Machine Learning
Measuring Memory and Generalization as Separable Geometric Channels: The Topo^2 Framework
Zhanbo Zhang, Ming Liu and Qing Wang
Deep networks trained on noisy labels simultaneously generalize on clean data and memorize flipped labels. These are usually conflated as pressures on one capacity. We present Topo^2, a measurement framework that makes them causally separable, measurable, and law-governed. Persistent-homology H1 structure of the representation space separates into a within-class
manifold channel (a function of the training stopping point) and a cross-class channel (a monotone readout of memorized flipped samples). An intervention, the FM0 prescription (zero loss on flipped samples from epoch 0), reaches each setting's generalization ceiling while memorizing essentially nothing. Within the framework we establish a law set with graded evidence: (L2) FM0 separation prescription (9/9); (L1) the within-channel as a training-position function (mid-rise 6/6; convergence-back CIFAR 3/3, SVHN 2/3); (L3) a ring-construction identity (definitional, not a law); and TLS (
memory-generalization topological layering):
memory is causally additive, anchored (silencing clean collapses the representation), invertible (stripping
memory restores near-ceiling generalization), and quantitatively billable (the memorization cost law, effective slope coefficient C ~ 0.38 at the reference capacity: CIFAR-10 0.3801 / SVHN 0.3806 / CIFAR-100 0.384 / VGG 0.3715, capacity-dependent in general and traced to clean-sample feature displacement). We also publish the framework's boundaries: a falsification ledger of nine dead ends, and an instrument-vindication section that excludes six families of global statistics as explanations of the within-channel. The framework turns "memorization" from an ill-defined capacity into a measurable, separable, invertible topological layer.
Read the full abstract ▾
Computation and Language
Two Centuries of Sexism in British Parliament: A Computational Analysis of Women's Representation in the Hansard Corpus
Mohammad Omar Khursheed, Mandira Sawkar and Ashiqur R. KhudaBukhsh
The
language a legislature uses to debate women's rights, even in favour of them, encodes systematic patterns of sexism that persist across two centuries. In this work, we analyse 6,531
speeches over 200 years of UK parliamentary debate (Hansard, 1803-2005) by using large
language models to classify a speaker's perspective towards women's suffrage and political representation, as well as analyse sexist
speech in parliament from the lens of the Ambivalent Sexism Inventory. We also release this parliamentary
dataset, an organized and metadata-enriched version of the publicly available Hansard Corpus optimized for computational social science research, with 6.7 million
speeches across 1.2 million debates, with 89% gender-matching for
speeches by MPs from the House of Commons. We find that 54% of
speeches opposing women's representation contain sexist content, compared to 21% of
speeches that are for the cause, and that the two sides use fundamentally different types of sexism: anti-suffrage rhetoric combines hostile and benevolent framing, while pro-suffrage sexism is overwhelmingly benevolent. Female MPs support women's political rights at 93% compared to 70% for male MPs, a gap that closes only after enfranchisement. Our findings are evidence that benevolent and hostile sexism are used in different rhetorical contexts in a manner consistent with the theory of Ambivalent Sexism.
Read the full abstract ▾
Computer Vision
VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs
Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie et al. (+1 more)
Object
hallucination remains a persistent reliability issue in large
vision-
language models, where generated object mentions may sound plausible but lack visual grounding. Recent training-free detectors use internal signals such as
token likelihood,
attention, visual confidence, or image-text similarity to identify hallucinated objects. These signals are useful, but they are often source-confounded. They measure how strongly an object is supported inside the model without distinguishing whether that support comes from object-specific visual evidence or the generated text prefix. In difficult cases, a hallucinated object can still receive high internal support because it fits the scene, is associated with nearby visual cues, or follows naturally from the generated text prefix. We propose VisER, a training-free two-sided metric for object-level
hallucination detection. VisER evaluates each generated object mention from two complementary views. Visual Evidence measures whether object-context compatibility is backed by object-specific evidence from image
tokens. Visual Reliance measures whether the object is supported more by the image than by the generated prefix. Combining these views gives a more source-aware grounding score, while avoiding additional object-level verification generations. Across multiple LVLMs and
benchmarks, VisER improves AUROC and AUPR over a range of baselines.
Read the full abstract ▾
All authors Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie, Sarah Erfani
Information Retrieval
HF-SID: High-Fidelity Semantic IDs for Generative Retrieval in Location-Based Services
Haowen Lin, Jing Li, Zhibin Hao et al. (+5 more)
Generative
retrieval has attracted increasing
attention in Location-Based Services (LBS), where each Point-of-Interest (POI) is represented as a Semantic ID (SID). As the SID is the only channel through which POI information reaches the generative model, whatever it fails to preserve is irrecoverable at decoding time, and LBS
retrieval is especially sensitive to the fine-grained differences that existing SIDs blur. Specifically, (1) LLMs embed continuous coordinates discontinuously, so their numeric differences do not reflect true geographic distance; (2) dynamic numerical attributes differ vastly in scale, so an identical gap may be decisive for one attribute yet negligible for another; and (3) short text cannot convey hierarchical affiliation, as text-similar POIs may belong to different hierarchies. We therefore propose HF-SID, which restores geographic, numerical, and structural fidelity at the representation stage, before any information is committed to a discrete code. It transforms coordinates into a continuous 3D Cartesian form and encodes each numerical value as a single unit, consolidated inside the LLM by Geo-CPT and Num-CPT with type-aware
embeddings; a Structure-based Contrastive Learning objective, applied only to the last-layer residual, then separates co-located POIs that share a coarse tag but differ at the fine level. Because these mechanisms enrich the representation rather than lengthen the identifier, HF-SID uses a 3-
token SID at no extra decoding cost. On a large-scale industrial
Read the full abstract ▾
All authors Haowen Lin, Jing Li, Zhibin Hao, Fangye Wang, Lihui Su, Song Yang, Xiaojiang Zhou, Pengjie Wang
Computation and Language
Agents in the Large: Perception-Centered Architecture for Persistent Agents
Shihan Dou, Haoxiang Jia, Shichun Liu et al. (+14 more)
Cognitive
language agents have achieved substantial progress by equipping
language models with
memory, tools, and decision-making procedures, enabling
agents to reason and act in interactive environments. Existing frameworks largely cast these
agents as systems for solving user-specified, bounded tasks. An increasingly important goal is for
language agents to provide persistent assistance in long-lived settings where user needs, context, and service procedures persist and change, and to remain useful across the broad range of tasks that arise over time. Yet we still lack a framework to characterize persistent AI
agents, organize existing work, and guide future development. To this end, we propose a Perception-Centered Architecture for Persistent
Agents (Pera). Pera describes a persistent
agent organized around perception and control components that continually perceive service-relevant signals from episodic task executions, internal context, and changes in the surrounding environment, and use these signals to construct lifecycle tasks. These tasks drive the ongoing operation and adaptation of the
agent's service procedures. We use Pera to retrospectively organize recent work, examine a detailed case study, and offer forward-looking insights for building more capable persistent
agents. Just as software engineering moved from programming in the small to programming in the large, Pera frames the
evolution of
language agents as an analogous architectural transition toward long-lived, adaptive intelligence systems.
Read the full abstract ▾
All authors Shihan Dou, Haoxiang Jia, Shichun Liu, Feng Chen, Chenhao Huang, Yujiong Shen, Shaofan Liu, Jiayi Chen, Jiahang Lin, Honglin Guo, Qianyu He, Minghao Guo, Ziyi Ye, Pluto Zhou, Tao Gui, Qi Zhang, Xuanjing Huang
Computation and Language
ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation
Samir Abdaljalil, Hunzalah Hassan Bhatti, Ahlam Bashiti et al. (+11 more)
We present an overview of the ImageEval 2026 shared task on culturally grounded Arabic
multimodal evaluation. It includes two tasks: (i) AynVQA, covering spoken visual question answering and image-grounded
hallucination detection in English and Modern Standard Arabic (MSA), and (ii) CRAI-Bench, evaluating the cultural accuracy of text-to-image generation. A total of 14 teams participated in the test phase, with 12 teams submitting system description papers. Participating systems used a range of approaches, including zero-shot prompting, fine-tuning of
vision-
language models,
speech-recognition pipelines, ensembling, and score calibration. We describe the task setup,
datasets, evaluation procedure, and participating systems, and summarize the main results across the different tracks. All
datasets and evaluation scripts from the shared task are released to the research community. The shared task highlights the challenges of culturally grounded
multimodal evaluation, particularly for Arabic
speech and image-text
reasoning.
Read the full abstract ▾
All authors Samir Abdaljalil, Hunzalah Hassan Bhatti, Ahlam Bashiti, Farina Amir, Md Arid Hasan, Basel Mousi, Nadir Durrani, Fahim Dalvi, Zien Sheikh Ali, Erchin Serpedin, Hasan Kurban, Mustafa Jarrar, Shammur Absar Chowdhury, Firoj Alam
Cryptography and Security · Cross-listed from math.ST
Bounds on the Posterior-to-Prior Ratios for Inclusion Belief under Bounded Differential Privacy
Jan Reiter Sørensen, Heidi Søgaard Christensen, Rasmus Rask Kragh Jørgensen et al. (+1 more)
Differential
privacy has become the standard for generating
privacy-protected data releases. However, differential
privacy does not translate intuitively to disclosure risk. In particular, it remains unclear how much an adversary's belief about an individual's inclusion in a
dataset can change after observing a protected release. To address this question, we derive upper and lower bounds on the posterior-to-prior ratios of inclusion beliefs under bounded probabilistic and approximate differential
privacy. By assuming a worst-case adversary with all-but-one auxiliary information, i.e., knowledge of all except for one of the participants in a
dataset, we obtain bounds that apply to any adversary. Because these bounds may fail with non-zero probability, we study the corresponding failure probability for the Gaussian mechanism. We derive a theoretical upper limit on this probability and compare it with Monte Carlo estimates across a wide range of parameter settings. The observed failure rate is several orders of magnitude smaller than its theoretical upper limit, indicating that the latter is highly conservative. These findings suggest that the inferential
privacy guarantees provided by differentially private mechanisms may be substantially stronger in practice than what is implied by the theoretical upper limit.
Read the full abstract ▾
All authors Jan Reiter Sørensen, Heidi Søgaard Christensen, Rasmus Rask Kragh Jørgensen, Martin Bøgsted
Machine Learning
ToxLens: A Reproducible Graph-Learning Framework for Leakage-Aware, Uncertainty-Calibrated Molecular Toxicity Prediction
Magnus H. Strømme, Alex G. C. de Sá and David B. Ascher
Molecular toxicity prediction is increasingly used to prioritise compounds before experimental testing, but conventional
benchmark performance can overstate practical utility when structurally related molecules occur across training and test folds. We introduce ToxLens, a reproducible multi-task graph-learning framework for 11 toxicity endpoints spanning Ames mutagenicity, acute oral toxicity, hERG inhibition, and Tox21
nuclear-receptor and stress-response assays. The workflow combines conservative chemical curation, sphere-exclusion filtering, a leakage-aware UMAP-HDBSCAN split, parallel graph and global-feature encoders joined by late concatenation, temperature-scaled Monte Carlo dropout with conformal-style prediction sets, applicability-domain analysis, and SHAP-guided toxicophore discovery with occlusion controls. On the leakage-controlled test fold, a five-seed soft-voting ensemble achieved a Matthews correlation coefficient score of 0.44, an area under the receiver operating characteristic curve score of 0.83, and an area under the precision-recall curve score of 0.58. It exceeded four ECFP4-based shallow baselines on all 11 endpoints under the same split and validation-based threshold-selection protocol. Controlled ablations showed that the global pathway was important, whereas late concatenation outperformed the tested gated and feature-wise linear modulation fusion variants. Conformal-style prediction sets revealed substantial endpoint-specific variation in set efficiency, and discrimination and calibration improved with similarity to the training domain. Retraining on fixed published Tox21 Challenge and TDA folds produced competitive, but not uniformly state-of-the-art, performance. SHAP-guided occlusion and consensus subgraph mining yielded model-derived structural hypotheses, 44 of which contained at least one occurrence that passed the predefined counterfactual criteria.
Read the full abstract ▾
Computer Vision
HorizonNet for visual terrain navigation
Bertil Grelsson, Andreas Robinson, Michael Felsberg et al. (+1 more)
This paper investigates the problem of position estimation of unmanned surface vessels (USVs) operating in coastal areas or in the archipelago. We propose a position estimation method where the horizon line is extracted in a 360 degree panoramic image around the USV. We design a CNN architecture to determine an approximate horizon line in the image and implicitly determine the camera orientation (the pitch and roll angles). The panoramic image is warped to compensate for the camera orientation and to generate an image from an approximately level camera. A second CNN architecture is designed to extract the pixelwise horizon line in the warped image. The extracted horizon line is correlated with digital elevation model (DEM) data in the
Fourier domain using a MOSSE correlation filter. Finally, we determine the location of the maximum correlation score over the search area to estimate the position of the USV. Comprehensive experiments are performed in a field trial in the archipelago. Our approach provides promising results by achieving position estimates with GPS-level accuracy.
Read the full abstract ▾
All authors Bertil Grelsson, Andreas Robinson, Michael Felsberg, Fahad Shahbaz Khan
Numerical Analysis
A Barrier-Regularized Symmetric Nitsche Method for the Signorini Problem
Peter Hansbo and Mats G. Larson
We introduce and analyze a barrier-regularized symmetric Nitsche method for the scalar Signorini problem. Applying a logarithmic barrier to the nonnegative slack variable in an augmented Lagrangian and then eliminating that variable yields a smooth positive-part operator and the perturbed complementarity relation on a primal-dual central path, with barrier parameter $\mu=\gamma s$. For every $s>0$, the discrete problem is continuously differentiable, uniquely solvable, and has a symmetric positive definite Newton
matrix when the Nitsche parameter is sufficiently large. Under a mild barrier-feasibility condition, the continuous logarithmic energy has a unique minimizer $u_\mu$ for every $\mu>0$, its gap is positive almost everywhere, and $\|u-u_\mu\|_{H^1(\Omega)}\lesssim\mu^{1/2}$. Under the Sobolev regularity used for finite element approximation, this minimizer satisfies the \(L^2\) central-path boundary law. If the obstacle is locally the trace of an $H^2$-function, we also prove a uniform local $H^2$ bound in the interior of each planar contact face, on neighborhoods that may contain a free-boundary point of the limiting Signorini solution. The method is exactly consistent and quasi-optimal relative to $u_\mu$, with constants independent of $s$. If $u_\mu$ is uniformly bounded in $H^r(\Omega)$, $3/2<r\leq k+1$, then $\|u-u_h\|_{H^1(\Omega)}\lesssim h^{r-1}\|u_\mu\|_{H^r(\Omega)}+\mu^{1/2}$; hence the sufficient balance $s\lesssim h^{2r-1}$ preserves the available energy-norm rate. We also derive rates for discrete penetration and the complementarity residual. Numerical experiments with $P_1$ and $P_2$ elements on structured and unstructured meshes support the predicted rates and the local Newton theory, while showing that a rate-preserving smoothing may still resolve the contact set poorly.
Read the full abstract ▾
Computation and Language
Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering
Jueun Kim, Sungho Park and Wook-Shin Han
A central bottleneck in multi-hop Question Answering (QA) is that the granularity at which a question is expressed often differs from the granularity at which corpus evidence is retrievable. Existing methods address this mismatch by imposing fixed graph structures over the corpus, by iteratively reformulating the query, or by executing a generated program over it, but these strategies do not explicitly decide when a query unit is already supported by evidence and when it should be refined. We formulate this bottleneck as retrievable granularity discovery and introduce Hi-Q, an evidence-conditioned framework for hierarchical query refinement. At each query node, a resolution operator tests whether retrieved evidence supports the current query unit; resolved nodes terminate, while unresolved nodes are expanded by a dependency-preserving binary operator and checked by a semantic coverage verifier. Hi-Q therefore grows a query tree whose
topology is determined by corpus support signals rather than by a fixed decomposition template or a pre-built graph. We evaluate Hi-Q on three multi-hop QA
benchmarks, primarily under full-corpus
retrieval, where dependent evidence must be located among open-domain distractors rather than within a small annotated pool. In this setting Hi-Q reaches 52.3 EM and 64.0 F1 averaged over the three
benchmarks, ahead of the iterative
retrieval baseline IRCoT by 15.1 EM / 18.2 F1 on that same average, and ahead of the graph-based RAG baseline PropRAG by 11.5 EM / 12.0 F1 on MuSiQue-full, without corpus-wide graph construction. In the restricted supporting/distractor setting used by prior work, Hi-Q likewise attains the best accuracy, with 57.9 EM and 69.3 F1 on average, ahead of PropRAG by 5.6 EM / 3.9 F1 and IRCoT by 13.7 EM / 15.8 F1. The project page is available at https://hi-q-project.github.io/.
Read the full abstract ▾
Computer Vision
Beyond Accuracy: Quantifying Pulmonary Attribution in Anatomy-Guided Chest X-Ray Classification Under Domain Shift
Abdullah Al Mamun, Md. Nasif Osman Khansur, Md Ashraful Hossen Akash et al. (+2 more)
Deep-learning models can achieve strong chest X-ray (CXR) classification performance without establishing whether their predictions predominantly rely on pulmonary image content. This study evaluates pulmonary attribution containment as an anatomy-related reliability property distinct from diagnostic performance. We propose DBCA-SegNet-MGAP, a multi-task anatomy-guided CNN-
Transformer framework that combines complementary feature representations through bidirectional cross-backbone
attention, predicts a soft lung mask, and incorporates this anatomical prior directly into classification through Mask-Guided Adaptive Global Average Pooling (MGAP). Pulmonary attribution containment is quantified using the Anatomical Local Energy Ratio (ALR) and high-intensity cumulative ALR (cALR@0.9). Experiments were repeated across three training seeds using the COVID-19 Radiography Database for four-class internal testing and a locked Shenzhen-to-Montgomery protocol for zero-shot external tuberculosis testing. On COVID-19, the proposed model achieved a weighted F1 of $0.9615 \pm 0.0015$ and macro ROC-AUC of $0.9906 \pm 0.0007$. In an architecture-matched dual-bridge comparison, replacing conventional GAP with MGAP increased ALR from $0.3878 \pm 0.0098$ to $0.7086 \pm 0.0104$ and cALR@0.9 from $0.5265 \pm 0.0101$ to $0.9905 \pm 0.0018$, while weighted F1 remained essentially unchanged ($0.9618 \pm 0.0015$ vs. $0.9615 \pm 0.0015$). Under locked external transfer to Montgomery, ROC-AUC remained $0.9080 \pm 0.0043$ and pulmonary ALR remained $0.6466 \pm 0.0081$, whereas weighted F1 decreased to $0.7528 \pm 0.0080$ and ECE increased to $0.1683 \pm 0.0055$. These findings show that diagnostic discrimination, calibration, and pulmonary attribution containment are distinct model properties and support their joint evaluation under internal testing and external domain shift.
Read the full abstract ▾
All authors Abdullah Al Mamun, Md. Nasif Osman Khansur, Md Ashraful Hossen Akash, Md. Kishor Morol, Tze Hui Liew
Artificial Intelligence
CHASE: How Content Ecosystems Are Reshaped When Ranking Is the Only Target
Qianwen Gao, Zichang Su, Yiwen Hou et al. (+2 more)
Generative Engine Optimization (GEO) is increasingly used to improve content visibility in LLM-based
retrieval systems, yet its population-level effects under repeated optimization remain poorly understood. We introduce Content Homogenization under rAnking Signal Exploitation (CHASE), a controlled simulation framework for studying how content ecosystems are reshaped when creators repeatedly adapt documents to an LLM ranking signal. We use ranking as a proxy for source visibility and validate this abstraction against citations in grounded generated responses, obtaining a rank-citation AUC of 0.853 $\pm$ 0.093 across six domains. CHASE then iterates ranking, feature discrimination, rewriting, and evaluation over 20 rounds across different domains. Quality-ranking
alignment decreases in all six domains: from R0 to R20, the change in Spearman's rho ranges from -0.107 to -0.018, with a mean change of -0.068, which means documents closer to the ranking feature profile become less aligned with independently judged document quality over the simulation horizon. A random-target control has shown that it is associated with adaptation toward ranking-derived incentives rather than iterative rewriting alone. The resulting ecosystem dynamics are strongly domain-dependent. Together, these findings show how repeated optimization against a fixed LLM ranking signal can reshape both content populations and the incentives faced by content creators.
Read the full abstract ▾
All authors Qianwen Gao, Zichang Su, Yiwen Hou, Arlen Kumar, Leanid Palkhouski
Databases
Strengthening LargeRDFBench for Interoperable Federated SPARQL Evaluation
Bryan-Elliott Tam, Muhammad Saleem and Ruben Taelman
LargeRDFBench is one of the most comprehensive
benchmarks for evaluating
federated SPARQL query engines, combining real, interlinked
datasets with a rich query suite that has made it a reference point for the community. Evaluations of
federated engines are published by comparing engine results against the
benchmark's expected results, so those expected results must themselves be reproducible. Moreover, several of its data dumps violate the RDF specifications, so only engines that parse RDF leniently can host them, and its expected results are distributed in an ad hoc format. We identify, categorize and repair these data-quality issues with a reproducible cleaning pipeline, producing standards-conformant serializations of every affected
dataset. Furthermore, we re-encode the
benchmark's expected results in the W3C SPARQL 1.1 Query Results JSON Format and correct their discrepancies. Every
dataset now parses under strict RDF parsers, and the expected results are machine-verifiable through a standard format, extending the
benchmark's reach to the full range of conformant engines while staying faithful to the original data. Reproducing the expected results end-to-end with an independent implementation uncovers corruption in the published reference, and discrepancies between our results and the original ones, some not trivial to resolve, others open questions. We further perform a preliminary comparison, not previously explored, of ASK- and COUNT-based source selection in the FedX
algorithm. This work strengthens an already valuable community resource by aligning its artifacts with the RDF standards, broadening the set of engines that can be fairly and reproducibly compared. We also raise the question of how the results of
federated queries under automatic source selection can be made reproducible.
Read the full abstract ▾
Computation and Language
More Capable, Less Faithful: A Multilingual Analysis of Mathematical (Un)Solvability Detection in LLMs
Maria-Eleni Zoumpoulidi, Nikolaos Xiros and Georgios Paraskevopoulos
Solvability detection is one of the most challenging aspects of mathematical
reasoning for Large
Language Models (LLMs). While prior work has studied this capability extensively, these analyses have been limited to English. Consequently, it remains unclear whether
multilingual failures arise from differences in internal Solvability Belief or from
language-dependent failures to express it. To address this gap, we introduce the first
multilingual benchmark of paired solvable and unsolvable mathematical problems, extending ReliableMath to French and Greek. Using this, we train
multilingual probes predicting Solvability Belief and analyze the solvability detection capabilities of state-of-the-art LLMs behaviorally, representationally, and in terms of faithfulness. We find that Solvability Belief is encoded as a largely universal,
language-agnostic feature, and that higher-resource
languages such as English, despite achieving stronger mathematical
reasoning performance, exhibit lower solvability-detection faithfulness.
Read the full abstract ▾
Computation and Language
Enhancing Low-Resource Language Reasoning via High-Resource Language Feature Transfer
Minju Song, Hyeon Hwang, Junhyun Lee et al. (+1 more)
Large
language models exhibit substantial performance variation across
languages, even when solving semantically equivalent tasks. Existing analyses often treat this phenomenon as an observational disparity caused by differences in pretraining data, tokenization, or
benchmark coverage. We study a complementary hypothesis: high-resource
languages (HRLs) may more reliably elicit latent computations useful for task-specific (i.e. mathematical)
reasoning, while lower-resource
languages (LRLs) may under-activate those computations despite expressing the same task. To test this hypothesis, we introduce a mechanistic intervention framework for identifying and transferring task-relevant sparse latent features across
languages. Using sparse autoencoders over residual-stream activations, we isolate features enriched in successful HRL task-specific
reasoning while filtering out source-
language and generic-generation features. We then construct steering directions from these features and inject them during LRL inference. The resulting interventions test whether the selected features are functionally involved in the observed
reasoning gap: suppressing them should impair source-
language reasoning, while activating them should partially recover target-
language reasoning beyond random and non-task controls. Our framework reframes some cross-lingual
reasoning gaps as failures of mechanism elicitation rather than capability absence, and offers a causally testable route to feature-mediated transfer without translation, fine-tuning, or changing the user-facing
language.
Read the full abstract ▾
All authors Minju Song, Hyeon Hwang, Junhyun Lee, Jaewoo Kang
Computation and Language
From Final Artifacts to Trajectories: Retrospective Process Supervision for Evidence-Grounded Long-Form Generation
Junjie Huang, Jiarui Qin, Di Yin et al. (+4 more)
Trajectory data is getting more vital for training large
language models for boosting the agentic abilities. Unlike the verifiable domains such as coding or mathematics, scaling trajectory data for open-ended tasks is much more difficult because these tasks lack singular ground truth and are costly to annotate or verify. In this paper, we propose RetroGen, a self-improving framework of retrospective process supervision. Our key observation is that although expert trajectories are scarce, high-quality final artifacts such as literature reviews, analyst reports and legal judgments, are abundant in pre-training data and can be viewed as compressed traces of the evidence-seeking processes that produced them. RetroGen reconstructs candidate latent trajectories from expert artifacts, verifies them against both the artifact and supporting evidence, and trains models on their own successful reconstruction data, without requiring trajectory data from stronger models. Experiments show that RetroGen improves grounding, faithful synthesis, and long-form evidence-seeking
agent tasks.
Read the full abstract ▾
All authors Junjie Huang, Jiarui Qin, Di Yin, Weiwen Liu, Yong Yu, Xing Sun, Weinan Zhang
Computer Vision
Federated Multi-Task Learning for Bladder Tumor Segmentation and MIBC Classification Using a Hybrid CNN-Transformer Architecture
Malhar Udmale, Divyanshu Dwivedi, Aarohi Dhand et al. (+3 more)
Accurate bladder tumor
segmentation and assessment of mus- cle invasion from T2-weighted MRI are important for treatment plan- ning, but developing robust models across institutions is challenging be- cause patient data cannot be centrally pooled and imaging characteristics vary across scanners and acquisition protocols. We propose a
federated multi-task learning framework for joint bladder tumor
segmentation and MIBC/NMIBC classification across four clinical centers. The proposed Swin Hybrid model combines a ResNet-34 branch for local texture and boundary information with a Swin-Tiny
Transformer for global anatomi- cal context. A
segmentation-guided classification mechanism further uses tumor localization information to support MIBC prediction. We also investigate several augmentation strategies under both centralized and
federated training to improve robustness to multi-center variability. Ex- periments on the FedBCa
dataset show that the Swin Hybrid provides the best overall balance between
segmentation and classification among the evaluated architectures. Under
federated training, Geo+Elastic aug- mentation achieved a DSC of 0.8100 and a patient-level AUC of 0.8931, yielding the highest combined score of 0.8474. These results demonstrate that joint
segmentation and classification can be effectively performed across multiple institutions using
federated training without centralizing patient data.
Read the full abstract ▾
All authors Malhar Udmale, Divyanshu Dwivedi, Aarohi Dhand, Sachin Dudda Nagaraju, Mayank Rai, Bagesh Kumar
Machine Learning
Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry
Jiani Guo, Junjie Wang, Jie Wu et al. (+5 more)
Multimodal geometry
reasoning requires VLMs to extract precise visual relations and preserve them through multi-step deduction. Existing free-form traces obscure the decisions that determine the answer, and trajectory-level reinforcement learning distributes a single terminal signal across the entire response. We introduce credit-addressable
reasoning, in which the semantic units exposed during inference also define where learning compares alternatives and assigns credit. We instantiate this principle with Code-CoT, which retains the diagram, represents visual relations as line-addressable executable code, and organizes
reasoning into typed events, and CE-GRPO, which selects event boundaries using structural priors and type-normalized
entropy, samples complete continuations from shared prefixes, and converts outcome differences into localized advantages. Across nine geometry
benchmarks, CE-GRPO achieves an average accuracy of 76.04, outperforming Qwen3-VL-8B and trajectory-level GRPO by $8.09$ and 3.43 points, respectively. Its relative advantage increases with the number of intermediate events, demonstrating the value of representation–optimization co-design for long, dependency-heavy
multimodal reasoning.
Read the full abstract ▾
All authors Jiani Guo, Junjie Wang, Jie Wu, Pengxiang Zhao, Dongdong Zhang, Shaohan Huang, Yujiu Yang, Furu Wei
Machine Learning
Self-Supervised Pretext Tasks for Infant Cry Analysis: A Controlled Comparison and a Cautionary Result on Donateacry
Luigi Simeone
We compare six self-supervised pretext tasks for infant cry analysis under a fixed budget, meaning the same compact encoder of 1.17M parameters, the same 115 hours of license-verified public pretraining audio, and the same evaluation protocol for every candidate. On cry detection the reconstructive objectives dominate, and a linear probe over a masked-spectrogram encoder reaches 0.988 AUC with subject-wise splits even though the encoder never observed a cry during pretraining. On cry-reason classification over donateacry, the de facto public
benchmark for cry reasons, every encoder performs at chance (0.38 to 0.54 macro AUC over 5 classes), and neither domain adaptation on 1.8 hours of real cries nor end-to-end fine-tuning moves the result. Since a frozen HuBERT-base with 80 times more parameters shows the same pattern, the bottleneck must sit in the labels and not in model capacity. We then reproduce the 90%+ accuracies of the donateacry literature on our own system by changing nothing but the evaluation protocol: clip-wise splits raise accuracy to 85.2% (barely above the 83.8% majority-class baseline), and applying augmentation before splitting raises it to 97.9%, matching the reported state of the art, from the same model that measures 0.49 macro AUC under subject-wise splits. Under leakage-free splits, a twentyfold augmentation of the labeled set (vocoder speaker perturbation and noise mixing, 21 hours) leaves cross-subject AUC unchanged: for this task the effective sample size is the number of infants. We release code, seeds and per-clip license manifests.
Read the full abstract ▾
Information Theory
Marker-Delimited Codes for Short-Blocklength, High-Rate Coding over Multi-Read Edit Channels
Sinan Ates Yercan, Marc Antonini and Serge Kas Hanna
The read process of DNA-based data storage systems generates multiple noisy copies of the stored DNA sequences, affected by edit errors consisting of substitutions, deletions, and insertions. Motivated by the challenge of ensuring reliable data
retrieval in the presence of edit errors, we present a concatenated coding scheme that accounts for practical design constraints in DNA storage. We introduce and apply the marker-delimited code (MDC) as the inner code, which enables fast and reliable computation of symbolwise a posteriori probabilities (APPs). We combine MDC with an outer LDPC code. The LDPC is decoded via belief propagation using the soft information generated by MDC. Our results show that, in comparison with prior work, this construction provides more efficient error correction over multi-read edit channels in the short-blocklength and high-rate regime.
Read the full abstract ▾
Computer Vision
SeqAlign3DVG: A Sequence-Aligned Benchmark and Voxel Reasoning Framework for 3D Visual Grounding
Yi Zhang, Yi Wang, Yueting Wu et al. (+3 more)
Image-based 3D visual grounding is critical for
embodied agents, yet existing
benchmarks suffer from loose text-observation
alignment and neglect temporal ordering. We introduce SeqAlign3DVG, a novel
benchmark dedicated to temporally ordered and strictly observation-aligned image-based 3D visual grounding. Unlike prior works using order-agnostic views or global point clouds, SeqAlign3DVG ensures all expressions are human-verified and strictly grounded in the provided RGB observations (single frames or ordered observation sequences). It comprises 9,622 single-view and 14,493 sequence samples featuring rich descriptions, complex relations, and multi-instance ambiguities. To tackle this
benchmark, we propose a unified voxel-based pipeline featuring Relevance-Ordered Voxel
Memory (ROVM) and Progressive
Language-Voxel Fusion (PLVF). ROVM dynamically ranks and aggregates multi-view evidence via a conservative
memory to mitigate noisy observations, while PLVF performs coarse-to-fine spatial-linguistic
reasoning for precise disambiguation. Our approach achieves state-of-the-art performance under the depth-free protocol, significantly improving localization for targets defined by complex relations and appearance cues.
Read the full abstract ▾
All authors Yi Zhang, Yi Wang, Yueting Wu, Kaiyue Yang, Yuejiao Su, Lap-Pui Chau
Computer Vision
FlowVVTON: Flow-Guided Mask-Free Video Virtual Try-On
Shengyao Chen, Xianbing Sun, Liqing Zhang et al. (+1 more)
Video virtual try-on aims to transfer a target garment onto a moving person across
video frames. Current methods rely on human parsing masks or pose keypoints that frequently fail under large motions and occlusions, causing boundary artifacts and temporal inconsistency. A further limitation is that most approaches rely solely on
attention mechanisms for temporal modeling, providing no explicit motion supervision. We propose FlowVVTON, a mask-free framework that eliminates parsing mask dependency entirely. Optical flow is used solely as a training-time supervision signal: a flow-warped latent loss, applied across all layers of the generation model, enforces multi-scale temporal consistency by aligning adjacent-frame features under explicit physical motion constraints. A two-stage training strategy establishes mask-free spatial
alignment before introducing flow-guided temporal supervision. Experiments on TikTokDress show that FlowVVTON outperforms baselines by substantial margins, particularly in temporal consistency (5.7$\times$ VFID-R improvement over SwiftTry), while requiring no
segmentation masks, pose keypoints, or region annotations at any stage.
Read the full abstract ▾
All authors Shengyao Chen, Xianbing Sun, Liqing Zhang, Jianfu Zhang
Machine Learning
PRIME: Mitigating Subgroup Optimization Competition in Shared CTR Top Networks with Plug-in Residual Input-Conditioned Mixture of Expert
Heng Yao, Siyun Hou, Tianying Liu et al. (+8 more)
Click-through rate (CTR) models vary in feature-interaction design, yet their top networks usually remain a single multilayer perceptron shared by all examples. Heterogeneous user, item, and context subgroups therefore update the same parameters; weakly aligned learning signals make the aggregate gradient a compromise among competing directions. We study the competition on Avazu with 4 models and 4 semantic fields. Across all architectures, semantic subgroups show lower Top-NN gradient cosine similarity than random groups matched by sample size and label ratio, with reductions of 0.23-0.37. This competition motivates input-conditioned experts, but directly replacing an established Dense mapping changes its initial function, sharing pattern, and capacity, obscuring the source of gains. We introduce
PRIME (Plug-in Residual Input-conditioned Mixture of Experts), a Dense-anchored mixture of low-rank residual experts.
PRIME anchors the original prediction and uses zero-residual initialization to match the Dense baseline exactly at training onset. Input-dependent routing weights low-rank experts for example-specific logit corrections; multi-bag aggregation and EMA load biases stabilize conditional estimation. We evaluate
PRIME on held-out Avazu and Criteo test sets across 13 CTR architectures and five paired seeds. Median paired AUC gains are +0.0022 and +0.0066, with LogLoss reductions of 0.0011 and 0.0081, respectively. On FiBiNET and DCNv2,
PRIME outperforms APG in all ten seed-level AUC comparisons while using fewer parameters and lower inference latency on both backbones. These results show that function-preserving conditional residuals add input-dependent capacity while preserving the Dense path and its optimization stability. Code is available at https://github.com/YH-learning/
PRIME.
Read the full abstract ▾
All authors Heng Yao, Siyun Hou, Tianying Liu, Yulou Shu, Yong He, Chuan Yuan, Kaibin Qiu, Guowei Chen, Jiayu Zhao, Chao Yu, Ke Ding
Machine Learning · Cross-listed from q-fin.PM
End-to-End Neural Shrinkage of Indefinite Pairwise Correlation Matrices for Small-Cap-Inclusive Portfolios
Christian Bongiorno and Lorenzo Villassero
Small-cap-inclusive equity universes contain recently listed and intermittently traded securities, so enforcing a common look-back discards a substantial fraction of the available information. Pairwise-complete estimation preserves the longest overlap for each asset pair, but the resulting correlation
matrix can be indefinite because its entries are computed on different samples. This prevents direct use in Markowitz optimization and falls outside the assumptions of standard random-
matrix shrinkage. We adapt a rotation-invariant neural covariance
estimator to this setting. The model computes mask-aware marginal moments and a pairwise correlation
matrix proxy, processes its signed spectrum, and uses a bidirectional gated recurrent unit conditioned on factor-aligned effective sample lengths derived from the overlap
matrix and eigenvector loadings. It maps all
eigenvalues, including negative ones, to a positive inverse spectrum. The reconstructed covariance is positive definite and is trained end-to-end to minimize five-day realized global-minimum-variance risk. We evaluate 26 expanding-window models from 2000 to 2025 on up to 1,500 U.S. equities in a closing-auction simulator with point-in-time selection, commissions, financing, corporate actions, and
market impact. Across the 26-year out-of-sample period, the neural
estimator reduces annualized five-day
volatility by approximately 20% and increases the Sharpe ratio by approximately 40% relative to the next-best covariance
estimator. These improvements are consistent across realized risk, risk-adjusted performance, and drawdown control, remain after the modeled execution frictions, and are supported by a 99.9% Model Confidence Set that retains only the neural
estimator.
Read the full abstract ▾
Hardware Architecture
Non-uniform Memory Partitioning For Low-Power Spiking Neural Networks
Simon Richter, Darío Fernández Khatiboun, Maryam Sadeghi et al. (+2 more)
Spiking Neural Networks (SNNs) naturally excel in processing temporally rich and sparse data. However, because of their time-stepped processing,
memory access, specifically to synaptic weights stored in SRAM (static random-access
memory), tends to dominate total power consumption. To address this issue, without incurring a large area overhead, we propose to leverage the greatly varying average firing rate of
neurons in the network to efficiently allocate synaptic weights to an on-chip
memory consisting of multiple non-uniformly sized
memory banks. By assigning weights of frequently firing
neurons to shallow, low-access cost
memory and less actively accessed weights to deeper, high-density
memories, the average power consumption of the synaptic weight
memory is decreased without incurring a large area overhead. To
benchmark our proposed architecture and find optimal configurations of
memory arrangements, we perform an automatic exploration based on application requirements and hardware constraints. For
memory designs synthesized in 28-nm CMOS technology, we show that our architecture can achieve a synaptic weight
memory access power reduction of up to 61% compared to a conventional design, with a 2.1$\times$ lower area overhead, as compared to a traditional uniformly partitioned
memory bank that achieves a comparable reduction.
Read the full abstract ▾
All authors Simon Richter, Darío Fernández Khatiboun, Maryam Sadeghi, Milad Zamani, Farshad Moradi
Machine Learning
Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient Registry
Kihun Rhee
Recent offline reinforcement learning (RL) studies report policies that outperform physician decisions on clinical outcomes. We conduct a systematic, partially crossed evaluation of five offline RL
algorithm families and 14 reward designs in 44,894 post-2018 acute ischemic stroke patients from a nationwide registry (N = 129,033). Standard Fitted Q-Evaluation (FQE) yields an apparent policy-improvement estimate of +0.0069; adding an Early Neurological Deterioration penalty increases it to +0.0101. We identify reward-embedded confounding, in which a proxy terminal reward encodes baseline severity and prognosis as well as treatment efficacy. A 2 x 2 factorial analysis finds that terminal reward confounding accounts for 218.6% of the observed signal change, so its removal overshoots the null. After DML-inspired GBM reward residualization, the FQE estimate attenuates to +0.0033 (p = 0.132), and full deconfounding yields +0.0025 (p = 0.291). FQE-based diagnostics, T-learner analyses, and direct recurrence analyses converge away from a clinically meaningful aggregate improvement. A 1-year mRS factorial analysis replicates the attenuation. We provide an empirically motivated six-step evaluation checklist. NIHSS-stratified heterogeneity is hypothesis-generating for prospective trial design; hospital-level disagreement does not persist after full reward deconfounding.
Read the full abstract ▾
Cryptography and Security
ECLIPSE: Self-Evolving Stealthy Prompt Injection Attack against Long-Horizon Agentic Systems
Shiqian Zhao, Yangfan Zhou, Xinfeng Li et al. (+5 more)
Recently, large
language model (LLM)
agents, such as Codex, Claude Code, and OpenClaw, have become capable of planning and executing long-horizon tasks through repeated tool calls. This capability also creates new opportunities for
prompt injection. Existing attacks either place the malicious objective in one explicit instruction, making it easy to detect, or distribute the intent across multiple execution stages, making successful completion unreliable. In this work, we propose ECLIPSE, a self-evolving and stealthy
prompt-injection framework for long-horizon agentic systems. ECLIPSE combines direct user-
prompt injection with indirect tool-side injection through two components. On the one hand, Stealthy Attack Trajectory Synthesis uses a sandbox to generate and iteratively verify candidate tool chains, then renders a verified chain as a natural one-shot
prompt to serve as the direct instruction. Then, Tool-Chain Steering transfers this plan to the target environment through Static Workflow Encoding (SWE), which embeds state-transition cues in target-tool descriptions, and Dynamic Trajectory Correction (DTC), which supplies corrective signals when execution deviates from the planned chain. To enable systematic evaluation, we further introduce LASE-Bench, a long-horizon
agent-safety
benchmark with 120 malicious tasks and 198 unique tools; 96.7% of its tasks make at least five tool calls. The experimental results show that ECLIPSE is highly effective: it achieves up to 96.7% attack success without defense and 69.2% under the common safety filter, exceeding the strongest baseline by 27.5% in the defended setting. Evaluations against representative defenses further show that existing safeguards do not reliably defend it, which raises the need for more effective defenses.
Read the full abstract ▾
All authors Shiqian Zhao, Yangfan Zhou, Xinfeng Li, Runyi Hu, Yechao Zhang, Yi Xie, Tianwei Zhang, Luu Anh Tuan
Neural and Evolutionary Computing
Event-Driven Language Models with Sparse Neural Activity for Neuromorphic Hardware
Simon Richter, Ruhai Lin, Jason Yik et al. (+4 more)
Inference with
transformer-based large
language models (LLMs) is often limited by the
memory-bound KV cache and quadratic
attention cost. State-space models (SSMs) mitigate this through linear
attention and fixed-size recurrent states, but their large dense linear projections remain computationally expensive even after quantization. We introduce a method that induces sparse neural activity in heavily quantized linear-
attention models with minimal performance loss. Activations below a per-projection trainable threshold ($\pm \Delta$) are nullified while preserving crucial outliers, achieving comparable performance to dense models with up to 4$\times$ fewer effective arithmetic operations. Targeting a multi-core, multi-chip neuromorphic platform, where event-driven execution converts unstructured sparsity into throughput at both the compute and communication levels, a capability GPU architectures fundamentally lack, we project up to 37$\times$ higher throughput and 16$\times$ lower power versus edge GPU inference of a comparable
transformer-based model, and up to 5.4$\times$ improvements over the non-sparsified baseline. These results position sparse, quantized linear-
attention models as a natural fit for deploying LLMs on event-driven multi-core platforms.
Read the full abstract ▾
All authors Simon Richter, Ruhai Lin, Jason Yik, Taylor Kergan, Rui-Jie Zhu, Farshad Moradi, Jason Eshraghian
Computation and Language
Graph Evidence Is Not Enough: Diagnosing Native Decoder Use in Graph-Augmented LLMs
Xiaoyu Guo, Pengcheng Chen, Jiong Yu et al. (+3 more)
Graph-augmented large
language models often assume that graph evidence produced by external computation and placed in the input can be used by the native decoder. We test this assumption with HopQA, a deliberately bounded diagnostic that asks for the shortest-hop distance between two query nodes. Because the answer is a small integer and the target is purely topological, failure cannot be dismissed as open-ended generation or ambiguous evaluation. Yet existing graph-augmented baselines still fail on this setting, showing that providing graph evidence is not the same as making it usable. We introduce an intervention triangle with three matched conditions: readable graph evidence, shuffled graph evidence, and no-graph input. This separates evidence inclusion, structural readability, and decoder-usable
topology. Guided by this diagnosis, we present S$^2$GE as an instance showing that diagnosis-driven interface design can improve native decoder usability. S$^2$GE uses query-aware sampling, endpoint and proximity-based ordering, and structure-preserving
alignment. Across DBLP, Biomedical, GoodReads, and PubMed, S$^2$GE achieves strict exact-match scores of $36.5\%$, $57.8\%$, $76.6\%$, and $52.0\%$, improving over the strongest native-generation baseline by $53.5$ points on average. The interventions further reveal harmful-shuffle, shuffle-robust, and no-graph-saturated regimes.
Read the full abstract ▾
All authors Xiaoyu Guo, Pengcheng Chen, Jiong Yu, Yi Lu, Yaohua Wang, Ziyang Li