中 EN
Sign In Register

Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

Sign In Register
01.
arXiv (math.PR) 2026-06-18

Formation of clusters and coarsening in weakly interacting diffusions

Authors:
Nicolai Gerber↗Rishabh S. Gvalani↗Martin Hairer↗Grigorios A. Pavliotis↗Andr\'e Schlichting↗

arXiv:2510.17629v3 Announce Type: replace-cross Abstract: This paper studies the clustering behavior of weakly interacting diffusions under the influence of sufficiently localized attractive interaction potentials on the one-dimensional torus. We describe how this clustering behavior is closely related to the presence of discontinuous phase transitions in the mean-field PDE. For local attractive interactions, we employ a new variant of the strict Riesz rearrangement inequality to prove that all global minimizers of the free energy are either uniform or single-cluster states, in the sense that they are symmetrically decreasing. We analyze different timescales for the particle system and the mean-field (McKean-Vlasov) PDE, arguing that while the particle system can exhibit coarsening by both coalescence and diffusive mass exchange between clusters, the clusters in the mean-field PDE are unable to move and coarsening occurs via the mass exchange of clusters. By introducing a new model for this mass exchange, we argue that the PDE exhibits dynamical metastability. We conclude by presenting careful numerical experiments that demonstrate the validity of our model.

Read & Discuss → View Source →
02.
arXiv (CS.CV) 2026-06-16

CogCanvas: A Benchmark for Evaluating Multi-Subject Reference-Based Image Generation

Authors:
Long-Bao Nguyen↗Quang-Khai Tran↗Tam V. Nguyen↗Minh-Triet Tran↗Trung-Nghia Le↗

Multi-subject reference-based image generation requires jointly preserving multiple human identities, binding per-person objects and fashion items, and respecting a specified background scene, a regime where current diffusion models remain brittle. Existing benchmarks evaluate only one axis at a time and none jointly captures multi-identity composition with human-object interaction, background grounding, and spatial plausibility. We introduce CogCanvas, a benchmark of 1,952 curated reference images spanning 100 celebrity identities, 115 distinctive objects and fashion items, and 29 real-world background scenes including landmarks, from which we construct 1,361 compositional prompts covering 2-5 person group sizes. The curation pipeline combines DINOv2-based deduplication, two-stage aesthetic filtering, and automated derivation of structured interaction and position graphs that serve as ground-truth supervision. CogCanvas supports three tasks, reference-based multi-human-object generation (primary), text-to-image compositional generation, and reference retrieval, under a unified six-axis evaluation protocol. We introduce two metrics tailored to the multi-reference setting: BG-Sim, which scores background fidelity on SAM 3-masked regions via DINOv3 feature similarity, and Attr-VQA, which uses a multimodal LLM to verify per-subject attribute binding and inter-person interactions against the structured graphs. Benchmarking five SOTA methods reveals that every model degrades substantially as group size grows from 2 to 5, with near-complete failure on object/fashion binding beyond three subjects.

Read & Discuss → View Source →
03.
arXiv (CS.CL) 2026-06-25

The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms

Authors:
Jinghan Zhang↗Zerui Cheng↗Shiqi Chen↗Ge Zhang↗Wenhao Huang↗Jiashuo Liu↗Junxian He↗Tianle Cai↗

Traditional evaluations measure a learning algorithm's final performance on an i.i.d. test set, reducing learning to a single aggregate score. This approach obscures a fundamental question: to what extent does learning from a specific example generalize to others? Such per-sample generalization, akin to learning by analogy in human cognition, captures how far the knowledge extracted from one example can transfer, yet remains invisible to standard benchmarks. We introduce the Generalization Spectrum, an evaluation framework designed to expose this hidden dimension. For each training example, we construct a controlled suite of test variants arranged by increasing transfer distance, from exact recall to implementation transfer across languages, context transfer under complete narrative re-framing, category-matched in-domain problems, and an unpaired baseline. By tracking performance across these distances, we reveal not just whether an algorithm learns, but how far that learning extends. We instantiate this framework on competitive programming, using a selection-and-synthesis pipeline seeded with recent problems to mitigate contamination. We first compare three canonical learning paradigms under matched memorization. RL converts memorization into near-transfer more efficiently than SFT-family baselines, while ICL exhibits strong but correspondence-dependent transfer. We then use the Spectrum to diagnose within-family variants. The resulting profiles show that local gains need not expand the generalization radius: abstractions and hints mainly lift local transfer, RFT preserves a stronger far-transfer tail than reference SFT, and self-distillation or hint-assisted RL can reduce far transfer even when local transfer or optimization improves.

Read & Discuss → View Source →
04.
arXiv (CS.CL) 2026-06-16

A Unified Definition of Hallucination: It's The World Model, Stupid!

Authors:
Emmy Liu↗Varun Gangal↗Chelsea Zou↗Michael Yu↗Xiaoqi Huang↗Alex Chang↗Zhuofu Tao↗Karan Singh↗Sachin Kumar↗Steven Y. Feng↗

Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review existing definitions of hallucination and fold them into a single, unified definition wherein prior definitions are subsumed. We argue that hallucination can be unified by defining it as simply inaccurate (internal) world modeling, in a form where it is observable to the user. For example, stating a fact which contradicts a knowledge base OR producing a summary which contradicts the source. By varying the reference world model and conflict policy, our framework unifies prior definitions. We argue that this unified view is useful because it forces evaluations to clarify their assumed reference "world", distinguishes true hallucinations from planning or reward errors, and provides a common language for comparison across benchmarks and discussion of mitigation strategies. Building on this definition, we also connect our framework to HalluWorld, a complementary benchmark that instantiates fully specified reference world models for stress-testing model hallucinations.

Read & Discuss → View Source →
05.
arXiv (CS.AI) 2026-06-11

Are LLMs Bad at Moral Reasoning?

Authors:
Menghang Zhu↗Seth Lazar↗

arXiv:2606.11635v1 Announce Type: cross Abstract: For highly capable AI systems to operate safely in dynamic, open-ended environments, they must be able to identify, understand, and respond to moral reasons for action, and constrain their behaviour accordingly. A growing body of research aims to evaluate this capacity – moral competence – in today's most capable AI systems, recently reaching broadly pessimistic conclusions. One of the most ambitious such papers collects gold-standard human-authored rubrics for evaluating moral reasoning in 1,000 cases, and benchmarks frontier AI models against those rubrics, with underwhelming results. In this paper, we argue that the MoReBench dataset can be redeployed to give a much more optimistic picture of LLMs' moral reasoning (an essential part of moral competence). We show that if, instead of scoring LLMs' responses to these cases against these rubrics, we instead give the LLMs the same task given to humans – to generate scoring rubrics for the moral analysis of particular cases – the rubrics they generate are both better calibrated to the human rubrics than their open-ended responses, and, where they differ, plausibly reflect nothing more than the vast dimensionality of most moral problems, as well as highlighting some human departures from the "rubric for creating rubrics". Taking these points into consideration, the MoReBench dataset suggests that LLMs are significantly more capable at moral reasoning than was previously believed.

Read & Discuss → View Source →
06.
arXiv (CS.AI) 2026-06-18

Generative-Model Predictive Planning for Navigation in Partially Observable Environments

Authors:
Thomas Quilter↗Yifan Zhu↗Guorui Quan↗Mingfei Sun↗Samuel Kaski↗

arXiv:2606.18888v1 Announce Type: new Abstract: Navigation in partially observable environments presents a significant challenge for autonomous agents, requiring effective decision-making with limited sensory information in unknown environments. Belief-based methods, particularly those using neural networks to approximate the belief space, often fail to capture the inherent multimodality of belief spaces, especially in high-dimensional cases with perceptual aliasing. While generative models present a compelling alternative, they typically require substantial data or expert demonstrations and lack explicit mechanisms for long-term planning. In this paper, we introduce BeliefDiffusion, a novel framework that combines the benefits of both generation and planning. BeliefDiffusion leverages diffusion models to explicitly characterize multimodal belief distributions and utilizes Model Predictive Control (MPC) to simultaneously plan ahead. It consists of two steps: (1) Imagining plausible environment configurations based on observation history and (2) Planning efficient navigation strategies across an aggregated configurations. Through extensive experiments in synthetic map environments, we demonstrate that BeliefDiffusion significantly outperforms both model-free reinforcement learning baselines and other generative approaches in navigation success rate and path efficiency. Our results validate that explicitly incorporating multimodal belief representations into planning enables more robust navigation in partially observable settings.

Read & Discuss → View Source →
07.
arXiv (CS.CL) 2026-06-15

Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2

Authors:
Pere Martra↗

Structured width pruning of GLU-MLP layers in Llama-3.2 models, guided by the Peak-to-Peak Magnitude (PPM) criterion, reveals a systematic dichotomy in how reducing the expansion ratio affects different model capabilities. While performance on tasks relying on parametric knowledge (e.g., MMLU, GSM8K) and perplexity metrics degrades predictably with decreasing expansion ratios, instruction-following capabilities improve at the 2.4x equilibrium ratio (IFEval: +4.8 points / +46% in Llama-3.2-1B and +3.7 points / +39% in Llama-3.2-3B), and multi-step reasoning remains robust (MUSR). This pattern, observed consistently across both evaluated model sizes, challenges the prevailing assumption in compression research that pruning induces uniform degradation. To investigate this, we evaluated seven expansion ratio configurations using comprehensive benchmark suites that assess factual knowledge, mathematical reasoning, language comprehension, instruction-following, and truthfulness. Our analysis identifies the expansion ratio as a critical architectural parameter that selectively reshapes the model's task performance profile, rather than merely serving as a compression metric.

Read & Discuss → View Source →
08.
arXiv (CS.CV) 2026-06-12

V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

Authors:
Lorenzo Mur-Labadia↗Matthew Muckley↗Amir Bar↗Mido Assran↗Koustuv Sinha↗Mike Rabbat↗Yann LeCun↗Nicolas Ballas↗Adrien Bardes↗

We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene understanding. The approach combines four key components. First, a dense predictive loss uses a masking-based objective in which both visible and masked tokens contribute to the training signal, encouraging explicit spatial and temporal grounding. Second, deep self-supervision applies the self-supervised objective hierarchically across multiple intermediate encoder layers to improve representation quality. Third, multi-modal tokenizers enable unified training across images and videos. Finally, the model benefits from effective scaling in both model capacity and training data. Together, these design choices produce representations that are spatially structured, semantically coherent, and temporally consistent. Empirically, V-JEPA 2.1 achieves state-of-the-art performance on several challenging benchmarks, including 7.71 mAP on Ego4D for short-term object-interaction anticipation and 40.8 Recall@5 on EPIC-KITCHENS for high-level action anticipation, as well as a 20-point improvement in real-robot grasping success rate over V-JEPA-2 AC. The model also demonstrates strong performance in robotic navigation (5.687 ATE on TartanDrive), depth estimation (0.307 RMSE on NYUv2 with a linear probe), and global recognition (77.7 on Something-Something-V2). These results show that V-JEPA 2.1 significantly advances the state of the art in dense visual understanding and world modeling.

Read & Discuss → View Source →
09.
medRxiv (Medicine) 2026-06-24

MedGenesis: Toward a World Model for Autonomous Clinical and Translational Research

Authors:
Xiao↗Jiang↗Zhang↗Yin↗Gui↗Shao↗Ge↗Wei↗Pan↗Ma↗Yang↗Zhao↗…

Clinical research advances slowly because its core tasks, from evidence synthesis to mechanistic validation, remain fragmented. We present MedGenesis, a clinical artificial intelligence (AI) scientist built on a world-model reasoning loop that jointly updates a Latent Hypothesis Space and a Latent Action Space under expected information gain (EIG), uncertainty reduction (UR), and a safety prior P(safe), and integrates longitudinal electronic health records (EHRs) via the Virtual Clinical Trajectory and Observation Representation (ViCTOR) for cohort retrieval, trajectory stratification, and time-to-event analysis. On two benchmarks - ClinicalResBench (1,697 expert-curated questions) and ClinicalRepBench (40 paper-reproduction tasks) - MedGenesis outperformed frontier language models and biomedical AI systems while reducing hallucination. Across 1 million patient observations spanning five clinical evidence formats, it generated traceable outputs across meta-analysis, randomized controlled trials, real-world trajectories, case-control studies, and case reports, with one wet-lab-coupled run nominating a 3-hydroxybutyrate - neutrophil axis modulating antitumor immunity. These results compress hypothesis-to-evidence cycles from years to hours, creating a continuous clinical discovery process.

Read & Discuss → View Source →
11.
arXiv (CS.AI) 2026-06-16

LLM4RTL: Tool-Assisted LLM for RTL Generation

Authors:
Jing Jin↗Robert Chu↗Ning Yan↗Masood S. Mortazavi↗

arXiv:2606.15500v1 Announce Type: cross Abstract: Large language models (LLMs) have facilitated impressive progress in software engineering, code generation, tooling, and systems. Concurrently, a significant body of research has developed which explores a growing variety of methods and systems for applying LLMs to hardware and chip design (e.g., systems for RTL code generation based on functional description). However, when it comes to open Verilog/RTL code-generation, we need high-quality training samples to build specialized and more effective LLM systems through fine-tuning or low-rank adaptation. Here, we propose a ``judge-renew-check-renew-check'' (JRCRC) pipeline which updates a current public dataset using a hierarchy of state-of-the-art commercial LLM models differing in their costs and capabilities in RTL code generation. This approach achieves a cost-effective mechanism for filtering and refining code-generation samples into a higher-quality training dataset. Our experiments also identify some common weaknesses of LLMs in rule-based reasoning and logic, and consequently, in RTL code-generation. Having identified these weaknesses, we develop an architecture for incorporating pre-processing tools to dynamically assist the LLMs in inferring logical relationships from tabular data formats. With our tools-assisted architecture for RTL code generation, we achieve significant overall performance gains in the VerilogEval benchmark and outperform many state-of-the-art methods. Our LLM4RTL system achieves performance comparable to that of GPT-4O using a significantly much smaller LLM.

Read & Discuss → View Source →
12.
arXiv (CS.CL) 2026-06-17

ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents

Authors:
Ander Alvarez↗Santhiya Rajan↗Samuel Mugel↗Rom\'an Or\'us↗

Tool-using LLM agents increasingly use the Model Context Protocol (MCP) to answer from heterogeneous evidence sources, including search, APIs, databases, clinical records, and formulary tools. Standard factuality metrics usually test whether an answer is supported by pooled evidence, missing a provenance-sensitive failure mode: a claim may be supported somewhere while being attributed to the wrong source. We call this cross-source conflation. We introduce ProvenanceGuard, a source-aware verifier for MCP-grounded answers. It consumes captured MCP traces with stable tool IDs, source IDs, and raw outputs; decomposes answers into atomic claims; routes claims to source-specific evidence; checks support with NLI and a token-alignment proxy; compares stated attribution with the routed source; and returns per-claim verdicts plus an answer-level allow/block decision. Blocked answers can be repaired with retrieval-augmented answer revision and re-verified. We evaluate on 281 medical-domain MCP-agent traces. A 266-trace adjudicated subset yields 2,325 LLM-assisted claim labels split by trace; 361 held-out labels are human-verified. On the 40-trace held-out split, ProvenanceGuard achieves block F1 0.802 and source accuracy 0.858 over 260 source-eligible claims, outperforming source-blind baselines that do not emit claim-to-source IDs. On a harder multi-source benchmark it reaches block F1 0.846, while source-plus-relation accuracy drops to 0.229, showing that exact source ownership remains difficult with semantically close sources. Repair-and-reverify resolves all blocked answers in the full trace set, often via conservative fallback. In 50 controlled clinical conflation probes, ProvenanceGuard detects all injected attribution swaps with no retained wrong attribution. These results show that source attribution is an independent axis for factuality verification in MCP-based agents.

Read & Discuss → View Source →
13.
arXiv (CS.CV) 2026-06-18

Beyond the Linear Separability Ceiling: Aligning Representations in VLMs

Authors:
Enrico Vompa↗Tanel Tammet↗Mohit Vaishnav↗

A challenge in advancing Visual-Language Models (VLMs) is determining whether their failures on abstract reasoning tasks, such as Bongard problems, stem from flawed perception or faulty top-down reasoning. To disentangle these factors, we introduce a diagnostic framework centered on the Linear Separability Ceiling (LSC), the performance achievable by a linear classifier on a VLM's raw visual embeddings. Applying this framework to state-of-the-art VLMs, we uncover a pervasive ''alignment gap'', where most models fail to generatively outperform the linear separability of their representations. We find that the few models surpassing this ceiling do so via two mechanisms: by further refining visual representations into a more linearly separable format or by executing non-linear decision logic. We demonstrate that this bottleneck is not a fundamental limitation but a solvable visual alignment issue. Our method augments standard next-token prediction with a contrastive objective to restructure the visual manifold into a more one-dimensionally linear geometry, improving image-to-image comparison and enabling models to significantly surpass the LSC on abstract compositional reasoning tasks.

Read & Discuss → View Source →
14.
arXiv (CS.LG) 2026-06-15

Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learning

Authors:
Omar Adalat↗Edwin Hamel-De le Court↗Francesco Belardinelli↗

arXiv:2606.14130v1 Announce Type: new Abstract: Safe coordination problems surface in multi-agent reinforcement learning when global safety cannot be enforced by any agent unilaterally: the admissibility of one agent's action may depend on the dynamics of other agents. Decentralised shields can enforce safety at runtime, but purely factorised permissions often exclude optimal team behaviour that is safe only through coordination. We study deterministic safety guarantees for agents trained and deployed under decentralised execution, recovering team-optimal safe behaviour without centralised runtime control. Agents have a shared global specification $\phi$ in the safety fragment of Linear Temporal Logic ($\mathsf{LTL}_{\mathsf{safe}}$ ), and select among tuples of local $\mathsf{LTL}_{\mathsf{safe}}$ obligations whose conjunction implies the global specification $\phi$. Each agent may rely on the other agents' local obligations as assumptions because the whole contract tuple is certified simultaneously and allows projection into local action masks. At learning time, a non-stationary multi-armed bandit chooses among a library of local $\mathsf{LTL}_{\mathsf{safe}}$ obligations to select the tuple that optimises team reward, all without forgoing end-to-end safety. We evaluate the approach across 6 environments and 15 algorithmic variants.

Read & Discuss → View Source →
15.
arXiv (CS.AI) 2026-06-16

TrustedARI: Towards Trust-Native Agentic Routing Infrastructure for Agentic AI

Authors:
Qi Li↗Zhenhua Zou↗Shuo Li↗Mingwei Xu↗Zhuotao Liu↗

arXiv:2606.15822v1 Announce Type: new Abstract: AI agents increasingly access external models, tools, and services through Agentic Routing Infrastructure (ARI) to manage the overhead of heterogeneous interfaces and fragmented subscriptions. Yet, the architecture of ARI introduces fundamental trust risks: it obtains plaintext access to agent queries and service responses, while leaving agents unable to verify that their queries are routed to intended service providers or that requests and responses remain untampered. To address this problem, we present TrustedARI, the first trust-native agentic routing infrastructure for agentic AI. Architecturally, TrustedARI is built upon three core innovations: (i) an ARI-adapted three-party TLS handshake that enables the agent and ARI to jointly authenticate the service provider through role-specific distribution of TLS key materials; (ii) a privacy-preserving query-construction protocol that allows the agent and ARI to collaboratively construct well-formed queries without exposing their respective private inputs; and (iii) a verifiable billing protocol that supports fair usage-based settlement while preserving the integrity and confidentiality of service responses. We implemented and extensively evaluated a prototype of TrustedARI to validate its performance. Experiments confirm that TrustedARI is highly efficient: our ARI-adapted handshake protocol reduces communication overhead by 39.34% compared to the existing three-party TLS handshake. Furthermore, the privacy-preserving query-construction protocol imposes negligible overhead-averaging 0.19 seconds in computation time and 0.58 MB in communication costs-while the verifiable billing protocol speeds up proof generation by 28.20x. Crucially, TrustedARI is readily deployable without any modification to the service providers.

Read & Discuss → View Source →
16.
arXiv (CS.CL) 2026-06-25

Space-Efficient Language Generation in the Limit

Authors:
Nicolas Flammarion↗Chirag Pabbaraju↗Hristo Papazov↗Miltiadis Stouras↗Ola Svensson↗

We initiate a resource-aware theory of language generation in the limit under the minimal constraint of space efficiency. In our framework, a learner observes an adversarial positive stream from a target language $K$ and must eventually output a hallucination-free hypothesis language $L \subseteq K$ while omitting at most $\Delta$ strings of $K$. We focus on $\mathcal{C}_{s,k}$, the collection of languages recognized by DFAs with at most $s$ states over an alphabet of size $k$, as the natural hypothesis class for memory-bounded learners. In the exponential-space regime, we prove that a learner can exactly identify the target $K$. Under a stricter memory budget, we characterize the strongest possible generation guarantees. In particular, we present a streaming algorithm using $\mathrm{poly}(s,k)$ space that converges to a hypothesis with generation gap $\Delta = O(k^{2s-2})$. Moreover, the learned hypothesis captures every string in $K$ of length at least $2s-1$. We complement this result with a near-matching lower bound through a reduction from a standard communication complexity problem. Specifically, achieving generation gap $\Delta \le k^{(1-\varepsilon)s}$ requires $k^{\Omega(\varepsilon s)}$ memory. Together, these results reveal a sharp transition between polynomial-space generation and exponential-space exact identification.

Read & Discuss → View Source →
17.
arXiv (CS.AI) 2026-06-25

On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity

Authors:
Andrei Liviu Nicolicioiu↗Mohammad Pezeshki↗Aaron Courville↗

arXiv:2606.26091v1 Announce Type: cross Abstract: On-policy self-distillation achieves strong pass@1 accuracy by using a single model as both teacher and student, with the teacher conditioned on a correct demonstration to provide dense token-level feedback. We show that this could come at a hidden cost: rollout diversity decreases and pass@k curves flatten (i.e., generating more rollouts fails to improve accuracy). We trace this to compounding biases in the design of self-distillation with sampled demonstrations. The teacher scores each student rollout while conditioned on a sampled correct rollout, channeling its feedback through the model's own biases. We theoretically analyze the optimal self-distillation policy and show that it tilts the base distribution by a pointwise conditional mutual information score between the student's rollout and the correct rollout used as context. Unlike the ideal optimal on-policy reinforcement learning (RL), which preserves probability ratios among equally correct rollouts, self-distillation can amplify existing probability gaps, concentrating mass on already-dominant modes. On a controlled graph path-finding task and science question-answering benchmarks, self-distilled models match or exceed RL on average performance but exhibit substantially lower functional and semantic diversity, failing on out-of-distribution settings that require diverse strategies.

Read & Discuss → View Source →
18.
arXiv (quant-ph) 2026-06-11

Towards the implementation of a quantum classifier

Authors:
Lorenzo Confalonieri↗

arXiv:2606.10150v2 Announce Type: replace Abstract: In this work, we investigate the use of a quantum circuit as a binary classification model in the context of quantum machine learning. We call this model, binary quantum classifier. First, we describe fundamental concepts of quantum computing and introduce the computational tool used: Qibo, an open-source framework for efficient quantum simulations and quantum hardware control. Then, we describe how to design a binary quantum classifier for the classification of images and small arrays of variables by showing how to input data in the circuit, defining a quantum circuit model Ansatz with trainable parameters and a loss function, and implementing multiple minimizers. We test our quantum classifier with two data sets. The first one is the MNIST data set which is composed of handwritten digits (reduced to only handwritten zeros and handwritten ones for binary classification). We study the behavior of different minimizers by increasing the number of layers of the Ansatz. The second data set represents two different high energy collisions that can occur at colliders such as LHC (CERN). Due to in-time proton-proton interactions known as pile-up, we distinguish two different data sets: "without pile-up" and "with pile-up". These collisions can be represented by images of size 32x32 or by six high-level variables that we call features. By increasing the size of the training data set and the number of layers of the Ansatz, we search for the best minimizer. Splitting the data set in training set and test set, we compute: ROC curve, AUC score, confusion matrices and test set accuracy. For "with pile-up" images, we compare the results obtained with the quantum classifier with a small convolutional neural network. We conclude that is possible to build a binary quantum classifier with a quantum circuit and we highlight its performances and limitations in comparison with classical technologies.

Read & Discuss → View Source →
19.
arXiv (CS.CV) 2026-06-25

TriViewBench: Controlled Complexity Scaling for Multi-View Structural Reasoning in MLLMs

Authors:
Yu-Yang Chen↗Lan-Zhe Guo↗

Multimodal Large Language Models (MLLMs) demonstrate strong performance on standard visual question answering benchmarks, yet their scalability under controlled structural complexity remains poorly understood. We introduce TriViewBench, a controlled three-view visual reasoning benchmark constructed from synthetic 3D scenes with explicitly parameterized object count and occlusion. The benchmark contains 1,923 scenes and over 14K Question-Answer (QA) pairs organized into four complexity levels and three reasoning categories: Local Decision, Object Counting, and Global Recovery. We evaluate 18 open- and closed-source MLLMs under a unified prompting protocol. All 18 models exhibit an identical capability hierarchy without exception (Local Decision > Object Counting > Global Recovery), and performance degrades monotonically with complexity: Local Decision tasks decline modestly (12.11% relative drop), while Object Counting degrades substantially (59.14%) and Global Recovery collapses severely (80.02%). Error analysis on Object Counting reveals two mechanistically independent failure modes: single-view tasks are dominated by undercounting due to occlusion blindness, whereas the multi-view task reverses to overcounting due to cross-view identity confusion. Chain-of-Thought (CoT) prompting yields near-zero overall benefit ($\Delta = -0.16\%$) and its effect on Global Recovery is strongly capability-gated, suggesting that the bottleneck lies in cross-view spatial representation rather than reasoning strategy. These findings reveal fundamental scalability limitations in current MLLMs and position TriViewBench as a controlled diagnostic framework for analyzing structural reasoning failures.

Read & Discuss → View Source →
20.
bioRxiv (Bioinfo) 2026-06-24

Statistical tests for bivariate spatial association across multi-omics data with disjoint coordinates

Authors:
Hawinkel↗Hu↗Velten↗Maere↗

Spatial biology has entered a new era of multimodal profiling, with multiple, high-dimensional spatial omics types being measured on consecutive tissue slices, or co-assayed on the same slice. Interest then lies in statistical testing for spatial association between the features of the different modalities, to gain insight in biological processes. One major challenge is the multitude of bivariate combinations, leading to high computational demands. Another difficulty is the difference in spatial resolution between technologies, implying no one-to-one matching between the measurement spots of the two modalities, even after alignment. As a result, common statistical measures such as joint distributions and correlations are not defined, and tests need to rely on spatial vicinity only. Moreover, we argue that many existing bivariate association tests address an inappropriate null hypothesis, or make inappropriate assumptions, both implying absence of spatial autocorrelation in any of the features and leading to misleading conclusions. As a remedy, we modify tests for the detection of spatially variable genes (Moran's I, Gaussian processes and generalized additive models (splines)) to derive bivariate tests across modalities with non-overlapping coordinate sets and provide variance estimators that do account for spatial autocorrelation. We develop inference methods for single sections as well as for replicated experiments with multiple sections, and compare their performance in nonparametric and parametric simulations. Finally, we apply the newly developed methods to two co-assayed spatial transcriptomics and metabolomics datasets from mouse and human. The full suite of tests is available from github.com/sthawinke/sbivar as the R-package sbivar.

Read & Discuss → View Source →
21.
arXiv (CS.CV) 2026-06-24

Beyond a Single Light: A Large-Scale Aerial Dataset for Urban Scene Reconstruction Under Varying Illumination

Authors:
Zhuoxiao Li↗Wenzong Ma↗Taoyu Wu↗Jinjing Zhu↗Shuai Zhang↗Jing OU↗Tongyan Hua↗Yinrui Ren↗Rongjun Qin↗Hui Xiong↗Wufan Zhao↗

Recent advances in Neural Radiance Fields and 3D Gaussian Splatting have demonstrated strong potential for large-scale UAV-based 3D reconstruction tasks by fitting the appearance of images. However, real-world large-scale captures are often based on multi-temporal data capture, where illumination inconsistencies across different times of day can significantly lead to color artifacts, geometric inaccuracies, and inconsistent appearance. Due to the lack of UAV datasets that systematically capture the same areas under varying illumination conditions, this challenge remains largely underexplored. To fill this gap, we introduceSkyLume, a large-scale, real-world UAV dataset specifically designed for studying illumination robust 3D reconstruction in urban scene modeling: (1) We collect data from 10 urban regions data comprising more than 100k high resolution UAV images (four oblique views and nadir), where each region is captured at three periods of the day to systematically isolate illumination changes. (2) To support precise evaluation of geometry and appearance, we provide per-scene LiDAR scans and accurate 3D ground-truth for assessing depth, surface normals, and reconstruction quality under varying illumination. (3) For the inverse rendering task, we introduce the Temporal Consistency Coefficient (TCC), a metric that measuress cross-time albedo stability and directly evaluates the robustness of the disentanglement of light and material. We aim for this resource to serve as a foundation that advances research and real-world evaluation in large-scale inverse rendering, geometry reconstruction, and novel view synthesis.

Read & Discuss → View Source →
22.
arXiv (math.PR) 2026-06-16

Higher-order spectral perturbation expansions II: Kernel matrices and manifold learning

Authors:
Bernhard Stankewitz↗Martin Wahl↗

arXiv:2606.16373v1 Announce Type: cross Abstract: We study spectral concentration bounds for kernel matrices as approximation of the corresponding kernel integral operator. Results are established under weak assumptions on the data setting and the reproducing kernel relying only on a Mercer condition and a local Weyl law. This allows us to deal with key features of kernel matrices, such as large multiplicities, large effective dimension, and heavy-tailed distributions. Our results apply to infinite dimensional principal component analysis, manifold learning, and Bayesian nonparametric statistics. We illustrate this via two prototypical examples: The heat kernel on the sphere and a wavelet prior from Bayesian nonparametrics.

Read & Discuss → View Source →
23.
arXiv (CS.AI) 2026-06-16

Open-SWE-Traces: Advancing Dual-Mode Multilingual Distillation for Software Engineering Agents

Authors:
Wasi Uddin Ahmad↗Nikolai Ludwig↗Somshubra Majumdar↗Boris Ginsburg↗

arXiv:2606.16038v1 Announce Type: cross Abstract: The path toward autonomous software engineering is currently bottlenecked by a severe deficit of diverse, large-scale trajectory data. We address this by introducing \ourdataset, an expansive dataset of 207,489 agentic trajectories spanning nine programming languages (Python, Go, TS, JS, Rust, Java, PHP, C, C++). Sourced from 20,000 real-world PRs via OpenHands and SWE-agent harnesses, the dataset utilizes a hybrid-reasoning synthesis: Minimax-M2.5 generates trajectories with explicit "thinking" processes, while Qwen3.5-122B provides high-quality "non-thinking" traces. Filtered for permissive licenses (MIT, Apache, BSD) from SWE-rebench-V2, this data facilitates the training of models capable of long-horizon reasoning. We validate the dataset by fine-tuning the Qwen3-30B-A3B series (Thinking, Instruct, and Coder). The best performing model achieves resolve rates of 61.7% on SWE-bench Verified, 57.1% on SWE-bench Multilingual, and 36.8% on SWE-bench Pro. These results establish Open-SWE-Traces as a premier resource for distilling human-level software engineering capabilities into efficient, open-source agentic LLMs.

Read & Discuss → View Source →
24.
arXiv (CS.LG) 2026-06-24

Polaris: A Godel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair

Authors:
Aditya Kakade↗Vivek Srivastava↗Shirish Karande↗

arXiv:2603.23129v3 Announce Type: replace Abstract: Gödel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop. We introduce Polaris, a Gödel agent for compact models that performs policy repair via experience abstraction, turning failures into policy updates through a structured cycle of analysis, strategy formation, abstraction, and minimal code pat ch repair with conservative checks. Unlike response level self correction or parameter tuning, Polaris makes policy level changes with small, auditable patches that persist in the policy and are reused on unseen instances within each benchmark. As part of the loop, the agent engages in meta reasoning: it explains its errors, proposes concrete revisions to its own policy, and then updates the policy. To enable cumulative policy refinement, we introduce experience abstraction, which distills failures into compact, reusable strategies that transfer to unseen instances. On MGSM, DROP, GPQA, and LitBench (covering arithmetic reasoning, compositional inference, graduate-level problem solving, and creative writing evaluation), a 7-billion-parameter model equipped with Polaris achieves consistent gains over the base policy and competitive baselines.

Read & Discuss → View Source →
25.
arXiv (CS.CL) 2026-06-19

Telenor Nordics Customer Service self-help corpus

Authors:
Mike Riess↗

This paper presents a multilingual customer service self-help corpus comprising 1,122 manually validated documents in Finnish, Danish, Norwegian, and Swedish, totaling 274,599 words and 1,884,833 characters. The documents have been sourced from the public self-help pages of four Nordic telecommunications operators and subsequently filtered for person-identifiable information and relevance through a combined LLM and human annotation pipeline. Domain-specific datasets for Nordic languages remain scarce, particularly in customer service: a domain of growing importance for retrieval-augmented generation, cross-lingual transfer learning, and emerging agent-based service architectures. An analysis of the corpus reveals substantial variation in document length and structure across operators, reflecting distinct editorial strategies, as well as broad topical coverage spanning network hardware, mobile services, TV and streaming, billing, and account management. The dataset is publicly available under a CC-BY-NC-SA-4.0 license at https://zenodo.org/records/20732652, intended to support reproducible research in Nordic NLP and information retrieval.

Read & Discuss → View Source →