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。

01.
medRxiv (Medicine) 2026-06-15

The clinical utility of functional testing in fibroblasts to diagnose primary mitochondrial disease

Genome sequencing of the heterogeneous primary mitochondrial disorders (PMD) frequently reveals variants of uncertain significance that require functional tests for diagnosis, and does not identify variants in all patients. We analyzed mitochondrial enzyme assays, blue native polyacrylamide gel electrophoresis (BN-PAGE) with in-gel activity staining, complex I assembly blot, and select protein abundances in fibroblasts of a case series of 204 PMD patients divided into functional classes, in comparison to 51 controls and 53 differential diagnostic conditions. Overall, sensitivity and specificity for respiratory chain enzyme assays were 46% and 93% respectively, for BN-PAGE 40% and 98%, for complex I assembly assay 49% and 99%. The overall sensitivity of all tests was 76%, specificity 93%, with positive predictive value 96% and negative predictive value 67%. Categories with high sensitivity were isolated complex deficiencies, nuclear DNA-encoded mitochondrial protein synthesis defects, co-factor defects, and mitochondrial amino-acyl-tRNA synthetase conditions when aided by protein abundance. Mitochondrial DNA mutations and maintenance disorders showed poor sensitivities. Secondary dysfunctions were rare. A complete battery of functional tests showed strong diagnostic clinical utility in fibroblasts.

02.
arXiv (CS.CV) 2026-06-16

V2P-Manip: Learning Dexterous Manipulation from Monocular Human Videos

Achieving autonomous robotic dexterous manipulation requires precise, human-like action sequences at scale. As a scalable supplement to costly teleoperation data, extracting trajectories with both visual fidelity and physical plausibility from monocular videos represents a promising frontier in embodied AI. To this end, we introduce V2P-Manip, an efficient framework designed to learn dexterous manipulation policies directly from human demonstration videos. We establish an efficient, integrated pipeline encompassing 3D asset acquisition, trajectory estimation, and dexterous policy learning. To bridge the gap between visual perception and physical constraints, we introduce a two-stage refinement process to enforce spatial alignment and physical consistency. Evaluations on the TACO and OakInk benchmarks demonstrate that our approach significantly outperforms previous methods in pose accuracy, adaptability to unstructured environments, and training efficiency. Ultimately, experimental results confirm an average success rate of over 75% across multiple synthetic manipulation tasks and validate the adaptability of the extracted manipulation priors across diverse dexterous hand embodiments.

03.
arXiv (CS.AI) 2026-06-24

Weight-Space Geometry of Offline Reasoning Training

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

04.
arXiv (quant-ph) 2026-06-16

Conditions for Unitarity in Timeless Quantum Theory

arXiv:2504.01579v3 Announce Type: replace Abstract: Quantum timeless approaches solve the problem of time by recovering the usual unitary evolution of quantum theory relative to a clock in a stationary quantum Universe. For some Hamiltonians of the Universe, such as those including an interaction term with the clock, the dynamics is substantially altered and can be non-unitary. This work derives necessary and sufficient conditions for the relative dynamics to be unitary and finds the general form of the unitary evolution operator. A physical interpretation of these conditions is given in terms of the clock's rate. Unitary dynamics is associated with rates that are constant in time and independent of the clock's internal structure.

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

Ellipse Meets Bit-Planes: A Novel Approach to RNFL based Glaucoma Detection Using Advanced Image Processing and Deep Learning

This work proposes an integrated pipeline for automatic glaucoma detection method from easily available colour fundas images based on an adaptive algorithm for ellipse-based polar transformation, to enhance the analysis of the Retinal Nerve Fiber Layer (RNFL) as the primary biomarker for observing glaucomatous changes, regardless of optic disc and macula position. Utilizing this transformation, we introduce two distinct frameworks tailored to different operational needs. The first framework, a deep learning-inspired feature fusion approach, achieves a 99.3% detection rate, ideal for settings where high precision is essential, despite higher computational demands. The second framework employs a novel image-processing algorithm based on bit-plane slicing, offering 92.31% accuracy and optimized for environments requiring rapid inference with minimal resource consumption. Both frameworks provide scalable and cost-effective solutions for early glaucoma detection. This study highlights the potential of RNFL-based diagnostic tools in addressing the global challenge of glaucoma, particularly in underserved regions.

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

DiskChunGS: Large-Scale 3D Gaussian SLAM Through Chunk-Based Memory Management

Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated impressive results for novel view synthesis with real-time rendering capabilities. However, integrating 3DGS with SLAM systems faces a fundamental scalability limitation: methods are constrained by GPU memory capacity, restricting reconstruction to small-scale environments. We present DiskChunGS, a scalable 3DGS SLAM system that overcomes this bottleneck through an out-of-core approach that partitions scenes into spatial chunks and maintains only active regions in GPU memory while storing inactive areas on disk. Our architecture integrates seamlessly with existing SLAM frameworks for pose estimation and loop closure, enabling globally consistent reconstruction at scale. We validate DiskChunGS on indoor scenes (Replica, TUM-RGBD), urban driving scenarios (KITTI), and resource-constrained Nvidia Jetson platforms. Our method uniquely completes all 11 KITTI sequences without memory failures while achieving superior visual quality, demonstrating that algorithmic innovation can overcome the memory constraints that have limited previous 3DGS SLAM methods.

07.
arXiv (quant-ph) 2026-06-16

Witnessing Spin-Orbital Entanglement using Resonant Inelastic X-Ray Scattering

arXiv:2512.06718v2 Announce Type: replace Abstract: Entanglement plays a central role in quantum technologies, yet its characterization and control in materials remain challenging. Recent developments in spectrum-based entanglement witnesses have enabled new strategies for quantifying many-body entanglement in macroscopic materials. Here, we develop a protocol for detecting spin-orbital entanglement using experiment-accessible resonant inelastic x-ray scattering (RIXS). Central to our approach is the construction of a Hermitian generator from experimentally measurable spectra, which allows us to compute the quantum Fisher information (QFI) available in spin–orbital systems. The resulting QFI provides upper bounds for $k$-producible states and thus serves as a robust witness of spin-orbital entanglement. To account for realistic experimental limitations, we further extend our framework to include relaxed QFI bounds applicable to measurements lacking full polarization resolution.

08.
arXiv (CS.LG) 2026-06-19

Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving

作者:

arXiv:2606.20537v1 Announce Type: new Abstract: Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches. This is highly effective for high-throughput, high-concurrency serving, but it manages only one positional fragment of execution state: the KV cache. We study the opposite regime: low-latency, small-batch, on-device physical-AI serving, where interactive LLM agents, speech systems, and robot policies repeatedly branch, reset, interrupt, and re-enter under tight responsiveness budgets. We introduce execution-state capsules, a graph-bound checkpoint and restore mechanism for the complete restorable state at a committed boundary. FlashRT is a white-box, backend-facing kernel runtime whose evaluated NVIDIA CUDA backend runs captured graph plans over contiguous static buffers with no block-table indirection. Because the live state is a closed set of named buffers, a capsule can snapshot, restore, fork, or roll back the whole execution boundary, including KV, recurrent state, convolution state, MTP state, and metadata. This moves reuse from token-addressed KV fragments to graph-bound execution-state boundaries. On an RTX 5090, capsule restore is byte-exact at the stored-state level and token-identical under greedy decode. A KV-only ablation diverges, showing that recurrent state is load-bearing. GPU-resident snapshot and restore are sub-millisecond, and TTFT speedup over cold prefill grows from 3.9x at 2k tokens to 27x at 16k tokens. On Jetson AGX Thor and DGX Spark, the same correctness and structural properties hold. Capsules are not a replacement for high-throughput KV-cache serving; they define a complementary latency-first serving point for explicit execution-state reuse.

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

Can LLMs Accurately Score Medical Diagnoses and Clinical Reasoning?

arXiv:2604.14892v3 Announce Type: replace-cross Abstract: Evaluating medical AI systems using expert clinician panels is costly and slow, motivating the use of large language models (LLMs) as alternative adjudicators. Here, we evaluate an LLM Jury, composed of three frontier AI models, for scoring 3334 diagnoses on 300 real-world low- and middle-income country (LMIC) hospital cases. Both LLM- and clinician-generated diagnoses are scored against expert panel diagnoses across four dimensions: diagnosis, differential diagnosis, clinical reasoning, and negative treatment risk. The LLM Jury scores are compared with expert and independent re-scoring panel scores to assess error metrics, inter-rater agreement, severe-risk errors, and the effect of post hoc calibration using isotonic regression. In our data, we find that: (i) the uncalibrated LLM Jury scores preserve ordinal agreement with the expert clinician panel scores, but are systematically lower; (ii) the probability of severe-risk errors is lower for the LLM Jury than the human expert re-score panels; (iii) the LLM Jury combined with LLM diagnoses can be used to identify diagnoses at high risk of error, enabling targeted expert review and improved panel efficiency; (iv) the calibrated LLM Jury scores and rankings of diagnosing agents show excellent agreement with those of the primary expert panels; (v) LLM Jury models show no self-preference bias, they did not score diagnoses generated by their own underlying model or models from the same vendor more (or less) favourably than those generated by other models. Together, these results provide evidence that a calibrated LLM Jury is a trustworthy and reliable proxy for expert clinician evaluation in medical AI benchmarking. Confirming these findings in other clinical settings is an important direction for future work.

10.
arXiv (CS.CV) 2026-06-15

HumP-KD: A Hybrid Uncertainty-Aware Multi-Stage Progressive Knowledge Distillation Framework for Efficient Fire Classification

Real-time fire classification systems require models that are simultaneously accurate, computationally efficient, and deployable on resource-constrained hardware. This work proposes HumP-KD, a Hybrid Uncertainty-aware Multi-stage Progressive Knowledge Distillation framework for efficient fire classification. Two datasets, FlameVision and Dataset-II, containing 8,600 and 31,309 images, are used. Various CNN and transformer baselines are applied under standard preprocessing, online augmentation, Gaussian noise and motion blur robustness conditions. The proposed HumP-KD model distills knowledge from two frozen heterogeneous transformer teachers, Swin-Tiny and ViT-Base, along with their Meta-MLP ensemble, into a lightweight MobileViT-S student via three tightly integrated components. Hierarchical Progressive Knowledge Distillation employs a Hierarchical Feature Builder. It generates a fused spatial attention mask to guide distillation toward discriminative regions selectively. Multi-Stage Knowledge Distillation progressively activates three distillation stages across training. On Dataset-II, HumP-KD achieves a mean F1 score of $0.9876 \pm 0.0063$ across 10 independent trials, significantly outperforming the MobileViT-S baseline trained without distillation ($0.9537 \pm 0.0351$), with statistical significance confirmed by both independent t-test ($p = 0.0195$) and Wilcoxon signed-rank test ($W = 1$, $p = 0.0039$). The proposed method also demonstrates strong generalization across datasets and robustness under degraded visual conditions. The student model retains only 4.94M parameters and 19.01Mb model size, representing a $5.7\times$ parameter reduction over Swin-Tiny and a $17.5\times$ reduction over ViT-Base, while achieving 37.72 CPU FPS, making it suitable for real-time deployment.

11.
arXiv (CS.CV) 2026-06-12

Triangle Splatting SLAM

We present a dense RGB-D SLAM system using differentiable triangles as the 3D map representation. While 3D Gaussian Splatting has emerged as the leading method for novel-view synthesis, triangles remain the standard primitive for traditional rendering hardware, game engines, and downstream tasks requiring explicit geometry such as simulation, collision, and editing. Recent offline methods have demonstrated that an unstructured 'triangle soup' can be optimised into a photorealistic mesh via Delaunay triangulation across a set of posed images. Building upon this insight, we present the first dense SLAM system to employ Triangle Splatting to perform both tracking and mapping through online differentiable rendering of a triangle soup. The map can be converted into a connected mesh on-the-fly via restricted Delaunay triangulation, enabling new online capabilities such as mesh deformation and collision checking. On Replica and TUM-RGBD, our system outperforms baselines on 3D geometry, matches the camera-tracking accuracy, and enables online mesh-based scene editing.

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

Authority, Truth, and Citation Bias: A Large-Scale Multi-Domain Benchmark for Studying Epistemic Susceptibility in Large Language Models

arXiv:2606.13104v1 Announce Type: new Abstract: Large language models are increasingly deployed in citation-augmented settings, yet the effect of citation presence on model behavior independent of factual content remains poorly understood. We introduce AuthorityBench, a 220,564-prompt multi-domain benchmark that isolates how citation-based authority signals influence epistemic behavior in LLMs. The benchmark uses a fully balanced 2x2 factorial design crossing claim veracity with citation veracity, the first to do so, across four domains (general knowledge, science, law, and medicine), with controlled variation over 40 prompt templates, four venue prestige tiers, and a country-coded author name dataset. Evaluating seven models on 12 structured research questions, we find that citation presence, whether real or fabricated, consistently increases hallucination rates relative to a no-citation baseline. The effect is strongest when fabricated citations accompany true claims, raising hallucination rates by 3 to 22 percentage points and reaching 35 to 77% in the general knowledge domain, while legal claims are comparatively robust and venue prestige and author demographics show negligible impact. All datasets and evaluation code are available at: https://github.com/floating-reeds/AuthorityBench

13.
arXiv (math.PR) 2026-06-24

Genealogical processes of sequential Monte Carlo methods and other non-neutral population models under rapid mutation

arXiv:2406.16465v3 Announce Type: replace Abstract: We show that genealogical trees arising from a broad class of non-neutral models of population evolution converge to the Kingman coalescent under a suitable rescaling of time. As well as non-neutral biological evolution, our results apply to genetic algorithms encompassing the prominent class of sequential Monte Carlo (SMC) methods. The time rescaling we need differs slightly from that used in classical results for convergence to the Kingman coalescent, which has implications for the performance of different resampling schemes in SMC algorithms. In addition, our work substantially simplifies earlier proofs of convergence to the Kingman coalescent, and corrects an error common to several earlier results.

14.
arXiv (CS.CL) 2026-06-24

ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement

Despite the remarkable performance of large language models (LLMs) in text-to-SQL (SQL generation), correctly producing SQL queries remains challenging during initial generation. The SQL refinement task is subsequently introduced to correct syntactic and semantic errors in generated SQL queries. However, existing paradigms face two major limitations: (i) self-debugging becomes increasingly ineffective as modern LLMs rarely produce explicit execution errors that can trigger debugging signals; (ii) self-correction exhibits low detection precision due to the lack of explicit error modeling grounded in the question and schema, and suffers from severe hallucination that frequently corrupts correct SQLs. In this paper, we propose ErrorLLM, a framework that explicitly models text-to-SQL Errors within a dedicated LLM for text-to-SQL refinement. Specifically, we represent the user question and database schema as structural features, employ static detection to identify execution failures and surface mismatches, and extend ErrorLLM's semantic space with dedicated error tokens that capture categorized implicit semantic error types. Through a well-designed training strategy, we explicitly model these errors with structural representations, enabling the LLM to detect complex implicit errors by predicting dedicated error tokens. Guided by the detected errors, we perform error-guided refinement on the SQL structure by prompting LLMs. Extensive experiments demonstrate that ErrorLLM achieves the most significant improvements over backbone initial generation. Further analysis reveals that detection quality directly determines refinement effectiveness, and ErrorLLM addresses both sides by high detection F1 score while maintain refinement effectiveness.

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

COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers

arXiv:2512.02318v4 Announce Type: replace-cross Abstract: This paper studies how multimodal large language models (MLLMs) undermine the security guarantees of visual CAPTCHA. We identify the attack surface where an adversary can cheaply automate CAPTCHA solving using off-the-shelf models. We evaluate 7 representative MLLMs on 18 real-world CAPTCHA task types, measuring single-shot accuracy, success under limited retries, end-to-end latency, and per-solve cost. We further validate our findings through a supplemental external dataset and an adaptive-attacker setting with session memory, while also analyzing the impact of task-specific prompt engineering and few-shot demonstrations on solver effectiveness. We reveal that MLLMs can reliably solve recognition-oriented and low-interaction CAPTCHA tasks at human-like cost and latency, whereas tasks requiring fine-grained localization, multi-step spatial reasoning, or cross-frame consistency remain significantly harder for current models. By examining the reasoning traces of such MLLMs, we investigate the underlying mechanisms of why models succeed/fail on specific CAPTCHA puzzles and use these insights to derive defense-oriented guidelines for selecting and strengthening CAPTCHA tasks. To validate these principles, we present a proof-of-concept by hardening a vulnerable CAPTCHA type using our guidelines. We demonstrate that incorporating fine-grained localization and implicit counting reduces the success rate of state-of-the-art MLLMs from over 95\% to 0\%, confirming that structural changes can effectively mitigate the threat. We conclude by emphasizing the urgent need for CAPTCHA redesign as MLLM capabilities increasingly threaten existing defenses. Code Availability (https://doi.org/10.5281/zenodo.20406852).

16.
arXiv (CS.LG) 2026-06-18

Decomposing Prediction Mechanisms for In-Context Recall

arXiv:2507.01414v2 Announce Type: replace Abstract: We introduce a new family of toy problems that combine features of linear-regression-style continuous in-context learning (ICL) with discrete associative recall. We pretrain transformer models on sample traces from this toy, specifically symbolically-labeled interleaved state observations from randomly drawn linear deterministic dynamical systems. We study if the transformer models can recall the state of a sequence previously seen in its context when prompted to do so with the corresponding in-context label. Taking a closer look at this task, it becomes clear that the model must perform two functions: (1) identify which system's state should be recalled and apply that system to its last seen state, and (2) continuing to apply the correct system to predict the subsequent states. Training dynamics reveal that the first capability emerges well into a model's training. Surprisingly, the second capability, of continuing the prediction of a resumed sequence, develops much earlier. Via out-of-distribution experiments, and a mechanistic analysis on model weights via edge pruning, we find that next-token prediction for this toy problem involves at least two separate mechanisms. One mechanism uses the discrete symbolic labels to do the associative recall required to predict the start of a resumption of a previously seen sequence. The second mechanism, which is largely agnostic to the discrete symbolic labels, performs a "Bayesian-style" prediction based on the previous token and the context. These two mechanisms have different learning dynamics. To confirm that this multi-mechanism (manifesting as separate phase transitions) phenomenon is not just an artifact of our toy setting, we used OLMo training checkpoints on an ICL translation task to see a similar phenomenon: a decisive gap in the emergence of first-task-token performance vs second-task-token performance.

17.
arXiv (CS.CL) 2026-06-11

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning

Fine-tuning large language models (LLMs) achieves strong performance but is often limited by the memory overhead of backpropagation. Zeroth-order (ZO) optimization avoids this overhead by estimating gradients through forward passes alone, yet it typically converges slowly because random Gaussian perturbations yield high-variance gradient estimates in high-dimensional parameter spaces. In this paper, we propose a plug-and-play framework that turns random perturbations into more effective descent directions. The key idea is to draw a small pool of candidate perturbations, evaluate their loss values, and then select or combine those that are best aligned with the optimization objective. We develop two instantiations of this idea: MeZO-GV, which forms a guiding vector from the contrast between low-loss and high-loss perturbation groups, and MeZO-Greedy, which keeps the single best perturbation within a fixed evaluation budget. We theoretically show that both strategies yield a larger per-step reduction in the objective than standard ZO estimation, leading to improved convergence rates. Experiments on LLMs of different scales and architectures confirm that the proposed methods integrate naturally with existing ZO optimizers and consistently improve convergence speed and task accuracy. On OPT-13B, our approach outperforms all ZO baselines across 11 benchmarks and exceeds gradient-based methods on 9 of them, while retaining the memory efficiency of forward-only optimization.

18.
arXiv (CS.CV) 2026-06-19

OncoReg: Medical Image Registration for Oncological Challenges

In modern cancer research, the vast volume of medical data generated is often underutilised due to challenges related to patient privacy. The OncoReg Challenge addresses this issue by enabling researchers to develop and validate image registration methods through a two-phase framework that ensures patient privacy while fostering the development of more generalisable AI models. Phase one involves working with a publicly available dataset, while phase two focuses on training models on a private dataset within secure hospital networks. OncoReg builds upon the foundation established by the Learn2Reg Challenge by incorporating the registration of interventional cone-beam computed tomography with standard planning fan-beam CT images in radiotherapy. Accurate image registration is crucial in oncology, particularly for dynamic treatment adjustments in image-guided radiotherapy, where precise alignment is necessary to minimise radiation exposure to healthy tissues while effectively targeting tumours. This work details the methodology and data behind the OncoReg Challenge and provides a comprehensive analysis of the competition entries and results. Findings reveal that feature extraction plays a pivotal role in this registration task. A new method emerging from this challenge demonstrated its versatility, while established approaches continue to perform comparably to newer techniques. Both deep learning and classical approaches still play significant roles in image registration, with the combination of methods, particularly in feature extraction, proving most effective.

19.
arXiv (CS.AI) 2026-06-11

Can Open-Source LLM Agents Replace Static Application Security Testing Tools? An Empirical Assessment

arXiv:2606.11672v1 Announce Type: cross Abstract: This paper explores the value of agentic AI tools for cybersecurity purposes. We evaluate the efficacy of a general-purpose GenAI Large Language Model- (GenAI-) based agent when powered by three different Ollama-hosted general-purpose open source models. We assess each agent's performance using precision, recall, false positive count, and a calculated composite score based upon the interplay of the captured metrics, against the baseline performance of an existing, vetted Static Application Security Testing (SAST) tool, Bandit. Our findings refute the notion that a modern open-source GenAI LLM-based agent is currently suitable for the specialized task of SAST scanning under realistic conditions.

20.
arXiv (CS.AI) 2026-06-16

PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums

arXiv:2606.16175v1 Announce Type: new Abstract: Longitudinal personal albums are weak-schema multimodal databases: noisy perceptual records whose key facts require joins across faces, text, timestamps, locations, and repeated events. Existing visual, video, document, and lifelog benchmarks test sub-problems, but not album-scale profile reconstruction with social identity binding and evidence citation. Benchmarking this task is difficult because the ground truth needed for evaluation–owner profiles, social graphs, face-name maps, and evidence provenance–is private state that real albums cannot safely release. We introduce PAL-Bench, a controlled benchmark for evidence-grounded reconstruction under a public-record contract. Its Evidence Compiler builds latent private worlds, programs target-level evidence paths, renders album pixels, re-measures them through perception pipelines, and exports audited public/private views. Agents receive only perception-derived public records; targets, identifier maps, and evidence paths remain hidden. PAL-Bench contains 50 synthetic users, 36,659 public photo records, and 2,799 targets over owner facts, identities, and relations. A privacy-preserving audit with 10 participants confirms that PAL-Bench evidence structures match real private albums, though equivalent releases remain privacy-prohibitive. Across seven systems and two compute-matched diagnostics, a seven-metric protocol reveals a gap between plausible profile summarization and faithful social reconstruction: systems recover some owner facts but struggle with recurring identities and evidence citation. PAL-TRACE, a reference framework that freezes identity bindings before owner-fact mining, performs best but leaves hard identity resolution far from solved. PAL-Bench provides a testbed for perceptual entity resolution, multimodal data integration, temporal evidence aggregation, and provenance-aware structured prediction.

21.
arXiv (CS.CL) 2026-06-18

LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A Study of Item Discrimination in Reading Comprehension Assessment

Item discrimination is a fundamental psychometric property of educational assessment, which measures whether an item meaningfully distinguishes students with higher proficiency from students with lower proficiency. While various existing works have explored whether large language models (LLMs) can estimate item difficulty, it remains unclear whether they can capture item discrimination. In this work, we evaluate 42 proprietary and open-weight LLMs in zero-shot settings using two complementary approaches: direct discrimination prediction, where models explicitly estimate an item's discrimination value from its content, and response-based Classical Test Theory (CTT) calibration, where LLM answers are treated as synthetic student responses to compute discrimination scores. Our results show that direct prediction yields weak alignment with human-calibrated discrimination: the best-performing model reaches only a Spearman correlation of 0.152. Response-based CTT calibration provides a stronger but still limited signal, with the all-persona synthetic respondent pool reaching a Spearman correlation of 0.241. These findings highlight item discrimination as an open challenge for LLM-based psychometric evaluation: current LLMs contain non-random discrimination-relevant signal, but they do not yet reliably capture how assessment items distinguish human students.

22.
arXiv (CS.AI) 2026-06-19

LoRDO: Distributed Low-Rank Optimization with Infrequent Communication

arXiv:2602.04396v2 Announce Type: replace-cross Abstract: Distributed training of foundation models via $\texttt{DDP}$ is limited by interconnect bandwidth. While infrequent communication strategies reduce synchronization frequency, they remain bottlenecked by the memory and communication requirements of optimizer states. Low-rank optimizers can alleviate these constraints; however, in the local-update regime, workers lack access to the full-batch gradients required to compute low-rank projections, which degrades performance. We propose $\texttt{LoRDO}$, a principled framework unifying low-rank optimization with infrequent synchronization. We first demonstrate that, while global projections based on pseudo-gradients are theoretically superior, they permanently restrict the optimization trajectory to a low-rank subspace. To restore subspace exploration, we introduce a full-rank quasi-hyperbolic update. $\texttt{LoRDO}$ achieves near-parity with low-rank $\texttt{DDP}$ in language modeling and downstream tasks at model scales of $125$M–$720$M, while reducing communication by $\approx 10 \times$. Finally, we show that $\texttt{LoRDO}$ improves performance even more in very low-memory settings with small rank/batch size.

23.
arXiv (CS.AI) 2026-06-12

HalluJudge: A Reference-Free Hallucination Detection for Context Misalignment in Code Review Automation

arXiv:2601.19072v3 Announce Type: replace-cross Abstract: Large Language models (LLMs) have shown strong capabilities in code review automation, such as review comment generation, yet they suffer from hallucinations – where the generated review comments are ungrounded in the actual code – poses a significant challenge to the adoption of LLMs in code review workflows. To address this, we explore effective and scalable methods for a hallucination detection in LLM-generated code review comments without the reference. In this work, we design HalluJudge that aims to assess the grounding of generated review comments based on the context alignment. HalluJudge includes four key strategies ranging from direct assessment to structured multi-branch reasoning (e.g., Tree-of-Thoughts). We conduct a comprehensive evaluation of these assessment strategies across Atlassian's enterprise-scale software projects to examine the effectiveness and cost-efficiency of HalluJudge. Furthermore, we analyze the alignment between HalluJudge's judgment and developer preference of the actual LLM-generated code review comments in the real-world production. Our results show that the hallucination assessment in HalluJudge is cost-effective with an F1 score of 0.85 and an average cost of $0.009. On average, 67% of the HalluJudge assessments are aligned with the developer preference of the actual LLM-generated review comments in the online production. Our results suggest that HalluJudge can serve as a practical safeguard to reduce developers' exposure to hallucinated comments, fostering trust in AI-assisted code reviews.

24.
arXiv (CS.AI) 2026-06-19

KG-SoftMAP: Soft Knowledge-Graph Priors for Bayesian Network Structure Learning from Sparse Discrete Data

arXiv:2606.10358v2 Announce Type: replace-cross Abstract: Learning Bayesian network (BN) structure from sparse discrete data is hard: when each instance records only a few variables, most variable pairs lack the joint observations needed for reliable scoring, and data-only methods recover little structure. However, imperfect domain knowledge, expressible as a weighted directed knowledge graph (KG), is often available. We propose KG-SoftMAP, which encodes such a KG as a finite-strength, confidence-weighted edge prior and maximizes a MAP objective combining the BDeu score with a logit-form prior; the KG may be expert-curated or LLM-extracted. On synthetic benchmarks with known DAGs, KG-SoftMAP reaches Directed-F1 (DF1) $0.19$–$0.32$ at observation rate $\rho=0.05$ and DF1 $0.44$–$0.97$ at $\rho\geq0.2$, while every data-only learner tested stays near zero under the same sparse masks. Recovery tracks KG quality: controlled corruption degrades it smoothly, a zero-signal KG yields DF1 $0.00$, and a blindly LLM-extracted KG with imperfect precision and recall still drives substantial recovery. On three real sparse educational datasets, the learned BN acts as a concept-level posterior model: on SAF it matches logistic regression (LR) within $0.03$ F1_FAIL while providing an inspectable concept graph, calibrated Fail probabilities, and tractable posterior queries from partial observations.

25.
arXiv (CS.CV) 2026-06-25

SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning

Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the safety surface: risks can arise from multimodal question answering, assistant responses, and cross-modal composition, while moderation policies may vary across products, regions, and deployment stages. Most existing guardrails either rely on fixed taxonomies or target only a narrow set of interaction settings, which limits their adaptability when safety rules change at deployment time. We present SingGuard, a policy-adaptive multimodal guardrail model family for safety assessment in multimodal conversations. SingGuard treats the active policy as a runtime input: given natural-language rules, it checks the target content against the active policy rule by rule and predicts both the safety label and the triggered rule. To balance efficiency and interpretability, SingGuard supports fast, hybrid, and slow inference regimes along a fast-to-slow reasoning spectrum, ranging from direct safety judgments to policy-grounded deliberation. We further optimize this behavior with fast–slow decoupled reinforcement learning. We also introduce SingGuard-Bench, a multimodal guardrail benchmark with 56{,}340 examples spanning 80+ fine-grained risk types across multimodal QA, adversarial attack, and dynamic-rule evaluation settings, including cross-modal joint-risk cases where each modality is harmless in isolation but their composition implies unsafe intent. Across six benchmark families (35 datasets), SingGuard achieves state-of-the-art average F1 in every family. Dynamic-rule evaluation further shows improved policy-following accuracy from 0.6465 to 0.7415 under runtime policy shifts. Our code is available at https://github.com/inclusionAI/Sing-Guard.