Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

02.
arXiv (CS.CL) 2026-06-15

OLaPh: Optimal Language Phonemizer

Phonemization is a critical component in text-to-speech synthesis. Traditional approaches rely on deterministic transformations and lexica, while neural methods offer potential for higher generalization on out-of-vocabulary (OOV) terms. We introduce OLaPh (Optimal Language Phonemizer), a hybrid framework that integrates extensive multilingual lexica with advanced NLP techniques and a statistical subword segmentation function. Evaluations on the WikiPron benchmark show OLaPh significantly outperforms established baselines in overall accuracy and maintains robustness on OOV data through advanced fallback mechanisms. To further explore neural generalization, we utilize the framework to synthesize a high-consistency training corpus for an instruction-tuned Large Language Model (LLM). While the deterministic framework remains more accurate overall, the LLM demonstrates strong generalization, matching or partly exceeding the framework's performance. This suggests that the LLM successfully internalized phonetic intuitions from the synthetic data that transcend the framework's capabilities. Together, these tools provide a comprehensive, open-source resource for multilingual grapheme-to-phoneme conversion (G2P) research.

03.
arXiv (CS.CV) 2026-06-16

Position: The Systemic Lack of Agency in Visual Reasoning

This paper argues that a systemic lack of Agency constrains the implicit reasoning capabilities of current Vision-Language Models (VLMs). Implicit reasoning refers to the ability to autonomously discover and utilize hidden visual evidence to bridge information gaps, rather than merely relying on explicitly specified targets. This capacity underlies human visual understanding and everyday reasoning. We argue that this limitation arises from a tendency to approach visual reasoning primarily as passive semantic retrieval, rather than as active, situated reasoning that depends on autonomous visual exploration. As a result, most existing benchmarks primarily assess Passive Capacity, leaving this aspect of reasoning largely unmeasured. To address this gap, we introduce the Visual Implicit Reasoning Diagnosing Benchmark (V-IRD), which targets this missing quadrant by requiring models to derive answers strictly through autonomous visual analysis. Our results show that, despite strong retrieval abilities, prominent VLMs struggle to utilize reference objects and to attend to visual evidence that requires self-directed inquiry. Simply put, strong semantic recognition does not equate to active visual exploration, revealing a critical gap in current VLMs. More information can be found at https://haoychen.github.io/Implicit-Reasoning/

04.
arXiv (CS.CV) 2026-06-11

ReMoT: Reinforcement Learning with Motion Contrast Triplets

We present ReMoT, a unified training paradigm to systematically address the fundamental shortcomings of VLMs in spatio-temporal consistency – a critical failure point in navigation, robotics, and autonomous driving. ReMoT integrates two core components: (1) A rule-based automatic framework that generates ReMoT-16K, a large-scale (16.5K triplets) motion-contrast dataset derived from video meta-annotations, surpassing costly manual or model-based generation. (2) Group Relative Policy Optimization, which we empirically validate yields optimal performance and data efficiency for learning this contrastive reasoning, far exceeding standard Supervised Fine-Tuning. We also construct the first benchmark for fine-grained motion contrast triplets to measure a VLM's discrimination of subtle motion attributes (e.g., opposing directions). The resulting model achieves state-of-the-art performance on our new benchmark and multiple standard VLM benchmarks, culminating in a remarkable 25.1% performance leap on spatio-temporal reasoning tasks.

05.
arXiv (CS.CV) 2026-06-16

A Dual-Branch Collaborative Framework for Joint Optimization of Underwater Image Enhancement and Object Detection

Due to wavelength dependent light absorption and scattering, underwater images usually suffer from color distortion and blurred details, which limits underwater object detection performance. Existing underwater image enhancement methods mainly focus on visual quality improvement, while it is still difficult to balance enhancement quality, processing efficiency, and downstream detection performance. Therefore, this paper proposes an efficient dual-branch underwater image enhancement framework for object detection. The detail enhancement branch improves brightness and local contrast to recover texture details in dark regions. The color restoration branch uses adaptive compensation to reduce color distortion and improve color gradation. By combining the complementary outputs of the two branches, the proposed framework provides clearer and more informative images for object detection. On the UIEB and EUVP datasets, the proposed method achieves UIQM scores of 2.249 and 2.576. When applied to the YOLOv8 detection task on the URPC dataset, the proposed method improves mAP50 by 2.1\% compared with the baseline. Extensive experiments show that our method improves object detection in complex underwater scenes, while balancing enhancement quality and processing efficiency.

06.
arXiv (CS.CV) 2026-06-16

HemExp: Clinically-Guided Latent Diffusion for Modeling Hematoma Expansion

Hematoma expansion (HE) after spontaneous intracerebral hemorrhage (ICH) is a major determinant of acute triage and treatment decisions in neurosurgical care. However, most existing methods provide either a binary expansion risk or a single follow-up volume, limiting uncertainty-aware decisions. We introduce HemExp, a clinically-guided latent diffusion model that generates patient-specific follow-up non-contrast CT images, along with segmentations of intraparenchymal and intraventricular hemorrhage. Generation is conditioned on baseline imaging, clinical variables, and an explicit expansion indicator, enabling controllable simulation of realistic clinical scenarios. HemExp uses a hemorrhage-aware multi-head variational autoencoder and models progression as the difference between baseline and follow-up latent representations with a conditional diffusion model. The model is trained on paired scans from 450 patients across multiple centers and evaluated on 107 patients from a held-out institution. HemExp produces spatial HE probability maps by generating multiple synthetic follow-up images per patient to estimate distributions of plausible follow-up hematoma volumes. Perturbing clinical inputs such as symptom-onset-to-imaging time or anticoagulant status shifts the predicted follow-up volume distribution. HemExp extends binary predictors and demonstrates robust estimation of clinically relevant outcomes in the imaging space, such as hematoma volume, intraventricular involvement, and mass effects. Overall, our results support controllable latent diffusion as a promising direction for uncertainty-aware modeling of early ICH progression.

07.
arXiv (CS.AI) 2026-06-11

MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation

arXiv:2606.11416v1 Announce Type: cross Abstract: Repository-level benchmarks for evaluating Large Language Model (LLM) code repair on Secure Multi-Party Computation (MPC) software do not yet exist, and directly transplanting general-purpose benchmarks such as SWE-bench fails on three structural fronts: (i) MPC repositories are dominated by generic Python infrastructure rather than cryptographic logic; (ii) high-value MPC fixes lack the standardized tests rigid extraction pipelines require; and (iii) standard fail-to-pass evaluation is insufficient for code that must also be cryptographically safe. MPC is increasingly deployed for privacy-preserving machine learning, biomedical collaboration, and secure analytics. Existing MPC-specific code-synthesis efforts cover only operator-level or single-framework tasks; evaluating LLM agents on real repository-level MPC repair instead demands MPC-aware data curation and a verifier matched to the security and numerical-fidelity guarantees MPC programs must obey neither of which existing benchmarks provide. We introduce MPC-Patch-Bench, a repository-level benchmark organised around two frameworks. (1)The Data Curation Framework combines a domain-specific curation agent that filters raw pull requests through three cryptographic layers with a human-AI completion engine that synthesizes missing problem statements and Fail-to-Pass/Pass-to-Pass tests, yielding 205 fully verified instances. (2)The MPC Verifier provides dedicated security and numerical-fidelity checks via dynamic differential testing against plaintext oracles and MPC-specific static analysis rules that flag unsafe reveals, insecure arithmetic, and illegal public/private casts. The strongest evaluated LLM functionally resolves only 22.9% of MPC-Patch-Bench tasks; the MPC Verifier further reduces verified resolution to 17.1%, with up to 40% of functionally-passing patches rejected for cryptographic or numerical-fidelity violations.

08.
arXiv (CS.LG) 2026-06-15

MAD: Manifold Attracted Diffusion

arXiv:2509.24710v3 Announce Type: replace-cross Abstract: Score-based diffusion models are a highly effective method for generating samples from a distribution of images. We consider scenarios where the training data comes from a noisy version of the target distribution, and present an efficiently implementable modification of the inference procedure to generate noiseless samples. Our approach is motivated by the manifold hypothesis, according to which meaningful data is concentrated around some low-dimensional manifold of a high-dimensional ambient space. The central idea is that noise manifests as low magnitude variation in off-manifold directions in contrast to the relevant variation of the desired distribution which is mostly confined to on-manifold directions. We introduce the notion of an extended score and show that, in a simplified setting, it can be used to reduce small variations to zero, while leaving large variations mostly unchanged. We describe how its approximation can be computed efficiently from an approximation to the standard score and demonstrate its efficacy on toy problems, synthetic data, and real data.

09.
arXiv (CS.AI) 2026-06-15

MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis

arXiv:2606.13782v1 Announce Type: new Abstract: Large Language Models (LLMs) have made notable progress in automated theorem proving, yet existing formal benchmarks remain limited in both mathematical coverage and difficulty. Most are concentrated in areas that are easier to formalize, such as algebra and elementary number theory, and provide limited coverage of subfields that require deeper reasoning, including mathematical analysis. To address this gap, we introduce MA-ProofBench, to the best of our knowledge, the first formal theorem-proving benchmark dedicated to Mathematical Analysis. The benchmark contains 200 formalized theorems covering 6 core topics and 27 subcategories, including measure and integration theory, complex analysis, and functional analysis. The problems are divided into two difficulty levels, an undergraduate level (Level I, 100 problems) and a Ph.D. qualifying level (Level II, 100 problems), to evaluate how well LLMs perform formal reasoning at different mathematical depths. Each problem is constructed through a human-led, LLM-assisted formalization pipeline followed by independent expert review, ensuring that the formal statements remain faithful to the original mathematics. We evaluate a range of recent general-purpose reasoning models and formal theorem provers on MA-ProofBench. However, most models perform poorly: even the best-performing model, GPT-5.5, achieves only 16% Pass@8 on Level I and 5% on Level II, while most models stay close to 0% on Level II. Further analysis identifies Mathlib hallucinations and incomplete proofs as the two dominant failure modes, while an evaluation on the natural-language version of the benchmark exposes a clear gap between informal and formal reasoning. MA-ProofBench is intended to serve as a reliable reference for tracking progress in formal mathematical reasoning in advanced domains.

10.
medRxiv (Medicine) 2026-06-23

Shared Polygenic Architecture Across Arteriopathies: An Integrative Cross-Trait Analysis

Background: Non-monogenic arteriopathies are often classified as distinct entities according to the arterial territory involved, yet they share clinical features and may co-occur in the same individual. This pattern suggests shared susceptibility across anatomically distinct arteriopathies, potentially driven by common biological and genetic mechanisms. Methods: We investigated the shared genetic architecture of five arteriopathies (cervical artery dissection (CeAD), intracranial aneurysm (IA), spontaneous coronary artery dissection (SCAD), aortic aneurysm and dissection (AAD), and fibromuscular dysplasia (FMD)) using LD score regression, Association analysis based on SubSETs (ASSET), pairwise Multi-Trait Analysis of Genome-wide association summary statistics (MTAG), pleiotropy mapping and Mendelian randomization (MR) to identify shared loci and prioritise candidate causal genes. Results: LD score regression identified significant positive genetic correlations between CeAD-SCAD (rg = 0.64), IA-AAD (rg = 0.33), IA-SCAD (rg = 0.37), CeAD-AAD (rg = 0.56) and SCAD-AAD (rg = 0.20). ASSET identified 37 shared independent loci, and in MTAG analyses, one novel locus was identified for CeAD and SCAD (SLC39A8) and one for IA (FGF5). 13 loci showed strong cross-trait colocalization, including PHACTR1, LRP1, and CDKN2B-AS1. Using the Genotype-Phenotype Map, we found that arteriopathy-associated variants colocalized with blood pressure- and migraine-related traits, while many showed effect directions opposite to those observed for coronary artery disease. Proteome-wide MR identified 67 circulating proteins associated with at least one trait, including ECM1 and SHISA5 for CeAD and FGF5 for IA, with 17 supported by colocalization. Transcriptome-wide MR identified 204 colocalized tissue?specific signals, of which, 14 were shared across multiple traits. Enrichment analyses implicated pathways related to vascular development, smooth muscle cell function, extracellular matrix organization, and TGF-? signaling. Conclusions: These findings support shared genetic architecture across anatomically distinct arteriopathies, implicating pathways involved in vascular structure and prioritising therapeutic targets for future mechanistic investigation.

11.
bioRxiv (Bioinfo) 2026-06-11

OMIO: A policy-driven Python library for reproducible microscopy image I/O

Modern fluorescence and multiphoton microscopy workflows operate within a heterogeneous ecosystem of file formats, partially overlapping metadata standards, and reader-specific conventions. In practice, this frequently leads to silent axis misinterpretations, loss or corruption of physical voxel size information, and laboratory-specific glue code that is fragile, poorly documented, and difficult to reproduce. OMIO, short for Open Microscopy Image I/O, addresses these issues by providing a lightweight, policy-driven image I/O layer for Python that enforces a canonical, OME-compatible data representation at the API boundary. The central contribution of OMIO is the explicit separation of low-level format access from semantic normalization. Existing reader libraries are used as interchangeable backends for extracting pixel data and available metadata, while OMIO enforces axis conventions, metadata interpretation, and fallback decisions in a centralized and auditable policy layer. This design allows heterogeneous microscopy inputs to be converted into a stable representation without propagating backend-specific assumptions into downstream analysis code. The core design principles of OMIO include canonical axis semantics (TZCYX), robust metadata normalization with explicit and auditable fallbacks, memory-aware operation via optional Zarr-based backends, and workflow-level semantics that extend beyond individual files to folder stacks and BIDS-like project structures. This architecture allows OMIO to orchestrate existing reader libraries into a coherent and reproducible I/O pipeline without replacing or duplicating their functionality. OMIO is implemented as an open-source and community-oriented system in which support for additional file formats and metadata conventions can be added incrementally through modular reader backends. By encouraging the contribution of example datasets, backend extensions, and feature requests, OMIO is designed to evolve alongside emerging acquisition systems while preserving strict semantic guarantees at the interface level. The resulting standardized OME-TIFF outputs are immediately suitable for downstream quantitative analysis and interactive inspection in scientific Python workflows, including workflows based on ImageJ and Napari.

12.
arXiv (CS.AI) 2026-06-12

The Challenges of Balancing AI Compliance and Technological Innovations in Critical Sectors: A Systematic Literature Review

arXiv:2606.12423v1 Announce Type: cross Abstract: The rapid integration of artificial intelligence (AI) into critical infrastructure including healthcare, finance, energy, and defense, offers transformative benefits but also conflicts with evolving regulatory and governance frameworks. This paper presents a systematic literature review (SLR) to examine the challenges of balancing AI compliance and technological innovation across critical infrastructure sectors. The review follows established SLR guidelines to extract and synthesize insights from peer-reviewed articles, report, and institutional sources published between 2020-2025. The study identifies three interrelated challenges: fragmented regulations, excessive compliance burdens for smaller to medium enterprises (SMEs), and misaligned governance models. To address these challenges, the study highlights practical governance strategies, including risk-tiered regulation, compliance by design, and explainable AI, to support scalable and trustworthy AI deployment in critical sectors. Key contributions include a concise mapping of core AI-governance challenges and a conceptual diagram illustrating their overlap, as well as actionable strategies for policymakers and practitioner to harmonize oversight with innovation.

13.
arXiv (CS.LG) 2026-06-11

UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning

arXiv:2606.12372v1 Announce Type: cross Abstract: Human-in-the-loop reinforcement learning (HiL-RL) has emerged as an effective paradigm for real-world robotic manipulation, enabling online policy improvement with human guidance. However, current HiL-RL frameworks remain intervention-intensive, relying on frequent human corrections to redirect the policy out of unproductive exploration, which incurs high labor cost and limits real-world scalability. To address this, we propose UniIntervene, an agentic intervention model that detects unproductive exploration and autonomously recovers the policy toward high-value states, taking over the bulk of interventions from human operators. Specifically, UniIntervene first performs future-conditioned action-value estimation, predicting the latent consequence of the current action and evaluating its induced value, which provides a more stable progress signal. Building on this, a temporal value-risk critic aggregates recent value dynamics and triggers intervention when the estimated value exhibits sustained stagnation or degradation. When intervention is required, UniIntervene retrieves a high-value recovery target from a memory of past intervention episodes and produces executable corrective actions through a goal-conditioned recovery policy. In this way, UniIntervene turns intervention from passive human correction into a value-aware recovery process for efficient real-world RL. Extensive experiments on diverse real-world manipulation tasks demonstrate that UniIntervene improves the average success rate by 8.6% while reducing human interventions by 57% relative to state-of-the-art HiL-RL baselines.

14.
arXiv (CS.CL) 2026-06-11

Beyond Compaction: Structured Context Eviction for Long-Horizon Agents

We present Context Window Lifecycle (CWL), a context-management scheme that gives long-horizon LLM agents an effectively unbounded working horizon. As a session accumulates history, CWL keeps the context within budget through graduated, semantically-aware eviction: the agent annotates its trajectory as typed, dependency-linked episodes as work proceeds, and a deterministic, LLM-free policy evicts content in priority order within that structure when a token budget is exceeded. CWL preserves user turns and the exploratory context the agent is actively reasoning over, while aggressively shedding action episodes whose effects are already persisted in the environment, keeping active context near a stable ceiling that also avoids the performance degradation associated with very large prompts. Compared to summarization-based compaction, CWL avoids four well-known limitations: unpredictable lossiness, destruction of causal structure, blocking model cost, and compression-induced hallucination. Compared to recency truncation, CWL is semantically aware: it drops the oldest-and-most-recoverable content according to the dependency graph rather than oldest-in-time regardless of relevance. We describe the annotation protocol, the episode graph, the eviction policy, and the token-accounting loop, and evaluate CWL on long-horizon agentic benchmarks: a single agent session completing 89 sequential tasks across 80 million tokens with no measurable degradation in task accuracy relative to per-task isolated sessions

15.
arXiv (CS.AI) 2026-06-17

LineageMark: Multi-user White-box Watermarking for Contribution Tracing in Model Derivation Chains

arXiv:2606.17123v1 Announce Type: cross Abstract: In open large language model (LLM) ecosystems, models are frequently adapted across multiple domains and applications, forming multi-stage derivation chains. Consequently, tracking and verifying historical contributions is essential for model provenance and intellectual property protection. However, existing watermarking methods are mainly designed for single-user, one-time embeddings, often fail under repeated model derivation and incremental updates. To address this problem, we propose LineageMark, a multi-user white-box watermarking framework for model derivation chains. The framework encodes watermarks in model parameters using a projection-based approach. Stable carriers are first selected to reduce sensitivity to model changes, each watermark bit is then represented as a projection statistic over these carriers. Additional watermark insertions introduce only bounded perturbations in the projection space, and margin constraints are used to maintain signal integrity. We evaluate the effectiveness of LineageMark in multi-stage model derivation chains. Experimental results show that LineageMark preserves contributor watermarks across multi-stage derivation and supports incremental multi-user watermark insertion. Furthermore, it exhibits robustness against perturbations such as re-watermarking, fine-tuning, quantization, and pruning.

16.
arXiv (CS.LG) 2026-06-17

Generalization Guarantees for Multi-Input Neural Operator Learning in Sobolev Spaces

arXiv:2606.17419v1 Announce Type: new Abstract: We develop approximation and generalization error estimates for multi-input neural operators, with the output error measured in Sobolev norms. In contrast to standard operator-learning settings with a single input function, our framework allows multiple input functions defined on possibly different domains, with different dimensions and Sobolev regularities. The derived rates explicitly quantify the contribution of each input space to the final error bound. In particular, in the balanced regime, the approximation and generalization rates are governed by the interaction between the input dimensions, regularities, and Sobolev orders, while the dependence on the model complexity retains a \(\log\log/\log\)-type structure. Our analysis provides a general theoretical framework for multi-input operator learning, including Sobolev training, and is applicable to operator learning problems arising from partial differential equations and scientific computing.

17.
Nature (Science) 2026-06-17

Revealing competitive interfacial reactions in high-energy Li–S batteries

作者:

Charge transfer at solid–liquid interfaces plays a critical role in various energy-storage systems1, particularly under dynamically varying reactant concentrations. Deciphering these intricate reaction pathways remains a substantial challenge, notably in lithium–sulfur (Li–S) batteries, in which achieving high energy density requires efficient conversion of highly concentrated lithium polysulfides (LiPSs)2,3. However, the mechanisms governing lithium sulfide (Li2S) deposition and dissolution under lean electrolyte conditions remain poorly understood. Here, using in situ liquid-cell electron microscopy, we directly visualize concentration-driven phase segregation at the electrode–electrolyte interface. Within these high-concentration interfacial layers (HCILs), competitive surface and solution dictate the charge-transfer dynamics and ultimately govern Li2S deposition at different phase boundaries. Density functional theory (DFT) calculations reveal that the aggregation of LiPSs alters molecular geometry, electronic properties and orbital hybridization, collectively facilitating charge transfer through highly concentrated LiPSs clusters. Guided by these insights, we design optimized electrodes that balance interfacial reaction pathways, enabling fast charging (4 C, 26.8 mA cm−2) and achieving high energy densities exceeding 400 Wh kg−1. These findings provide mechanistic understanding of interfacial reactions under practical working conditions and offer a design strategy to advance Li–S batteries. Visualization of concentration-driven phase segregation within high-concentration interfacial layers in the context of high-energy lithium–sulfur batteries using liquid-cell electrochemical transmission electron microscopy reveals competitive interfacial reactions under lean electrolyte conditions at different phase boundaries.

18.
arXiv (CS.AI) 2026-06-15

Position: Align AI to Our Aspirations, Not Our Flaws

arXiv:2606.13755v1 Announce Type: cross Abstract: We argue that aligning AI to aggregated human preferences is the wrong target. With current technology, one can train AIs to share the values of a Silicon Valley techno-optimist, a degrowth environmentalist, a national-conservative culture warrior, a single-party state cadre, or a devout religious traditionalist. We should not. Human values produce societies that thrive or fail on the merits of those values - from failed states and extreme inequality to declining happiness, political polarization, and government dysfunction in the world's wealthiest democracies. The pluralistic-alignment program correctly diagnoses that there is no single "humanity" to align with, but is dangerous if taken as the main directive. We argue that AI should be trained to a non-negotiable floor of objective alignment goals - competence, bounded by the constraints of factual accuracy, honesty, and lawfulness and that pluralism belongs at the surface (language, register, conventions, missing-context defaults) and across the wide band of legitimate value tradeoffs that respect the floor, but not at the level of values that violate it. We highlight the empirical reality of unfiltered pluralistic values, propose four commitments as a constructive alternative, and engage six credible objections: commercial pressure and practical feasibility, democratic legitimacy, regulatory compliance, over-reliance on institutionalist explanations, the charge that the floor itself is culturally laden, and the limits of Coherent Extrapolated Volition.

19.
arXiv (CS.CL) 2026-06-19

Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias

LLM-as-a-Judge has become the dominant evaluation paradigm for language models, but judge validation in practice relies on exact-match agreement, a metric that does not correct for chance and systematically overstates discriminative ability. We present the largest systematic evaluation of LLM-as-a-Judge to date: 21 judges from nine providers across MT-Bench, JudgeBench, and RewardBench, evaluated under three protocols (agreement, consistency, bias audit) over 118 runs and approximately 541,000 individual judgments. Four findings emerge, consistent across the full cohort, including the April 2026 frontier: kappa deflation between exact match and Cohen's kappa is universal (33–41 pp on MT-Bench), judge rankings shift by up to 14 positions across benchmarks, high test–retest reliability (>0.95) coexists with severe position bias (>0.10) in two production-deployed judges (instantiating a consistency–bias paradox), and verbosity bias is small (

20.
arXiv (CS.CL) 2026-06-11

WorldReasoner: Evaluating Whether Language Model Agents Forecast Events with Valid Reasoning

Forecasting real-world events requires language-model agents to reason under uncertainty from incomplete, time-bounded information. Yet evaluating whether agents genuinely forecast requires more than final-answer accuracy: a model may be correct by recalling memorized training facts, citing fabricated evidence, or producing an unsupported causal story. We present WorldReasoner, an evaluation framework for temporally valid event forecasting. Each task gives an agent a resolved forecasting question, a simulated forecast date, and access only to evidence available before that date; after resolution, the framework scores the submitted probability, cited evidence, and optional causal event graph. WorldReasoner reports three complementary axes: outcome quality against resolved answers, evidence quality over cited sources, and reasoning quality against post-resolution hindsight graphs. The benchmark is built by an agentic construction pipeline that generates forecasting questions, collects time-stamped evidence, and builds hindsight reference graphs at scale, yielding 345 resolved tasks derived from 14,141 articles with graphs covering 8,087 extracted events. Across six controlled agent settings, temporally valid retrieval is the strongest driver of outcome accuracy; causal graph construction improves key-event recovery; and correct graph-enabled forecasts are more strongly grounded in key events and relevant sources, yet agents still struggle to convert grounded evidence into calibrated probabilities.

21.
arXiv (CS.LG) 2026-06-16

Model Stealing Through the Lens of Model Multiplicity

arXiv:2606.15493v1 Announce Type: new Abstract: Model stealing attacks, where adversaries create high-fidelity surrogate models, are a significant threat to the intellectual property of machine learning services. Conventional wisdom suggests these surrogates could provide adversaries with economic leverage comparable to the original service providers. This paper challenges this assumption by evaluating model stealing attacks beyond mere fidelity to the target model. Because query-based extraction provides only partial supervision of the target's input-output behavior, the surrogate is not uniquely identified: many near-optimal surrogates can achieve comparable fidelity while differing in deployment-relevant properties. Instead of performing a classic learning-based model stealing attack, we compute the Rashomon Set (i.e., the set of almost-equally-accurate models) of surrogate models, and evaluate its diversity using multiplicity metrics (ambiguity, discrepancy, and Rashomon Capacity) and group fairness metrics. Across tabular, medical imaging, and NLP tasks, our experiments on real-world datasets reveal that despite exhibiting similar fidelity to the target model, surrogate models can display significant variances in other critical performance metrics. These findings cast doubt on the presumed equivalence between high-fidelity surrogates and the target model in practical deployment scenarios.

22.
arXiv (CS.CL) 2026-06-11

Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models

Large language models (LLMs) are widely used to tackle complex tasks with autonomous workflows. Recently, reusable natural language skills have emerged as a popular paradigm to inject procedural knowledge into LLM applications. Since popular skills are often invoked repeatedly, placing their full text in every context significantly increases prefill cost and latency. While text compression techniques have the potential to solve this problem, most existing methods are designed to compress factual knowledge in documents instead of procedural knowledge, making them insufficient for skill compression. In this paper, we argue that an effective skill compression method should: 1) preserve logical dependencies among workflows and tool protocols, 2) enable lightweight, offline compression for frequently updated community skills, and 3) be adaptable to varying complexities across skills. To address this, we present SKIM (SKIll coMpression), an adaptive multi-resolution soft token compression framework for procedural skills. Depending on the complexity of each skill, SKIM creates different numbers of soft tokens that not only improve the efficiency of LLM inference, but also preserve the effectiveness of skill usage. Experiments indicate that SKIM compresses skills to 30 to 60 percent of their original token length while preserving task performance better than existing compression methods.We have released our code at https://github.com/bebr2/SKIM .

23.
arXiv (CS.AI) 2026-06-19

Techniques for Peak Memory Reduction for LoRA Fine-tuning of LLMs on Edge Devices

arXiv:2606.19528v1 Announce Type: cross Abstract: Fine-tuning of Large Language Models (LLMs) using Low-Rank Adaptation (LoRA) on an end-user's data offers personalized experiences while keeping data private, but faces severe memory constraints on consumer hardware. Peak memory during fine-tuning often exceeds device limits, especially for models with billions of parameters and long-context training data. This paper introduces a suite of complementary techniques to reduce memory footprint without sacrificing model quality: (1) base model quantization with on-the-fly dequantization, (2) memory-efficient checkpointing combining selective activation caching and disk offloading, (3) softmax approximation using semantically relevant token subsets, and (4) logits masking. Experiments on Llama-3.2 3B and Qwen-2.5 3B demonstrate up to $26\times$ and $28\times$ reduction in peak memory, enabling fine-tuning on resource-constrained devices.

24.
arXiv (CS.CL) 2026-06-12

Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models

Chain-of-thought (CoT) reasoning is the dominant paradigm for inference-time scaling in language models, yet the causal influence of individual steps on the final answer poorly understood. We estimate each step's causal importance via early exit and use this measure to study how answers form across the reasoning traces of several model families. Across diverse tasks, we find that reasoning typically crosses a commitment boundary – a sharp transition from transient intermediate guesses to a stable, high-confidence answer. This transition often happens in a single step, well before the model's reasoning block ends, and is followed by epiphenomenal CoT steps that leave the final answer probability unaltered. Using attention probes, we show that answer-formation stages can be linearly decoded from intermediate reasoning steps with high accuracy and generalize robustly to unseen reasoning tasks. We exploit this signal to early-exit reasoning blocks at the commitment boundary, reducing the length of CoTs up to 55\% on average with negligible impact on model performance.

25.
arXiv (CS.CL) 2026-06-19

Pitch Spelling Jazz Lead Sheets, Solo Transcriptions, Classical Piano and Monophonic Scores

We present an algorithm for pitch spelling and key estimation. Given an input in MIDI-like format, containing information on note pitches (expressed in semitones relative to the lowest reference note) and bar boundaries, it estimates the appropriate note names, a global Key Signature, and a local scale for each bar. This related information elements are evaluated jointly during two stages of optimisation. During an initial 'modal' stage, a probable scale is proposed for each bar, minimising the number of accidentals to be printed in the printed score with a shortest-path search. Then, during a second stage called 'tonal', these local scales are used to estimate the Key Signature and note names that would result in the best musical notation for the entire piece. We present evaluations conducted on datasets comprising a variety of digital musical scores: jazz lead sheets taken from the Real Book, transcriptions of recordings of jazz soli and bass lines, traditional tunes, as well as classical scores for piano and monophonic instruments. Our procedure was originally designed for use in music transcription, specifically for building digital collections of jazz solos transcribed from audio recordings, for the purposes of music analysis, teaching and the preservation of cultural heritage. This method should also prove useful for other tasks related to the processing of musical notation. Furthermore, to this end, we have defined new distances between various common jazz scales, which may be of some interest to musicological studies.