve the written string while changing the spoken meaning. We introduce CN-NewsTTS Bench v0.1, an open target-level benchmark for evaluating whether Chinese news TTS products pronounce such targets correctly from raw text, without user-side rules, LLM rewriting, SSML hints, or manual edits. The release contains a 200-record development set, an 800-record public test set, 992 public auto-evaluable targets, fixed transcripts from a three-ASR ensemble, an automatic target scorer, and initial results for seven product TTS systems. We additionally report ASR-route diagnostics, ASR-subset ablations, category-level results, confidence intervals, and provider configuration metadata. The best system reaches 0.879 strict accuracy, while several systems remain below 0.60.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15532

EIBench: A Simulator-Based Benchmark and Turn-Credit RL for Emotion Management

作者:

Rongzhi Zhu↗Xiang Huang↗Yuchuan Wu↗Rui Wang↗Zequn Sun↗Tao Ren↗Weiyao Luo↗Bingxue Qiu↗Jieping Ye↗Yongbin Li↗Wei Hu↗

Emotional intelligence (EI) in Large Language Models (LLMs) is often evaluated through static understanding tasks or single-response dialogue generation. However, emotion management is interactive: a good model should not only recognize a user's emotion, but also improve the user's emotional and relational state over several turns. We introduce EIBench, a simulator-based benchmark for interactive emotion management. EIBench contains 2,222 scenarios, with 2,009 for training and 213 for held-out testing. The scenarios are organized by a 2x2 taxonomy covering Support, Defense, Repair, and Charm, which together capture different forms of support, boundary maintenance, trust repair, and rapport building. In each scenario, an LLM simulator plays the user, updates an emotion-relation state after each turn, and maps the final state to an anchor-based score. This design makes EIBench both an evaluation benchmark and a training environment: the final state gives the outcome reward, while the per-turn state updates provide dense feedback for RL. We evaluate 15 open- and closed-source LLMs. Current models perform well on support and rapport-building scenes, but struggle with boundary maintenance under user pressure. To improve the EI ability of LLMs, we propose Centered Turn-Credit GRPO (CTC-GRPO), a GRPO extension that reuses the simulator's per-turn state updates as dense turn-level feedback while preserving the final outcome reward. CTC-GRPO improves Qwen3-8B from -22.4 to +22.4 on EIBench and also improves on out-of-distribution evaluations including SAGE (+12.4) and EQBench3 (+20.9%). Our results show that simulator-tracked user states can support both evaluation and training for multi-turn emotion management.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15449

Transfer Learning for FHIR Questionnaire Terminology Binding

作者:

Maxim Gorshkov↗

Electronic prior authorization workflows require FHIR Questionnaire items to carry LOINC codes, yet most items in the HL7 Da Vinci CDS-Library lack these bindings. We treat this as a retrieval problem: given a Questionnaire item's text, find the correct LOINC code in a pool of 97,314 active codes. We compare six methods (TF-IDF, frozen MiniLM, BioBERT, BioLORD, contrastively fine-tuned MiniLM, and a TF-IDF+GPT reranker) on a 54-item evaluation set spanning three query styles (natural question, medium, and terse). No single method wins on every metric. BioLORD, a frozen encoder pre-trained on biomedical ontology definitions, has the best top-rank accuracy (R@1 = 0.185, MRR = 0.246) despite seeing no task-specific data, while a contrastive fine-tune on raw LHC-Forms pairs takes R@5 (0.389) and R@10 (0.426). A distribution-shift ablation shows why the fine-tune in our main table is not the strongest one: adding GPT-generated paraphrases to the raw pairs drops R@5 from 0.389 to 0.296, so the augmented union underperforms raw-only training on every metric except R@1. Performance peaks at 5k training pairs. Error analysis on BioLORD's R@1 failures shows that wrong-specificity and ambiguous-text cases together account for 59% of errors.

阅读与讨论 → 访问原文 →