探索全球前沿学术脉络

01.

medRxiv (Medicine) 2026-06-22 DOI: HASH:d1abab03c8da17f1ec001ec8eed34b15

Study protocol: Feasibility and clinical implications of real-time cerebral autoregulation monitoring in major noncardiac surgery with the Medtronic Cotrending algorithm (AUTOREGULATE-NONCARDIAC-COTRENDING)

作者:

Gross↗Schindler↗Vogt↗A. P↗Pietsch↗Filipovic↗Steiner↗L. A↗Wanner↗P. M↗

Background: Perioperative hypotension is associated with postoperative organ injury. However, trials of hypotension avoidance have not found meaningful improvements in postoperative cardiovascular, renal, neurological or functional outcomes. One possible explanation is that organ perfusion depends on patients individual autoregulatory ranges. Hence, technology enabling monitoring of the autoregulatory status of vital organs, e.g. the brain, could provide a physiologic basis for personalising of blood pressure targets. However, current established methodologies for monitoring cerebral autoregulation in noncardiac surgery, e.g. the cerebral oximetry index (COx), are limited by performance and usability. The Medtronic Cotrending algorithm has been developed to provide automated, near real-time assessment of cerebral autoregulation. While feasibility was demonstrated in cardiac surgery, its applicability in major noncardiac surgery remains unknown. This study aims to evaluate the technical feasibility and clinical implications of Cotrending-based cerebral autoregulation monitoring in major noncardiac surgery. Objectives: Primary objective: To evaluate the technical feasibility of using the Medtronic Cotrending algorithm to monitor intraoperative cerebral autoregulation in real-time during major noncardiac surgery, drawing comparisons to the COx algorithm. Secondary objectives: to investigate the potential clinical implications of Cotrending-based cerebral autoregulation monitoring. Design: Single-centre, prospective cohort study. Setting: Swiss tertiary care centre Patients: Patients enrolled in AUTOREGULATE-NONCARDIAC who were monitored intraoperatively with the Medtronic INVOS(TM) 5100 near-infrared spectroscopy (NIRS) system. Outcomes: Technical feasibility outcomes include success rate of determination of the lower limit of cerebral autoregulation, intraoperative uptime, time to first estimate of the lower limit of cerebral autoregulation, sensitivity to external factors and to data artefacts; agreement of Cotrending-derived lower limit of cerebral autoregulation with COx-derived lower limit of cerebral autoregulation. Conclusions: N/A Trial registration: Clinicaltrials.gov NCT07630129

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2605.03940

Reentrant value fields as delayed coupled reaction-diffusion systems on finite graphs

作者:

Karsten Bohlen↗

arXiv:2605.03940v4 Announce Type: cross Abstract: We describe a dynamical system in which a symbolic field is coupled to a geometric field via a bipartite Hilbert-Schmidt kernel. The system is fully described by a retarded functional differential equation (RFDE) on the history space, subject to Lipschitz and small gain conditions. We show that the RFDE is well-posed under constant input and that it admits a compact global attractor. The principal subsystem $(H_L, X_R, P)$, which is comprised of the two primary fields as well as an executive field, is shown to be globally stable independent of delay, provided that the interfield coupling satisfies $C_{\mathcal{K}}^2

阅读与讨论 → 访问原文 →

03.

arXiv (quant-ph) 2026-06-25 DOI: arXiv:2606.24932

Recursive QLSTM with Dynamic Variational Quantum Circuit Adaptation

作者:

Samuel Yen-Chi Chen↗Yifeng Peng↗Jiun-Cheng Jiang↗Chun-Hua Lin↗Kuo-Chung Peng↗Junghoon Justin Park↗Huan-Hsin Tseng↗Hsin-Yi Lin↗Kuan-Cheng Chen↗Chen-Yu Liu↗Shinjae Yoo↗

arXiv:2606.24932v1 Announce Type: new Abstract: Recent advances in quantum computing and machine learning have motivated the development of quantum models for sequential data processing. In this paper, we propose a Recursive Quantum Long Short-Term Memory model, or Recursive QLSTM, which extends QLSTM through metacore-based recursive constructions. We numerically test the model under different input sequence lengths, metacore designs, and recursive rules, and identify the best-performing architecture among these variants. For this selected model, we further provide theoretical arguments explaining why its recursive structure improves temporal information propagation and enhances learning performance. Our results suggest that Recursive QLSTM offers a flexible and effective framework for quantum recurrent learning over input time series of various lengths.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2512.15133

HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens

作者:

Yi Zhou↗Haohao Qu↗Yunqing Liu↗Shanru Lin↗Le Song↗Wenqi Fan↗

arXiv:2512.15133v3 Announce Type: replace-cross Abstract: Proteins inherently possess a consistent sequence-structure duality. The abundance of protein sequence data, which can be readily represented as discrete tokens, has driven fruitful developments in protein language models (pLMs). A key remaining challenge, however, is how to effectively integrate continuous structural knowledge into pLMs. Current methods often discretize protein structures to accommodate the language modeling framework, which inevitably results in the loss of fine-grained information and limits the performance potential of multimodal pLMs. In this paper, we argue that such concerns can be circumvented: a sequence-based pLM can be extended to incorporate the structure modality through continuous tokens, i.e., high-fidelity protein structure latents that avoid vector quantization. Specifically, we propose a hybrid diffusion protein language model, HD-Prot, which embeds a continuous-valued diffusion head atop a discrete pLM, enabling seamless operation with both discrete and continuous tokens for joint sequence-structure modeling. It captures inter-token dependencies across modalities through a unified absorbing diffusion process, and estimates per-token distributions via categorical prediction for sequences and continuous diffusion for structures. Extensive results demonstrate that HD-Prot achieves competitive performance in unconditional sequence-structure co-generation, motif-scaffolding, protein structure prediction, and inverse folding tasks. Furthermore, our method can perform on par with state-of-the-art multimodal pLMs, despite being developed under limited computational resources (i.e., less than one-tenth the budget for modality extension fine-tuning). It highlights the viability of simultaneously estimating categorical and continuous distributions within a unified language model architecture, offering a promising alternative direction for multimodal pLMs.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2605.02849

Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion

作者:

Amirhosein Javadi↗Shirin Saeedi Bidokhti↗Tara Javidi↗

Diffusion models provide a powerful generative prior for perceptual reconstruction at ultra-low bitrates, but effective video compression requires controlling the generative process using highly compact conditioning signals. In this work, we present ActDiff-VC, a diffusion-based video compression framework for the ultra-low-bitrate regime. Our method partitions videos into variable-length segments, transmits keyframes only when needed, and summarizes temporal dynamics using a compact set of tracked point trajectories. Conditioned on these sparse signals, a conditional diffusion decoder synthesizes the remaining frames, enabling perceptually realistic reconstruction under severe rate constraints. To support this design, we introduce two mechanisms: content-adaptive keyframe selection and budget-aware sparse trajectory selection, which together enable compact yet effective conditioning for generative reconstruction. Experiments on the UVG and MCL-JCV benchmarks show that ActDiff-VC achieves up to 64.6\% bitrate reduction at matched NIQE, improves KID by up to 64.6\% and FID by up to 37.7\% at comparable bitrates against strong learned codecs, and delivers favorable perceptual rate–distortion trade-offs relative to learned and diffusion-based baselines in the ultra-low-bitrate regime.

阅读与讨论 → 访问原文 →

06.

arXiv (quant-ph) 2026-06-25 DOI: arXiv:2606.25974

Tensor network characterization and mitigation of readout errors

作者:

Yuchen Guo↗Shuo Yang↗

arXiv:2606.25974v1 Announce Type: new Abstract: Readout errors are a major bottleneck to extracting reliable information from near-term quantum processors, especially when spatial correlations are non-negligible. We present a unified tensor-network framework that models the readout process as a matrix product operator (MPO), enabling efficient characterization and mitigation beyond uncorrelated approximations. The MPO model is trained via likelihood optimization on calibration data and applies to multiple tasks, including nonlocal observable estimation, random circuit sampling, and random-measurement protocols, such as classical shadows and learning-based tomography. Experiments on a superconducting processor and numerical simulations up to 20 qubits show that the MPO model captures correlated readout errors that uncorrelated models miss, with a sample cost that grows only near-linearly with system size. When extended to two-dimensional systems, the framework can also be integrated with tensor-network quantum error-correction decoders by performing joint inference over data and readout errors. These results establish tensor-network readout error mitigation as a scalable and versatile approach for noise-aware quantum data processing.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16278

RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos

作者:

Zhenhua Wu↗Yun Pang↗Mingkun Chang↗Yuwei Ning↗Liangzhi Wang↗Yi Xiao↗Guanbin Li↗

Long-tail hazardous scenarios are essential for safety-oriented autonomous driving, yet they are difficult to collect and reproduce at scale. Editable 3D Gaussian Splatting (3DGS) simulation offers a promising alternative by reconstructing real driving scenes and supporting controllable scene editing. However, edited 3DGS-rendered videos still suffer from a significant Sim-to-Real gap, including rendering artifacts, degraded foreground assets, inconsistent illumination, and temporal flickering. Existing restoration and video generation methods are insufficient for this task, as they often fail to jointly repair 3DGS-specific artifacts, improve visual realism, and ensure temporal consistency. To fill this gap, we propose RealityBridge, a structure-preserving and asset-aware Sim-to-Real framework for edited 3DGS driving videos. RealityBridge uses multimodal controls, including rendered videos, foreground masks, edge maps, and semantic masks, together with a lightweight GateNet for adaptive condition allocation across backbone layers. We further construct targeted training data and introduce autoregressive long-video training with reward-guided post-training to improve restoration quality, temporal stability, and hallucination suppression. Extensive experiments on internal and public driving datasets show that RealityBridge outperforms existing methods in artifact removal, illumination harmonization, and long-sequence temporal consistency.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2601.22594

Language Model Circuits Are Sparse in the Neuron Basis

作者:

Aryaman Arora↗Zhengxuan Wu↗Jacob Steinhardt↗Sarah Schwettmann↗

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques which decompose the neuron basis into more interpretable units of model computation, such as sparse autoencoders (SAEs). However, not all neuron-based representations are uninterpretable. For the first time, we empirically show that MLP neurons are as sparse a feature basis as SAEs. We use this finding to develop an end-to-end gradient-based attribution pipeline for circuit tracing on the MLP neuron basis, which surfaces causally effective neurons on a variety of tasks. On a standard subject-verb agreement benchmark (Marks et al., 2025), a circuit of $\approx 10^2$ MLP neurons is enough to control model behaviour. On the multi-hop city-state-capital task from (Lindsey et al., 2025), we find a circuit in which small sets of neurons encode specific latent reasoning steps (e.g. mapping a city to its state), and can be steered to change the model's output. This work thus advances automated interpretability of language models without imposing additional training costs.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2602.13379

Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents

作者:

Xu Li↗Simon Yu↗Minzhou Pan↗Yiyou Sun↗Bo Li↗Dawn Song↗Xue Lin↗Weiyan Shi↗

LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in multi-turn interactions and employ diverse tools, introducing new risks overlooked by existing benchmarks. To systematically scale safety testing into multi-turn, tool-realistic settings, we propose a principled taxonomy that transforms single-turn harmful tasks into multi-turn attack sequences. Using this taxonomy, we construct MT-AgentRisk (Multi-Turn Agent Risk Benchmark), the first benchmark to evaluate multi-turn tool-using agent safety. Our experiments reveal substantial safety degradation: the Attack Success Rate (ASR) increases by 16% on average across open and closed models in multi-turn settings. To close this gap, we propose ToolShield, a training-free, tool-agnostic, self-exploration defense: when encountering a new tool, the agent autonomously generates test cases, executes them to observe downstream effects, and distills safety experiences for deployment. Experiments show that ToolShield effectively reduces ASR by 30% on average in multi-turn interactions. Our code is available at https://github.com/CHATS-lab/ToolShield.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.04474

Entity Binding Failures in Speech LLM Reasoning: Diagnosis and Chain-of-Thought Intervention

作者:

Ming-Hao Hsu↗Xiaohai Tian↗Jun Zhang↗Zhizheng Wu↗

Speech Large Language Models (SLLMs) underperform their text counterparts on complex reasoning. We reveal that this gap is not a uniform cognitive deficit. Evaluating two architecturally diverse SLLMs, we show speech-to-text (S2T) matches or exceeds text-to-text (T2T) on spatial, syntactic, and factual tasks. Yet on logical tasks requiring entity tracking, S2T accuracy collapses to chance. We diagnose this as an entity binding failure: continuous speech features blur precise entity-property associations during implicit reasoning. To validate this diagnosis, we introduce Entity-Aware Chain-of-Thought (EA-CoT), a lightweight inference-time intervention forcing SLLMs to enumerate entities and bind them to claims before reasoning. EA-CoT bridges the gap, even when spoken names are misrecognized, yielding up to a 24.4 percentage-point accuracy gain. Ablations confirm the gains stem from explicit semantic binding, reframing the gap as an elicitation failure rather than a missing capability.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19352

Sign-Language Datasets at Scale: A Comprehensive Survey on Resources, Benchmarks, and Annotation Standards

作者:

Yiming Ni↗Zhi-Qi Cheng↗Jiayu Li↗Wei Cheng↗

Sign languages are expressive visual languages used by Deaf and Hard-of-Hearing (DHH) communities. Despite substantial progress in sign-language recognition, translation, and production, advances remain constrained by fragmented datasets, inconsistent annotations, and limited linguistic coverage. Existing benchmarks often fail to reflect real-world communication needs, and systematic analyses of these limitations remain limited. In this survey, we present a comprehensive index of sign-language datasets, covering 120 resources across 35 sign languages. We analyze key challenges such as modality imbalance, annotation granularity, and signer bias, and outline considerations for future dataset design. We also introduce a 24-field Sign-Language Datasheet and release a public GitHub repository (https://github.com/Ginqwerty/Open-Sign-Language) to support standardized documentation and reproducible evaluation. Overall, our work provides a unified and practical foundation for developing inclusive, robust, and scalable sign-language technologies in real-world applications.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2407.04884

Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy

作者:

Rob Romijnders↗Antti Koskela↗

arXiv:2407.04884v4 Announce Type: replace Abstract: The hidden state threat model of differential privacy (DP) assumes that the adversary has access only to the final trained machine learning (ML) model, without seeing intermediate states during training. However, the current privacy analyses under this model are restricted to convex optimization problems, reducing their applicability to multi-layer neural networks, which are essential in modern deep learning applications. Notably, the most successful applications of the hidden state privacy analyses in classification tasks have only been for logistic regression models. We demonstrate that it is possible to privately train convex problems with privacy-utility trade-offs comparable to those of 2-layer ReLU networks trained with DP stochastic gradient descent (DP-SGD). This is achieved through a stochastic approximation of a dual formulation of the ReLU minimization problem, resulting in a strongly convex problem. This enables the use of existing hidden state privacy analyses and provides accurate privacy bounds also for the noisy cyclic mini-batch gradient descent (NoisyCGD) method with fixed disjoint mini-batches. Empirical results on benchmark classification tasks demonstrate that NoisyCGD can achieve privacy-utility trade-offs on par with DP-SGD applied to 2-layer ReLU networks.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.14981

Inference-time Policy Steering via Vision and Touch

作者:

Yilin Wu↗Zilin Si↗Zeynep Temel↗Oliver Kroemer↗Andrea Bajcsy↗

arXiv:2606.14981v1 Announce Type: cross Abstract: Inference-time steering adapts pre-trained generative robot policies during deployment by verifying candidate actions before execution. While prior methods typically perform this verification only with visual observations, vision alone is often insufficient for contact-rich manipulation, where success depends on both global task progress and subtle local interactions such as contact force. We introduce ViTaL, a visuo-tactile inference-time steering framework that formulates multimodal guidance as a bi-level optimization problem. At the high level, visual sampling-and-verification performs long-horizon mode selection, deciding what behavior the robot should execute. At the low level, tactile-guided diffusion editing refines the selected action sequence over a shorter horizon to satisfy local contact requirements. To support outcome-based steering, ViTaL learns a visuo-tactile latent world model and employs semantically aligned visual and tactile verifiers, including a novel text-conditioned tactile reward that scores predicted tactile futures directly in latent space. Across three real-world contact-rich manipulation tasks, ViTaL improves overall success by 51% over the base policy, outperforms unimodal steering by at least 33%, and exceeds naive multimodal fusion by at least 20%. Website: https://yilin-wu98.github.io/vital_website.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CL) 2026-06-25 DOI: arXiv:2511.05933

Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs

作者:

Renfei Zhang↗Manasa Kaniselvan↗Rylan Schaeffer abd Niloofar Mireshghallah↗

Reinforcement learning (RL) is often credited with improving language model reasoning at the expense of knowledge. We challenge this narrative by showing that reasoning models consistently outperform their instruction-tuned versions on pure knowledge recall tasks. These gains do not reflect newly acquired information, but rather an improved procedural skill in navigating and searching existing knowledge hierarchies within the model parameters. Structured prompting, which explicitly guides models through hierarchical traversal – recovers most of the instruct-reasoning gap across five model families. A controlled RL experiment on unseen, non-extractable facts improves recall of held-out frequent but previously inaccessible facts, ruling out simple data exposure. On depth-stratified retrieval tasks, reasoning models exhibit superior traversal as retrieval depth grows. Layerwise activation analysis further shows that while factual representations maintain high cosine similarity between instruct and reasoning models, query representations diverge noticeably, indicating that reasoning primarily reshapes how models traverse knowledge rather than the knowledge representation itself. Finally, we find that distilled models often fail to match reasoning models on knowledge recall because they imitate self-correction without acquiring the exploratory behavior needed for hierarchical navigation. Together, these findings suggest that improving factual recall in LLMs depends not only on expanding what models know but also on teaching them to navigate it – motivating future post-training methods that optimize traversal.

阅读与讨论 → 访问原文 →

15.

arXiv (math.PR) 2026-06-12 DOI: arXiv:2606.12820

Averaging principles for nonautonomous multiscale McKean-Vlasov stochastic systems

作者:

Jie Xiang↗Huijie Qiao↗

arXiv:2606.12820v1 Announce Type: new Abstract: This paper investigates a class of nonautonomous multiscale McKean-Vlasov stochastic systems. By leveraging the nonautonomous Poisson equation, we rigorously establish both strong and weak averaging principles, accompanied by explicit convergence rates. Notably, the coefficients of the averaging equations derived in the general case retain dependence on the scaling parameter $\varepsilon$. However, under the additional assumptions that the fast-scale coefficients are either asymptotically convergent or time-periodic, we demonstrate that the slow component converges, in the strong or weak sense, to averaging equations with coefficients independent of $\varepsilon$.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2603.12120

CRAFT: A Tendon-Driven Hand with Hybrid Hard-Soft Compliance

作者:

Leo Lin↗Shivansh Patel↗Jay Moon↗Svetlana Lazebnik↗Unnat Jain↗

arXiv:2603.12120v2 Announce Type: replace-cross Abstract: We introduce CRAFT hand, a tendon-driven anthropomorphic hand with hybrid hard-soft compliance for contact-rich manipulation. The design is based on a simple idea: contact is not uniform across the hand. Impacts concentrate at joints, while links carry most of the load. CRAFT places soft material at joints and keeps links rigid, and uses rollingcontact joint surfaces to keep flexion on repeatable motion paths. Fifteen motors mounted on the fingers drive the hand through tendons, keeping the form factor compact and the fingers light. In structural tests, CRAFT improves strength and endurance while maintaining comparable repeatability. In teleoperation, CRAFT improves handling of fragile and low-friction items, and the hand covers 33/33 grasps in the Feix taxonomy. The full design costs under $600 and will be released open-source with visionbased teleoperation and simulation integration. Project page: http://craft-hand.github.io/

阅读与讨论 → 访问原文 →

17.

bioRxiv (Bioinfo) 2026-06-11 DOI: HASH:7d877a310c7064fcfc6915949d100b91

DeePEn - A Depth sensitive benchmark for Protein Engineering

作者:

Schmirler↗Brenner↗Franz↗Heinzinger↗Rost↗

Recent progress in modeling techniques and high-throughput screening has significantly enhanced the accessibility of protein engineering. Nevertheless, further progress gets hindered by the lack of robust benchmarks that capture the practical challenges for real-world protein engineering. Here, we introduced DeePEn, a Depth-sensitive benchmark for Protein Engineering that quantifies a models generalization capabilities when predicting protein fitness at increasing mutational distance from the wildtype or training data. We defined distance as the number of simultaneous point mutations, i.e., single amino acid variants (SAVs), moving from wild-type to mutant (edit distance in computer science jargon). Specifically selecting four deep mutational scanning (DMS) datasets with sufficient multi-mutation data points from ProteinGym, we assessed recent predictive models, including general and biophysics-informed protein Language Models (pLMs), and a non-transformer neural network. Our results highlight how the performance of all models deteriorates with increasing mutational distance and that no single metric sufficiently captures the diverse requirements of protein engineering. To overcome these shortcomings, DeePEn provides a readily available resource for multi-metric benchmarking that focuses on the prediction of distant variants.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2605.12567

Pyramid Self-Contrastive Learning for Single-shot Test-time Ultrasound Image Denoising

作者:

Jiajing Zhang↗Bingze Dai↗Xi Zhang↗Yue Xu↗Wei-Ning Lee↗

The inherent electronic and speckle noise complicates clinical interpretation of ultrasound images. Conventional denoising methods rely on explicit noise assumptions whose validity diminishes under composite noise conditions. Learning-based methods are usually pretrained in a limited image domain using a labeled dataset, which implies inevitable domain shift in complex in vivo environments. This study proposes a Pyramid Self-Contrastive Learning (PSCL) framework for test-time ultrasound image denoising without pretraining. Given multiple noisy samples from only one-shot imaging, PSCL disentangles anatomical similarity and noise randomness into separate pyramid latent spaces. The clean image is then decoded from the anatomy space while discarding the noise space. We first apply PSCL to synthetic aperture ultrasound (SAU), where an Aperture-to-Aperture loop serves as a self-supervised proxy task to ensure denoising fidelity. Simulation experiments, including noise levels from 0 to 30 dB and inclusion geometries from simple to complex, demonstrated improvements of 69.3% in SNR and 34.4% in CNR. The in vivo results showed 84.8% SNR and 25.7% CNR gains using only two aperture data of the heart in six echocardiographic views, liver, and kidney. PSCL delivers clear images across diverse imaging targets and configurations, paving the way for more reliable anatomical visualization without domain shift and pretraining costs.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2507.20208

From Benchmarks to Skills: Low-Rank Factors for LLM Evaluation

作者:

Aviya Maimon↗Amir DN Cohen↗Gal Vishne↗Shauli Ravfogel↗Reut Tsarfaty↗

Current evaluations of large language models (LLMs) rely heavily on a growing collection of benchmarks and on aggregate benchmark scores, yet it remains unclear what this comparison actually captures, and what these scores reveal about models' underlying capabilities. Here, we propose a new paradigm for LLM evaluation, by asking whether benchmark performance reflects many independent abilities, or rather relies on a small number of shared dimensions. To answer this, we apply Factor Analysis (FA) to a massive performance matrix of LLMs versus benchmarks \((60\times44)\) revealing an intrinsically low-rank structure of that matrix. That is, a small number of latent factors captures most of the structure in the full task space. This low-rank geometry reveals substantial redundancy across existing tasks and explains why many benchmarks appear to be measuring overlapping abilities. We further show that these latent factors correspond to coherent, skill-like, dimensions of LLM behavior. Leveraging this latent skill-space, we deliver three practical tools for LLM evaluation and downstream users: (i)~identifying redundant tasks, (ii)~profiling new models using a small subset of tasks, and (iii)~selecting models aligned with desired skill profiles. Our method provides a solid alternative to the de-facto standard of a single aggregate score, and establishes an interpretable and practical framework for understanding and benchmarking LLM core capabilities.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.17062

RadSEM: A Finding-by-Finding Metric for Clinical Consistency in Radiology Reports

作者:

Zhenhong Yang↗Zhuoyun Liu↗Jintao Fei↗Wen Tang↗Shichao Quan↗Jun Zhao↗Jun Xu↗

arXiv:2606.17062v1 Announce Type: cross Abstract: Radiology report evaluation must distinguish clinical compatibility from surface similarity, because negation, laterality, or normal-abnormal polarity can reverse a finding. We propose RadSEM (Radiology Sentence-Level Evaluation Metric), a constrained LLM-assisted metric for reference-based evaluation of radiology Findings. RadSEM rewrites reference and generated reports into ordered atomic finding sentences, each expressing one site-finding proposition. It then performs contradiction-constrained many-to-many matching: incompatible pairs such as "effusion" and "no effusion" receive no credit, while compatible granularity differences can receive partial credit. A deterministic stage weights pairs by part-whole and abnormal-detail relationships, counts unmatched findings, and produces an abnormal-focused weighted F1 score. Thus, the LLM supports structured rewriting and local alignment rather than acting as an opaque judge. We evaluate RadSEM with SSREE, a controlled monotonicity stress test built from 2,448 de-identified reports expanded into five graded corruption levels. RadSEM achieves Kendall tau_b of 0.957, all-pairs concordance of 97.8%, adjacent concordance of 95.0%, and strict five-level ordering for 81.9% of reports, outperforming radiology-specific and general text metrics while avoiding the failure in which polarity-inverted reports regain lexical overlap. On the same SSREE set, RadSEM outperforms the Ref-anchored RadSEM-Alt policy, improving adjacent concordance from 90.7% to 95.0% and strict ordering from 67.2% to 81.9%. On a 599-triplet synonym/antonym subset, RadSEM prefers synonyms in 597 cases (99.67%). These results suggest that explicit finding units, contradiction-aware matching, and abnormal-focused deterministic scoring make report scoring more interpretable and sensitive to clinically meaningful errors. Code is available at https://github.com/jdh-algo/RadSEM.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.LG) 2026-06-25 DOI: arXiv:2606.24970

Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration

作者:

Pietro Tropeano↗Maria Maistro↗Tuukka Ruotsalo↗Christina Lioma↗

arXiv:2606.24970v1 Announce Type: new Abstract: Pruning Large Language Models (LLMs) reduces memory and inference costs by removing parts of the network, producing smaller models that retain most of their accuracy. As attention layers are the most resource-intensive parts of LLMs, pruning them is a promising compression strategy. Prior work shows that up to 33% of attention layers can be pruned with minimal accuracy loss. Nevertheless, the impact of attention pruning on model interpretability, specifically faithfulness and confidence calibration, remains unstudied. To address this gap, we study how pruning attention layers affects explanation faithfulness and confidence calibration across five LLMs and eight datasets. While the pruned models often maintain high accuracy, we find that their faithfulness and calibration often degrade. Notably, faithfulness and calibration can fluctuate significantly, even when accuracy remains stable, highlighting a misalignment between model confidence, interpretability, and accuracy. Our findings suggest that layer pruning can affect LLMs' interpretability and reliability in ways not captured by accuracy and efficiency measures alone. We recommend including explainability and calibration metrics when evaluating pruned models.

阅读与讨论 → 访问原文 →

22.

arXiv (math.PR) 2026-06-17 DOI: arXiv:2606.17604

Spectral recovery of a planted triangle-dense subgraph

作者:

Sam van der Poel↗Cheng Mao↗Benjamin McKenna↗

arXiv:2606.17604v1 Announce Type: cross Abstract: Given a simple graph on $n$ vertices and a parameter $k$, the triangle-densest-$k$-subgraph problem is known to be computationally hard in the worst case. To circumvent the computational hardness, we study an average-case model where a triangle-dense subgraph on $k$ vertices is planted in an Erdős-Rényi random graph on $n$ vertices. For the recovery of the planted subgraph, we propose a simple spectral algorithm and a semidefinite program, both of which use a graph matrix whose entries are local signed triangle counts. Theoretical guarantees for these algorithms are established through spectral analysis of the graph matrix. Finally, we provide evidence showing a statistical-to-computational gap analogous to that for the planted clique problem. The computational threshold in terms of the subgraph size $k$ is at least $\sqrt{n}$ in the framework of low-degree polynomial algorithms, while the information-theoretic threshold is at most logarithmic in $n$.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.AI) 2026-06-25 DOI: arXiv:2602.15438

Logit Distance Bounds Representational Similarity

作者:

Beatrix M. G. Nielsen↗Emanuele Marconato↗Luigi Gresele↗Andrea Dittadi↗Simon Buchholz↗

arXiv:2602.15438v3 Announce Type: replace-cross Abstract: For a broad family of discriminative models that includes autoregressive language models, identifiability results imply that if two models induce the same conditional distributions, then their internal representations are equal up to an invertible linear transformation. We ask whether an analogous conclusion holds approximately when the distributions are close instead of equal. Building on the observation of Nielsen et al. (2025) that closeness in KL divergence need not imply high linear representational similarity, we study a distributional distance based on logit differences and show that closeness in this distance does yield linear similarity guarantees. Specifically, we define a representational dissimilarity measure based on the models' identifiability class and prove that it is bounded by the logit distance. We further show that, when model probabilities are bounded away from zero, KL divergence upper-bounds logit distance; yet the resulting bound fails to provide nontrivial control in practice. As a consequence, KL-based distillation can match a teacher's predictions while failing to preserve linear representational properties, such as linear-probe recoverability of human-interpretable concepts. In distillation experiments on synthetic and image datasets, logit-distance distillation yields students with higher linear representational similarity and better preservation of the teacher's linearly recoverable concepts.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CL) 2026-06-24 DOI: arXiv:2601.11957

PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning

作者:

Bingxuan Li↗Jeonghwan Kim↗Cheng Qian↗Xiusi Chen↗Eitan Anzenberg↗Niran Kundapur↗Heng Ji↗

Overlapping calendar invitations force busy professionals to repeatedly decide which meetings to attend, reschedule, or decline. We refer to this preference-driven decision process as calendar conflict resolution. Automating this decision process is crucial yet challenging. Scheduling logistics can drain hours, and human delegation often fails at scale, which motivates us to ask: Can we trust large language models (LLMs) or language agents to manage time? To enable a systematic study of this question, we introduce CalConflictBench, a benchmark for long-horizon calendar conflict resolution. In CalConflictBench, conflicts are presented to agents round-by-round over a calendar year, requiring them to infer and adapt to user preferences progressively. Our experiments show that current LLM agents perform poorly with high error rates, e.g., Qwen-3-30B-Think has an average error rate of 35%. To address this gap, we propose PEARL, a reinforcement-learning framework that (i) augments the language agent with an external preference memory that stores and updates inferred strategies (e.g., attendee priorities, topic importance, time/location preferences), and (ii) optimizes the agent with round-wise rewards that directly supervise decision correctness, ranking quality, and memory usage across rounds. Experiments on CalConflictBench show that PEARL achieves an error reduction rate of 0.76 and a 55% improvement in average error rate compared to the strongest baseline.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14582

A Temporal Planning Framework for Disruption Aware Dynamic Route Optimization in Heterogeneous Railway Systems

作者:

Pollob Chandra Ray↗Sabah Binte Noor↗Fazlul Hasan Siddiqui↗

arXiv:2606.14582v1 Announce Type: new Abstract: Efficient route optimization play a vital role in ensuring both safety and punctuality in railway operations. It is very crucial particularly in heterogeneous multi-gauge railway networks with varying train speed, stopping pattern, infrastructure compatibility constraints increase coordination complexity. In single-track systems these challenges are further intensify due to all trains to share the same track and requires frequent track switching.Stochastic disruptions events including blocked tracks, blocked trains, engine failure and speed slowdowns introduces additional unpredictability in operations and deviate the timetable. However, existing studies predominantly focuses on high-level timetabling, omitting operational details such as track switching coordination. As a result leaving decision to human operators, increasing safety risks into railway operations. This study proposes a framework based on temporal planning for dynamic route optimization and disruption management in heterogeneous railway systems. The framework formulates railway operations as a temporal planning problem using PDDL 2.1 with explicitly modeling gauge compatibility constraints and diverse disruption scenarios. It generates conflict-free timestamped operational plans specifying both optimized schedules and executable action sequences. To evaluate the proposed framework, we developed a benchmark problem set with 200 instances using up to 1,000 track points and 120 trains. Two state-of-the-art temporal planners and a plan validator were employed to assessed the framework. The experimental results demonstrate that the framework effectively generates temporal operational plans for heterogeneous railway systems and handles multi-gauge constraints, disruptions, and reduces dependence on manual decision making.

阅读与讨论 → 访问原文 →