Robotics
Tracking the Ground: Online Lidar Identification of Robot-Induced Soil Deformation in Agricultural Environments
Tom Montagnon, Johann Laconte, Benoit Thuilot et al. (+2 more)
Agriculture faces many challenges, and robotic systems can play an important role in addressing them by improving the efficiency and sustainability of field operations. Among these challenges, preserving soil health is a critical concern, as vehicle-soil interactions can degrade the soil structure and produce unwanted surface deformation. A key step toward soil-aware robotics is to explicitly account for how vehicle traffic deforms the ground, yet soil state is typically not treated as a variable. We address this gap by proposing a framework to quantify traffic-induced soil deformation and estimate its
evolution online from
lidar observations. The method relies on a reduced-order parametric model that represents the soil behavior via physically interpretable parameters, yielding a continuously updated and observable representation of soil state. Experiments conducted in different soil conditions demonstrate the ability of the approach to capture deformation induced by the
robot. By making soil response measurable and interpretable during operation, the proposed framework establishes a basis for soil-aware robotic operation, in which the estimated state can be exploited to adapt robotic behaviors in order to reduce soil degradation.
Read the full abstract ▾
All authors Tom Montagnon, Johann Laconte, Benoit Thuilot, Wonjae Cho, Roland Lenain
Sound · Cross-listed from eess.AS
OpenEnded: An Open-Response Speech Corpus for Speaking Proficiency Assessment with Human Annotations and ALM Supervision
Yu-Wen Chen, Eric Zhou, Evelyn Ding et al. (+3 more)
The development of automated speaking assessment (ASA) is limited by the scarcity of public
datasets, with most existing work relying on read-aloud
speech, which limits applicability to real-world communication scenarios. In this work, we introduce OpenEnded, a corpus of English practice
speech from Mandarin speakers in open-response tasks. Unlike prior open-response
datasets that provide only holistic proficiency scores, OpenEnded offers utterance-level assessments of accuracy, fluency, and prosody. Approximately 10,000 utterances are collected and annotated using a hybrid framework: 1,000 are manually labeled via multi-rater scoring with discrepancy resolution to form a high-quality test set, while the remaining are pseudo-labeled by an audio
language model (ALM) for training and development sets. We evaluate ALMs and existing ASA models on the OpenEnded test set and introduce VoxPA as an additional baseline. Results show that ALM-generated pseudo-labels improve training over original ALM scoring, while VoxPA achieves the best performance among all baselines.
Read the full abstract ▾
All authors Yu-Wen Chen, Eric Zhou, Evelyn Ding, Tianyi Shen, Zhou Yu, Julia Hirschberg
Distributed Computing
CIDERS: Cloud-Edge LLM Collaborative Learning via Accelerating Personalized Bilevel Optimization
Victor H. Chen, Hairui Yu, Stella K. Chung et al. (+1 more)
Amid the rapid advancement of physical-world intelligence, cloud-edge collaborative large
language models (LLMs) have emerged as a promising roadmap for practical LLM deployment. However, existing cloud-edge paradigms struggle to balance global consensus with local personalization, which fails to satisfy the need for a unified knowledge foundation on the cloud and domain-specific adaptation at the edge. To address this, we introduce, for the first time, a personalized bilevel optimization framework that formalizes cloud-edge LLM collaboration as a dual structure: the upper level optimizes edge-side personalization, while the lower level governs cloud-side knowledge transfer, reaching cloud-edge evolving in coordination. We then propose CIDERS, an efficient solver that decomposes the model into a learnable backbone and a messenger. While the cloud performs knowledge transfer to the learnable backbone, the key lies in
embedding global trajectories into each local personalization step via consensus-variate correction to reconcile personalization with consensus. We provide a comprehensive theoretical analysis, including a
geometric characterization of the local trajectory and a full convergence guarantee, revealing an explicit trade-off structure between personalization and global convergence. Extensive experiments demonstrate that CIDERS consistently outperforms competitive baselines on the compressed edge path, with 3.1x and 1.7x gains on mathematical
reasoning and code generation, respectively, and a 10% relative gain on instruction metrics. Mechanism experiments attribute these gains to early consensus-corrected coordination and task-aware
distillation. Overall, CIDERS offers a viable path toward consensus-guided continuous personalization in cloud-edge LLM systems.
Read the full abstract ▾
All authors Victor H. Chen, Hairui Yu, Stella K. Chung, Hong Yan
Cryptography and Security
CiteShade: Citation Laundering in Multi-Source Retrieval-Augmented Generation and Its Counterfactual Defense
Guo Fuzheng
Retrieval-augmented generation (RAG) grounds a
language model's answers on retrieved external knowledge and returns each answer with citations that identify its sources. Those citations are the user's audit trail: they let a reader verify a claim without trusting the model. Prior security work on RAG asks whether an attacker can corrupt the answer, leaving the citation channel unexplored. We show that this channel is a new and practical attack surface. We propose CiteShade, the first citation laundering attack to RAG, in which an attacker controlling a single source induces a model to produce an attacker-chosen wrong answer and to attribute it to a trusted source that does not support it, while the evidence for the correct answer remains in context. We formulate the attack as an optimization problem, derive three necessary conditions (
retrieval, generation, and citation) and construct sources satisfying them without any instruction. On multi-source multi-hop question answering the attack raises the wrong-answer rate from 0.01 to 0.68, and source deletion confirms the malicious source is the causal driver in every measured case. Vulnerability tracks a model's propensity to cite rather than its scale, reaching CLR 0.84 under explicit instruction and 0.64 with no instruction at all on the most citation-prone model tested. We then show that perplexity filtering and citation-support checking are each insufficient, and propose a counterfactual defense that verifies which source actually drove the answer.
Read the full abstract ▾
Graphics
KaiNinja: Extending Native 3D Generators to the Part Level
Ruihan Yu, Lian Fu, Muyao Niu et al. (+9 more)
Native 3D generators turn one image into a single mesh. TRELLIS.2 and its peers deliver high-fidelity non-watertight geometry with materials, but the output is one fused object, while downstream work such as editing, rigging and simulation operates on part-level assets. A naive idea is to run a 3D
segmentation network on the fused mesh that TRELLIS.2 generates, but such pipelines are slow and bounded by the accuracy of the
segmentation. We want a simple way to extend an existing native 3D generator to the part level. But we face a critical problem: the O-Voxel grid stores one sheet of surface per voxel, so a single volume cannot represent the interface where two parts touch, at any resolution. We introduce a dual-volume representation to solve this problem and put forward KaiNinja, a part-level extension of TRELLIS.2 built on a dual-volume form of its O-Voxel representation. KaiNinja keeps the generation speed and quality of TRELLIS.2 while extending it to the part level, with no mask or segmenter in the pipeline. Its training data come from sources of many kinds, including CAD models and assets authored by an LLM-driven
agent; to our knowledge it is the first 3D generative model trained on
agent-authored part data. Surprisingly, we also find that whole-object fidelity improves over the same backbone fine-tuned on the same
dataset. Against part generation pipelines of different paradigms, it lowers whole-object Chamfer distance by 40% and raises strict part F-score by 16%.
Read the full abstract ▾
All authors Ruihan Yu, Lian Fu, Muyao Niu, Zheng-hui Huang, Yu-Ju Tsai, Sho Kuno, Fengbo Lan, Yonghao Yu, Erwin Wu, Ming-Hsuan Yang, Kaipeng Zhang, Zhixiang Wang
Artificial Intelligence · Cross-listed from stat.ML
Predictive Likelihood Ratios for Language Model Watermark Detection
Li Ma
Keyed watermark detection tests dependence between observed
tokens and pseudorandom variables reconstructed from a secret key. Building on the pivotal framework of Li et al. (2025), we construct predictive likelihood ratios that average over uncertain probability deficits and residual-tail distributions. The aim is robust detection power across alternative specifications without requiring a single signal-strength tuning. A mixture prior combines tail shape and effective width; hierarchical extensions allow within-document variation in deficit or width. The test maximizes prior-averaged power at a fixed size, but is not generally uniformly most powerful or minimax. Under the exact conditional pivot null, normalized predictive alternatives selected before each observation yield a Bayes factor that is also a test martingale: Type I error control is unaffected by alternative misspecification and remains valid under optional stopping. This guarantee does not cover violations of the conditional null, and the interpolated implementation has no certified anytime guarantee. Gumbel marginal likelihoods are evaluated by fixed quadrature. Across the evaluated tail-shape and tail-width alternatives and three horizons, the union-tail mixture has maximum observed Type II error regret .0080, compared with .0962 for the equal-tail mixture, relative to the best tested rule. On temperature-matched outputs from two open models, it improves AUC over the equal-tail baseline in all eight non-saturated model-temperature
cells, although the leading reference score generally has higher AUC. Supplementary experiments show retained power under independent null-like replacement and smaller changes from hierarchical dependence modeling. The evidence supports robustness across the evaluated alternatives, not uniform power guarantees or resistance to arbitrary text edits.
Read the full abstract ▾
Computation and Language
Empathy Is Steerable but Multi-Axial: Mechanism Geometry and Persona Effects in LLMs
JuHeon Ha, Byounghan Lee, Yunseo Choi et al. (+1 more)
Activation steering has been used to control traits such as honesty, refusal, and sycophancy, yet supportive empathy is evaluated along multiple dimensions that need not correspond to independently controllable activation directions. Using the EPITOME framework, which decomposes supportive empathy into Emotional Reactions, Interpretations, and Explorations, we study three instruction-tuned LLMs and ask whether candidate directions derived from these labels produce distinguishable intervention effects or instead share structure, and how persona
prompts interact with those directions. We find that contrastive activation addition yields a stable middle-layer intervention that consistently shifts the EPITOME proxy scores across models, moving empathy analysis beyond response-level scoring. However, the recovered directions are only partially separable: steering one direction induces off-target shifts, and hand-crafted prompting shifts the empathy profile rather than isolating a single dimension. Persona
prompts substantially change EPITOME scores, but a paired activation-shift decomposition shows that the recovered subspace captures only approximately 3 percent of persona-induced squared activation-shift magnitude at layer 15. Under this EPITOME-based definition, expressed empathy is steerable but multi-axial, and controlling persona-conditioned empathy requires targeting structure beyond individual mechanism directions.
Read the full abstract ▾
All authors JuHeon Ha, Byounghan Lee, Yunseo Choi, Kyung-Ah Sohn
Sound
Graph Attention Design Choices Matter: A Controlled Study of LoRA-Adapted Audio Anti-Spoofing
Haoyu Wang, Jing Yang, Chenyu Liu et al. (+7 more)
Audio anti-spoofing systems increasingly combine self-supervised learning, parameter-efficient fine-tuning, and graph-
attention-based backends. However, performance gains in such systems are often entangled with concurrent changes in the backbone, fine-tuning strategy, and training protocol, making the independent contribution of graph
attention design difficult to isolate. To address this issue, we conduct a systematic controlled study of the graph
attention layer under a unified experimental setting. We decompose the layer into three independently testable design dimensions: scoring
symmetry, temperature learnability, and routing granularity. These are instantiated as a concat-based scoring branch, a LearnT branch with learnable temperature, and a multi-temperature routing branch, respectively. Each dimension is implemented as an independently gated residual branch, enabling the evaluation of both individual variants and their combinations under the same experimental setting. Experiments on five evaluation sets with five random seeds show that the LearnT branch achieves the best average equal error rate (EER), yielding a 16.1% relative improvement over the baseline. In contrast, the multi-temperature routing branch does not improve average performance on its own, but substantially reduces cross-seed standard deviation when combined with the concat-based scoring branch. Moreover, two individually effective branches degrade performance when used together, resulting in a 25.6% relative deterioration compared with the baseline. This finding reveals strong non-additive interactions among graph
attention design dimensions. Overall, the results suggest that, under parameter-constrained fine-tuning, improvements in graph
attention layers depend more on capacity allocation and branch interaction than on simply adding more learnable parameters.
Read the full abstract ▾
All authors Haoyu Wang, Jing Yang, Chenyu Liu, Yushan Du, Yifan Liao, Ningning Pan, Gongping Huang, Yu Zhao, Gang Li, Jian Luan
Computer Vision
From Model Patterns to Abstract Semantics in Compositional Zero-Shot Learning
Weize Li, Zhicheng Zhao and Fei Su
Compositional Zero Shot Learning aims to recognize unseen compositions by recombining learned primitives. Recent methods rely on
vision language models and attempt to explicitly model contextual variations of primitives through multiple representations. However, such approaches are limited by fixed variant capacity and competition between abstract and concrete semantics. In this work, we present a new perspective that views primitive variations as the context-driven activation of concrete visual cues rather than independent entities. Based on it, we propose CLEAR, a CLoze-style
rEAsoning-based Re-ranking framework inspired by human perceptual processes. CLEAR extracts conditional variants from the primitive candidate set in a coarse-to-fine manner, performs cloze-style
reasoning to infer high-level semantics, and re-ranks predictions to correct biases toward salient concrete primitives. Extensive experiments demonstrate that CLEAR consistently improves the Base Model and outperforms state-of-the-art methods on the challenging C-GQA and MIT-States
datasets. Code is available at https://github.com/buptLwz/CLEAR.
Read the full abstract ▾
Cryptography and Security
Scaling Verification of Cryptographic Software with Aeneas, Rust, and Lean
Son Ho, Cédric Fournet, Jonathan Protzenko et al. (+7 more)
We develop a new methodology for verifying cryptographic software. We target production code written in Rust for performance and system integration, rather than verification convenience. Rust's ownership discipline enables Aeneas to extract a pure model of this code in Lean, relieving us from low-level
reasoning about pointer liveness and aliasing. Lean's extensibility lets us develop tactics and libraries that greatly simplify
reasoning about extracted Rust code. We design and tune our toolchain to facilitate the use of AI.
Agents autonomously write formal proofs, which are independently verified by the Lean kernel.
Agents also assist in the formalization of cryptographic standards and platform-specific intrinsics, which still requires expert design and review. We apply our methodology to SymCrypt, Microsoft's cryptographic provider. We verify its implementations of
algorithms such as SHA-3 and ML-KEM, which were ported from C to Rust. We also extend SymCrypt with experimental optimizations and implementations of
algorithms such as FrodoKEM, ML-DSA, and HPKE to explore the scalability of writing, adapting, and verifying cryptographic code. Our 237~KLOC Lean development establishes safety, panic-freedom, and functional correctness of 16.7~KLOC of Rust code supporting post-
quantum cipher suites for x86-64 and ARM platforms. Our evaluation shows that verified Rust can meet SymCrypt's performance, portability, deployment, and maintainability requirements.
Read the full abstract ▾
All authors Son Ho, Cédric Fournet, Jonathan Protzenko, Michael Naehrig, Joshua Clune, Patrick Longa, Guillaume Boisseau, Fernando Leal Sánchez, Aymeric Fromherz, Antoine Delignat-Lavaud
Computer Vision
MedDiME: Efficient Latent Diffusion with Adaptive Masking for Medical Counterfactual Generation
Yan Zeng, Changlu Guo, Anders Nymark Christensen et al. (+2 more)
Medical counterfactual generation modifies images to change model predictions for interpretability. However, existing
diffusion-based approaches are often prohibitively slow and
memory-intensive, making them difficult to apply in high-resolution settings. Moreover, existing masking strategies are tightly coupled with pixel-space representations, making them incompatible with latent-space
diffusion editing. To address these challenges, we propose MedDiME, a latent-space classifier-guided
diffusion framework that reduces computational and
memory overhead while introducing a latent-compatible, gradient-driven adaptive masking mechanism for spatially precise medical counterfactual generation. Extensive experiments demonstrate that MedDiME achieves high-quality counterfactual generation with significant efficiency gains compared to prior classifier-guided
diffusion baselines, achieving up to 40 times faster inference and 13 times lower peak GPU
memory usage.
Read the full abstract ▾
All authors Yan Zeng, Changlu Guo, Anders Nymark Christensen, Morten Rieger Hannemose, Anders Bjorholm Dahl
Machine Learning
Principal-timestep Restricted Init via Sparse Matrix-decomposition in Flow-matching
Jiayang Gu, Zheng Fang, Lichaun Xiang et al. (+3 more)
Flow-matching
diffusion models have recently emerged as a strong paradigm for high-fidelity visual generation. However, their prohibitively high fine-tuning cost limits scalability to downstream tasks. While Low-Rank Adaptation (LoRA) combined with spectral initialization has demonstrated accelerated convergence and improved performance in autoregressive
language models by better aligning gradient directions, we find that it fails to deliver similar gains in
diffusion fine-tuning, often yielding marginal or even negative improvements over vanilla LoRA.We attribute this discrepancy to a fundamental mismatch between LoRA's low-rank parameterization and the intrinsically high-rank gradients induced by the flow-matching objective. In particular,
stochastic timestep sampling introduces directionally heterogeneous gradient signals across training steps, leading to misaligned updates under low-rank constraints.To address this issue, we propose Prism-LoRA,a Principal-timestep Restricted Init via Sparse
Matrix-decomposition framework that improves gradient
alignment during fine-tuning. Our method consists of two key components: (i) principal timestep selection, which restricts initialization gradients to a subset of dominant timesteps to suppress effective gradient rank, and (ii) principal channel filtering, which removes task-irrelevant channels, enabling the one-step spectral initialization gradient to better align with the long-horizon optimization trajectory. Extensive experiments demonstrate that our method consistently improves both convergence speed and final performance across multiple
diffusion fine-tuning
benchmarks, including subject-driven generation, controllable generation, and deblurring, achieving not only performance improvement but also earlier stages of convergence over baseline LoRA and other spectral-init methods.
Read the full abstract ▾
All authors Jiayang Gu, Zheng Fang, Lichaun Xiang, Fanghui Liu, Xu Cai, Hongkai Wen
Discrete Mathematics · Cross-listed from math.CO
Protected tails and polynomial-time enumeration of permutations avoiding a direct sum of an increasing pattern and 231
Henning Arnór Skeggi Úlfarsson
We give an
algorithm counting the permutations that avoid a fixed pattern of the following form: the direct sum of an increasing pattern and 231. The first members of the family are 1342 and 12453. For each member the
algorithm uses polynomially many operations and stored integers, with degrees that grow linearly in the length of the pattern. It comes from a recurrence that reads a permutation from left to right and records the constraints that the letters read so far impose on those still unread. This recurrence has exponentially many states, but part of each state is protected: later steps carry it along unchanged and do not depend on it, and factoring the protected part out leaves a dynamic program of
polynomial size. For 12453 a translation
symmetry sharpens the bounds to degree seven for the operations and degree four for the storage. We also compute the number of 12453-avoiding permutations of every length up to 150. The previously published series, due to Biers-Ariel (2019), reached length 38. We also give a sampler of uniformly random avoiders. A floating-point implementation of it, proved to be within total variation distance $3.5\cdot10^{-5}$ of uniform for ideal random bits, draws the one million 12453-avoiding permutations of length 300 shown in a heatmap. The literal and kernel recurrences for 1342 and 12453 are verified in the Lean 4 proof assistant.
Read the full abstract ▾
Computer Vision
Human-Grounded Calibration for Long-Text Image-Text Congruence in Vision-Language Models
Alessandro Gambetti and Qiwei Han
Long-text image–text congruence scoring is increasingly important for
vision-
language systems that must evaluate whether detailed textual descriptions match visual content. However, raw similarity scores from dual-encoder models are difficult to interpret as calibrated congruence measures, especially under the modality gap between image and text
embeddings. This paper proposes Congruency Score (CS), a lightweight calibration layer that maps image–text similarity evidence into a bounded score. Using DOCCI and Urban1k, we evaluate four frozen
vision-
language backbones and show that observed reductions in post-projection centroid distance do not uniformly improve image–text
retrieval performance. Human-grounded evaluations on DOCCI further reveal a trade-off: direct post-hoc calibration preserves high association with human judgments, whereas selected projection-based configurations can reduce threshold-relevant slope and intercept distortions at the cost of
retrieval performance and association strength. These results establish long-text image–text congruence scoring as a calibrated score-estimation problem, where
retrieval performance, human association, and threshold calibration must be evaluated as distinct objectives. CS provides a lightweight way to expose and operationalize this separation.
Read the full abstract ▾
Computer Vision
SAM3D-Part: Interactive Part Selection and Generation from 3D Objects
Jiahao Chang, Dong Du, Wanhu Sun et al. (+6 more)
Part-level control is essential for modern 3D asset creation, where objects are frequently edited, reused, animated, or fabricated through their individual components. In many such workflows, users need only several specific components rather than a complete object decomposition. However, existing 3D generation methods produce all parts regardless of user intent, while promptable 3D
segmentation methods typically output partial surfaces instead of reusable complete meshes. In addition, image-conditioned part generators further struggle to preserve hidden geometry and accurate placement without directly conditioning on the source mesh. To address these problems, we present SAM3D-Part, a
prompt-driven framework for selective part generation from input 3D object meshes. Given a source mesh and a part
prompt, SAM3D-Part first encodes the source geometry into compact mesh features and aligns them with the rendered image, selective mask, and point-map observations via pixel-wise channel fusion. The fused representation conditions a feed-forward generative model to produce only the queried component as a completed mesh. To place the generated part back into the source coordinate frame, SAM3D-Part predicts dense per-voxel correspondences and estimates the part transformation from distributed spatial evidence rather than a single global pose code. For sequential multi-part queries, previously generated parts are stored in a part cache and reused as contextual constraints, reducing conflicts among independently requested components. Extensive experiments and ablations demonstrate that SAM3D-Part can significantly improve source
alignment, reduce conditioning cost, and enable consistent selective part generation, achieving state-of-the-art. Code and weights will be available at https://github.com/Jiahao620/sam3d-part.
Read the full abstract ▾
All authors Jiahao Chang, Dong Du, Wanhu Sun, Yujian Zheng, Chuanyu Pan, Bowen Zhao, Chongjie Ye, Yuanming Hu, Xiaoguang Han
Artificial Intelligence
Potential of Artificial Intelligence Algorithms for Identification of Relevant Diagnostic and Prognostic Biomarkers of Early-Stage Liver Cancer
Ali Bou Nassif, Darko Castven, Manar Abu Talib et al. (+4 more)
This study explores the use of deep learning and explainable artificial intelligence to diagnose hepatocellular carcinoma (HCC) and define effective biomarkers across five different stages of disease development using a transcriptomic biomarker HCC
dataset constructed via semi-supervised learning from three source
datasets. Several deep learning experiments were conducted with different feature extraction techniques and gene sets to identify the most effective features for training high-accuracy models with minimal loss. The best-performing model, using 15 selected genes with the SelectKBest
algorithm, achieved 90.74% accuracy, while the model with the lowest recorded loss of 0.3187 was obtained using 20 selected genes. To address the issue of class imbalance in the
dataset, a weighted training approach was conducted, and for model transparency and interpretability a SHAP-based XAI analysis provided insights into the model's decision-making, consistently finding DNAJB14 as the most influential gene. Functional validation in this study has provided compelling evidence that DNAJB14 plays an important role in the adverse properties of HCC and that its inhibition effectively reverses tumour
cell migration, invasion, colony and sphere formation. The main limitation of this study is the
dataset's class imbalance, and while weighted training helped mitigate this, further research and additional data are needed to guarantee model generalizability. Future studies should also explore the influence of genetic variations, environmental factors, and clinical differences on model performance across diverse populations.
Read the full abstract ▾
All authors Ali Bou Nassif, Darko Castven, Manar Abu Talib, Jibran Sualeh Muhammad, Ahmed Ammar Kubba, Jens Marquardt, Abdalla Sayed Ali
Hardware Architecture
Trillion-Parameter MoE in a Box: Decoupling Memory Provisioning with High-Bandwidth Flash
Pengfei Xia, Tuo Hao, Shengwei Li et al. (+5 more)
An MoE appliance for trillion-parameter models at low concurrency must host terabytes of weights on one node and serve prefill and decode with fixed resources. Combining operator analysis of two trillion-parameter MoE models, a measured expert routing trace, and agentic serving traces over multiple turns, we explore a design space spanning High-Bandwidth Flash (HBF) and DRAM configurations, bandwidth exposure, and near-data compute. We find that state bandwidth and HBF transport form two largely orthogonal knees and address two provisioning questions. Q1: Once weights move to HBF, what bandwidth-to-capacity ratio does DRAM require? With a 256-GB floor for the state tier, both models meet a $1.10\times$ completion time target at ratios of only $1.4$–$4.0~\mathrm{s}^{-1}$, roughly an order of magnitude below HBM3e's $33.3~\mathrm{s}^{-1}$. Q2: As HBF internal bandwidth scales with capacity, must bandwidth to the host scale proportionally? Six HBF packages expose 384~GB/s per package to the host, 2.30~TB/s aggregate and 62.5% below the 6.14~TB/s full exposure reference, while more packages reduce required bandwidth per package at the same target.
Read the full abstract ▾
All authors Pengfei Xia, Tuo Hao, Shengwei Li, Jinjing Chen, Shiru Wei, Wenjun Zou, Rui Zhang, Hui Zang
Computer Vision
ModaLens: Measuring Image Sensitivity in Report-Conditioned Medical VLMs
Sebastián Andrés Cajas Ordóñez, Maximin Lange, Quang Bui et al. (+9 more)
A radiology report can already answer a clinical question, so it is hard to tell whether a
vision-
language model also uses the image. ModaLens, a paired image-swap audit, measures how report availability changes image sensitivity: MedGemma-27B on 3,199 paired MIMIC-CXR cases from 293 patients, all 14 questions per case (13 finding-specific and one composite), each image replaced by one from another study, usually of the same patient, with question and report fixed. Under an explicit answer instruction, the model's generated answer changes on 4.26 percent of trials with the report and 20.94 percent without it, a paired increase of 16.7 points (patient-clustered 95 percent CI 15.6 to 17.7), so report availability reduces image-swap sensitivity under this protocol; the original
prompt with a lowercase first-
token readout gives 4.70 percent against 17.07 percent, and substitutions also move continuous answer scores where the binary prediction does not change. The labels are derived from reports, which limits conclusions about visual correctness; the direction replicates in two further model lineages. Code, the exact
prompts and a run record for every number are at https://github.com/criticaldata/MODALENS.
Read the full abstract ▾
All authors Sebastián Andrés Cajas Ordóñez, Maximin Lange, Quang Bui, Anqi Peter Li, Felipe Ocampo Osorio, Rafi Al Attrach, Kushul Reddy Palakala, Sahil Kapadia, Zakaria Laouabdia Sellami, Xinyue Zhang, Ashley Zhang, Leo Anthony Celi
Robotics
Flow-Matched Motion Priors: Online Optimal-Transport Rewards for Imitation Learning
Yilin Zou, Chenghua Liu, Chenglong Wu et al. (+1 more)
Learning a motion prior requires a reward that guides a policy from its current behavior toward demonstrated motion.
Adversarial Motion Priors (AMP) provide such a reward with a discriminator. However,
adversarial objectives can become uninformative when policy and expert supports are far apart. A naive use of optimal transport (OT) averages matched expert successors into a barycentric target. Averaging across gait phases can weaken the target's joint motion. We introduce Flow-Matched Motion Priors (FMP), an online scalar reward learned from paths connecting current rollout histories to an expert motion bank. Entropic OT supplies the coupling. Before each policy update, we train a neural potential with flow matching (FM) along the rollout-to-expert paths, endpoint-gradient supervision, and relative-value calibration. The actor receives only physical observations and the reward remains a scalar, as in AMP. Controlled reward-model experiments show substantially better generalization beyond the fitting rollout than value-only or endpoint-only fitting. On Unitree G1, matched 50-million-transition experiments compare FMP with AMP, a barycentric OT reward, and nested ablations under demonstration and fixed-pose initialization. FMP produces stable forward walking at 0.727 m/s from demonstration resets and 0.338 m/s from a fixed default pose. In the fixed-pose condition, it incurs 129 falls versus 243 for the endpoint-only control. Against a static score-gradient teacher, dynamic FM reduces score-increment error at interpolation fractions 0.25 and 0.50 while using 29% less offline fitting time.
Read the full abstract ▾
All authors Yilin Zou, Chenghua Liu, Chenglong Wu, Fanghua Jiang
Numerical Analysis
A {\phi}-FEM approach for time-dependent domains with unfitted meshes
Michel Duprez, Johan Marguet, Alexei Lozinski et al. (+1 more)
In this work, we propose an unfitted finite element scheme to approximate the solution of the heat equation on moving domains. We use the {\phi}-FEM paradigm in which the computational domain is described implicitly by a level-set function {\phi}. This function is incorporated into the variational formulation in order to enforce the boundary conditions, which allows the use of unfitted meshes in space. Such a strategy avoids the need for remeshing at each time step and makes it possible to handle complex geometrical evolutions. Moreover, the {\phi}-FEM approach has the advantage of being simple to implement within standard finite element libraries. We introduce a fully discrete scheme that combines the {\phi}-FEM spatial discretization with the lowest-order discontinuous Galerkin method in time. Under regularity assumptions on the level-set function and a mild restriction linking the time step to the mesh size, we establish an optimal a priori error estimate in the L2(0,T;H1) norm. Finally, we present several numerical experiments that confirm this convergence rate, exhibit a second-order convergence in the L{\infty}(0,T;L2) norm, and illustrate the robustness and accuracy of the proposed method.
Read the full abstract ▾
All authors Michel Duprez, Johan Marguet, Alexei Lozinski, Igor Voulis
Distributed Computing
DeepSeek-V4-Flash on AMD gfx90a: Correctness Recovery and Inference Performance Engineering
Siming Huang
We present the enablement, correctness recovery, and performance engineering of DeepSeek-V4-Flash inference on AMD Instinct MI250 GPUs using the gfx90a/CDNA2 architecture. The system integrates native safetensors loading, tensor and expert parallelism, FP4 routed mixture-of-experts computation, FP8 dense projections, sparse
attention, HIP graph execution, and OpenAI-compatible serving within SGLang. An initially fast execution path was found to be numerically incorrect because of a routed-expert W2 layout mismatch. We identify the output permutation, repair the weight layout at load time, and establish fixed-
token and hash-based correctness checks before further optimization. On the corrected path, decode performance is improved through packed FP4 weights, INT8 activation quantization, CDNA2 dot-product instructions, peer-read all-reduce, and
topology-aware kernel geometry. Prefill is accelerated using CDNA2 MFMA kernels, improved packed-weight reuse, reduced sparse-
attention overhead, larger chunks, and retuned expert sorting. On four MI250 GCDs, TP4/EP1 native autoregressive decode reaches approximately 74.5 tok/s, while a 4,604-
token prompt reaches 2.061-2.062 s TTFT, or approximately 2,234 input tok/s. The results show that efficient DeepSeek-V4-Flash inference on CDNA2 is limited not only by
memory bandwidth, but also by FP4 execution-format mismatch, low-M utilization, and per-layer synchronization costs.
Read the full abstract ▾
Machine Learning
FedLTLib: A Comprehensive Benchmark for Federated Long-Tail Learning
Changkun Lin and Junxiao Wang
Driven by the escalating demand for
privacy-preserving computing,
Federated Learning (FL) has witnessed remarkable progress, becoming a cornerstone technology for bridging distributed data silos in mobile edge networks. However, in real-world mobile computing environments, data is generated by heterogeneous mobile devices with varying user behaviors, leading to a significant Long-Tail Distribution. Unlike idealized balanced
datasets, data in the wild manifests an acute imbalance where a minority of head classes dominate the sample space while a vast number of tail classes, often representing rare but critical edge-case events, are extremely scarce. This data heterogeneity, which we formally characterize as "Double Heterogeneity", referring to the superposition of global class imbalance and local statistical skew, precipitates severe performance deterioration on tail classes, thereby spurring the vital research direction of
Federated Long-Tail Learning (FL-LT). To standardize evaluation and accelerate research in this field, we introduce FedLTLib, a comprehensive
benchmark tailored for FL-LT. Addressing the critical issues of inconsistent experimental configurations and unfair comparisons in prior work, FedLTLib establishes a standardized evaluation framework. The platform not only incorporates diverse
benchmark datasets reflecting mobile data characteristics but also implements 13 state-of-the-art FL
algorithms (4 traditional FL
algorithms and 9 FL-LT
algorithms). By leveraging FedLTLib, researchers can perform fair and reproducible evaluations of
algorithm robustness and generalization capabilities under a unified experimental protocol, ultimately advancing the deployment of robust intelligence in mobile computing ecosystems.
Read the full abstract ▾
Human-Computer Interaction
Beyond AI Literacy: A Structured Review and Exploratory Meta-Analysis of Measures for Competent Generative-AI Use
Daniele Veri'
Researchers assessing competent generative-AI use at work must choose among self-reports, objective tests, and measures of oversight and reliance. We conducted a structured, seeded review of 24 focal empirical publications, starting from the 2024 COSMIN-based review and adding a targeted update through 17 August 2026. We grouped the measures into four domains: knowledge and use, epistemic oversight, reliance calibration, and operational control of tool-using
agents. In an exploratory meta-analysis, we pooled three direct subjective-objective correlations from one research program (REML r = .055; Hartung-Knapp 95% CI [-.047, .156]; combined reported N = 2,765). We could not resolve a discrepancy between the largest study's reported correlation and p-value, leaving its weight uncertain. Adding a synthetic mean of 12 cross-factor correlations from a fourth study gave r = .079 (95% CI [-.025, .181]). This sensitivity analysis concerns a broader comparison. From this small evidence base, we cannot establish a population correlation, validate workplace cutoffs, or justify substituting self-ratings for performance scores. We identified tests of foundation knowledge (AICOS-S and GLAT) and measures of verification, reliance, trust, and dependency. We found no validated individual-level instrument in the focal corpus that tests the full combination of
agent scope, permissions, recovery, state isolation, independent review, and evidence-based closure; some cover subsets. We propose a four-layer workplace battery with non-compensatory decision rules, but have not tested its thresholds or whether it improves on other assessment approaches.
Read the full abstract ▾
Systems and Control
MM-LMPC: Multi-Modal Learning Model Predictive Control via Mode-Specific Terminal Design and Bandit-Based Exploration
Wataru Hashimoto, Kazumune Hashimoto and Masako Kishida
Learning Model Predictive Control (LMPC) improves iterative control tasks by using previous executions to construct the terminal constraint and terminal cost of the MPC problem. Although effective, this reuse of past trajectories can make LMPC sensitive to the initial data. In particular, LMPC may repeatedly exploit stored trajectories with favorable cost-to-go values while insufficiently exploring alternative route patterns that could yield lower cost after further improvement. To address this issue, we propose Multi-Modal LMPC (MM-LMPC). The proposed framework clusters past trajectories into motion modes, constructs a mode-specific LMPC controller for each mode, and uses an LCB-based meta-controller to select which mode-specific controller to execute at each iteration. Mode information is incorporated into the terminal constraint and terminal cost through two designs. The hard-constrained design uses mode-specific terminal constraints and terminal costs constructed from the data associated with each mode. The soft-regularized design retains a shared terminal constraint while adding membership-based penalties to the terminal cost. These designs reduce the bias caused by pooling all trajectories into a single terminal
memory while retaining the recursive feasibility and stability structure of LMPC. Our theoretical analysis shows that both designs preserve recursive feasibility and closed-loop stability. For the hard-constrained design, we further establish mode-wise cost convergence, asymptotic best-mode performance, and a logarithmic cumulative regret bound under the LCB rule. Simulations on multi-route obstacle-avoidance tasks show that MM-LMPC improves exploration and achieves lower costs than standard LMPC.
Read the full abstract ▾
Machine Learning
Where to Compute and How to Interact: Operator-Readable Adaptation with Gauge-Aware Transport
Zixuan Shen, Quanxu Wan, Bingchuan Wang et al. (+2 more)
Adaptive meshes enable neural operators for partial differential equations (PDEs) to allocate spatial samples and computation according to local physical structures. Existing approaches, however, mainly address where to compute, with less
attention to how information should interact after node relocation. Mesh adaptation changes local sampling scales, neighborhood structures, and
geometric contexts, so representations formed at different nodes may not be directly comparable. Direct aggregation can therefore entangle physical variation with discretization-induced representation variation. Because allocation and interaction are jointly optimized through the same output objective, their individual roles are also difficult to distinguish from final errors alone. We introduce operator readability, requiring an adaptive operator to account for and test why computation is allocated to particular locations and how representations interact under the resulting nonuniform discretization. Based on this principle, we propose the Gauge-Aware Adaptive Mesh Neural Operator (GA-AMNO). Physics-informed adaptive allocation answers where to compute, while geometry-conditioned low-rank Gauge transport maps source features into target representation contexts before aggregation, answering how to interact. This makes mesh-to-solver information exchange inspectable and intervenable. We establish sufficient conditions for representation-consistent aggregation and analyze approximate transport errors and continuity under
topology-preserving mesh deformations. Experiments on five PDE
benchmarks demonstrate improved predictive accuracy, while controlled interventions and
geometric-mismatch analyses verify the roles of allocation and interaction and show that Gauge transport improves cross-discretization representation compatibility under strong
geometric mismatch.
Read the full abstract ▾
All authors Zixuan Shen, Quanxu Wan, Bingchuan Wang, Zhi Wang, Biao Luo
Information Retrieval
IROH: Insightful Ranking Of Humor using Multi-Stage Hybrid Retrieval with Rationale-Distilled LLM Judges for JOKER 2026 Track Task 1 English
Ana-Maria Luisa Mocanu, Sebastian Mocanu, Ciprian-Octavian Truica et al. (+1 more)
Our team, VANGUARD, presents IROH (Insightful Ranking of Humor), a three-stage
retrieval system for JOKER Task 1 English at CLEF 2026, achieving first place on the leaderboard with 0.6347 MAP. Our pipeline combines hybrid sparse-dense
retrieval, cross-encoder reranking, and a LoRA-adapted Large
Language Model judge ensemble. We employ Gemma 4 to generate query-aware rationales under two
prompt strategies, generic and typed, and produce up to four types of structured hard negatives for training data construction. Through an ablation across three cross-encoder architectures, four dense embedders, and eight judge configurations, our key findings are threefold: (1) the rationale-distilled judge is the primary driver of ranking quality, whereas appending rationales to the first-stage index contributes negligibly; (2) structured hard negatives degrade generalisation in nearly all configurations despite inflating local validation scores; and (3) across the components we ablate, the lighter, better-calibrated model is competitive with or stronger than its larger counterpart, with the generic-rationale Qwen2.5-7B judge (0.6055 MAP) outperforming every Gemma-4-31B configuration, and the advantage of generic over typed rationales is concentrated almost entirely in the smaller model.
Read the full abstract ▾
All authors Ana-Maria Luisa Mocanu, Sebastian Mocanu, Ciprian-Octavian Truica, Elena-Simona Apostol
Cryptography and Security
Tractable Defense against Advanced Persistent Threats in Networked Settings
Brandon Collins, Keith Paarporn, Shouhuai Xu et al. (+1 more)
Recently, the theory of Boolean Dynamical Systems was proposed to study the decision theory surrounding the defense of computer networks against Advanced Persistent Threats (APTs). Boolean Dynamical Systems naturally capture four first principle primitives of APTs: the stealthy nature of attacks, limited and noisy information from automated systems like intrusion detection systems, lateral movement after the attacker penetrates into the network, and the defender's ability to secure a subset of computers at any time at the loss of resources such as system uptime. Currently, doing optimal/heuristic control in a computationally tractable manner is not possible because the emergent value function is computationally intractable (with respect to the network size). To resolve this, we propose a mean-field analysis inspired heuristic value function. We prove that our proposed heuristic is based on an exact computation of the value function under the assumption that the underlying state estimate distribution maximizes
entropy. We numerically evaluate the quality of our heuristic as parameterized by the degree to which the
entropy assumptions are violated.
Read the full abstract ▾
All authors Brandon Collins, Keith Paarporn, Shouhuai Xu, Philip N. Brown
Machine Learning
Multi-View Molecular Representation Learning with Hierarchical Graphs and Contextualized Fingerprints
Gwang-Hyeon Yun, Jong-Hoon Park, Bing Hu et al. (+3 more)
Molecular property prediction requires representations that generalize from limited labeled data to structurally novel compounds. Existing molecular pretraining methods often rely on a single view: graph-based approaches model atom-bond
topology but provide limited fragment-level supervision, whereas fingerprint descriptors encode chemical patterns but are typically used as fixed auxiliary features. We propose HiFi-Mol, a multi-view framework that separately pretrains a hierarchical graph encoder and a contextualized fingerprint encoder before downstream integration. The graph branch uses fragment-aware masking with multi-resolution supervision to capture substructure-aware representations, while the fingerprint branch tokenizes active entries from seven fingerprint families and applies masked
language modeling to learn contextualized
embeddings. During fine-tuning, HiFi-Mol combines projected multi-resolution graph features with fingerprint
embeddings for downstream prediction. Evaluated on MoleculeNet
benchmarks under the scaffold split, HiFi-Mol achieves a 2.77% improvement in average ROC-AUC over the best baseline across eight classification tasks while maintaining competitive performance on three regression tasks. Further analyses reveal that fragment-aware masking improves graph representation quality, and classification results demonstrate
dataset-dependent strengths of the individual graph and fingerprint variants, confirming that the two views provide complementary predictive signals.
Read the full abstract ▾
All authors Gwang-Hyeon Yun, Jong-Hoon Park, Bing Hu, Helen Chen, Anita Layton, Young-Rae Cho
Artificial Intelligence
Diversified and Perceptible Counterfactual Examples Leveraging Expert Knowledge
Akram Bensalem, Fahima Djelil, Marie-Jeanne Lesot et al. (+1 more)
CounterFactual Examples (CFEs) are a cornerstone of eXplainable Artificial Intelligence (XAI), offering local, post hoc, and model-agnostic explanations by identifying minimal input modifications that alter a model's prediction. Yet, in order to be intelligible, these modifications must also be semantically meaningful to the explainee. This paper proposes to integrate knowledge expressed as a fuzzy linguistic vocabulary to represent the explainee's perception and interpretation of the data. The domain induced by this fuzzy vocabulary imposes structural constraints that make the features dependent, preventing the use of gradient-based optimisation methods for CFE generation, e.g., DiCE. The paper proposes a continuous data
embedding in this linguistic domain and exploits it to define a variant of DiCE that allows personalisation for the explainee, named DiCEf. As illustrated by experimental results on a real-world
dataset, this extension of the DiCE method enables the generation of CFEs that are linguistically perceptible while preserving cost minimality, sparsity, and diversity.
Read the full abstract ▾
All authors Akram Bensalem, Fahima Djelil, Marie-Jeanne Lesot, Grégory Smits
Computation and Language
Through the Eyes of the Beholder: Biometric and Demographic Conditioning for Multimodal Sexism Detection
Ana-Maria Luisa Mocanu, Sebastian Mocanu, Ciprian-Octavian Truică et al. (+1 more)
Detecting sexism on the internet is a fundamentally subjective task; our team, VANGUARD, addresses this challenge in the EXIST 2026 Task 2 by proposing a human-centered
multimodal framework that analyses and incorporates the psychological and demographic characteristics of human annotators into the detection pipeline. We fuse five input modalities through a cross-
attention architecture with Feature-wise Linear Modulation conditioning. Meme text is extracted and visually described with Gemma 4, then augmented by automatic translation between English and Spanish with NLLB-200. Text and image representations are produced by LoRAadapted XLM-RoBERTa and CLIP encoders and fused with sensor features encoded by a pretrained autoencoder. To model annotator subjectivity, we frame Subtask 2.1 as a label distribution learning problem, optimizing a Kullback-Leibler divergence loss over the full annotator label distribution. At inference time, predictions are produced by soft-voting between the deep
multimodal network and a complementary SVM trained on stylometric and physiological features. Our best submission ranks 29th out of 114 on Subtask 2.2 (source intention) under soft evaluation, and the normalized ICM scores remain above the baseline on Subtasks 2.1 and 2.2, indicating that annotator-centered conditioning contributes a usable signal. We release our full pipeline and analysis to support reproducible human-centered modeling.
Read the full abstract ▾
All authors Ana-Maria Luisa Mocanu, Sebastian Mocanu, Ciprian-Octavian Truică, Elena-Simona Apostol