Computer Vision · Cross-listed from eess.IV
Modality-Invariant Coarse-to-Fine Retinal Image Registration
Bo Wen, Nehal Nailesh Mehta, Melanie Tran et al. (+3 more)
Retinal image registration is essential for ophthalmic diagnosis, longitudinal disease monitoring, and
multimodal retinal image analysis. Existing retinal registration methods are typically modality-dependent: they are designed or optimized either for a single imaging modality in mono-modal registration or for a fixed pair of modalities in cross-modal registration. This limits their flexibility and applicability in practical scenarios involving diverse retinal imaging modalities and different combinations of them. In this work, we propose a generalizable two-stage, modality-invariant framework for retinal image registration. First, we introduce a sparse feature-matching model driven by a universal retinal vessel
segmentation to achieve robust coarse global
alignment across modalities. Second, we develop a modality-invariant optical flow estimation network, termed MI-RAFT, to refine the
alignment through dense local registration. Extensive experiments demonstrate that the proposed method can handle diverse combinations of commonly used retinal imaging modalities, exhibiting strong modality invariance while outperforming state-of-the-art modality-dependent registration methods.
Read the full abstract ▾
All authors Bo Wen, Nehal Nailesh Mehta, Melanie Tran, Dirk-Uwe Bartsch, William Freeman, Truong Nguyen
Artificial Intelligence
MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment
Tony Tu, Sayan Chakraborty, Ruomeng Xu et al. (+2 more)
Aligning a
language agent to several objectives at once is a persistent failure mode of preference-based training: when objectives are combined additively, optimization collapses onto whichever is cheapest to improve and sacrifices the rest, so a support
agent learns to sound warm while giving no real help. The root issue is that an additive reward has no notion of balance. We introduce Mint (MIN-selection preference
disTillation), a one-line change to preference
distillation: rather than ranking sampled candidates by a weighted sum of rewards, we rank them by their weakest objective, distilling the best-balanced candidate over the most lopsided one with an unchanged DPO objective. This is the p -> negative infinity limit of a generalized-mean family spanning additive to worst-case selection. Across cooperative emotional support and
adversarial negotiation, min-selection lifts both objectives while sharply cutting their imbalance; on emotional support it raises the weaker axis from 0.37 to 0.64 (p < 10^-40), surpassing human experts and persisting across full multi-turn rollouts. A turn-by-turn analysis yields our central finding: min-selection corrects imbalance in proportion to how imbalanced the reference policy is, and its benefit endures over an interaction precisely as long as that imbalance does.
Read the full abstract ▾
All authors Tony Tu, Sayan Chakraborty, Ruomeng Xu, Tony Qin, Austin Tian
Distributed Computing · Cross-listed from quant-ph
Enabling Hybrid HPCQC Workflows with a Heterogeneous Software Stack
Muhammad Nufail Farooqi, Minh Chung, Burak Mete et al. (+5 more)
In this work, we demonstrate hybrid High Performance Computing-
Quantum Computing (HPCQC) workflows on a production petascale system. The demonstration combines three components: the SuperMUC-NG supercomputer at the Leibniz Supercomputing Centre (LRZ), a 20-
qubit superconducting
quantum processor provided by IQM
Quantum Computers (IQM), and Munich
Quantum Valley (MQV)'s Munich
Quantum Software Stack (MQSS). Integrating
quantum processors into High Performance Computing (HPC) systems requires a heterogeneous software stack capable of orchestrating classical and
quantum resources within established supercomputing workflows. MQSS treats
Quantum Processing Units (QPUs) as scheduler-managed accelerators and it performs resource coordination following a two-level scheduling scheme. Slurm performs system-level allocation by exposing QPUs as Generic RESources (GRES), while the MQSS
Quantum Resource Manager & Compiler Infrastructure (QRM&CI) performs just-in-time compilation and subsequent dispatch of
quantum circuits. To integrate with existing HPC operations without modifying the scheduler core, MQSS introduces an open-source SLURM Plugin Suite based on Prolog/Epilog scripts and SPANK modules. Experimental results show that hybrid HPCQC workflows can be executed without significant latency overhead compared to conventional workloads. The presented architecture provides a portable integration model for
quantum accelerators on large-scale HPC systems and is directly applicable to next-generation Hewlett Packard Enterprise (HPE) Cray platforms, including LRZ's upcoming 'Blue Lion' supercomputer.
Read the full abstract ▾
All authors Muhammad Nufail Farooqi, Minh Chung, Burak Mete, Eric Mansfield, Bernd Hoffmann, Teemu Mattsson, Laura Schulz, Jorge Echavarria
Cryptography and Security · Cross-listed from eess.SP
Explainability Boosted Anomaly Detection Framework for O-RAN based NextG Networks
Nurullah Aksu, Ali Fuat Sahin and Semiha Tedik Başaran
The wireless networks have historically faced significant security vulnerabilities, necessitating advanced anomaly detection mechanisms, especially as networks evolve towards 6G and beyond. This study introduces an advanced anomaly detection framework that leverages explainable artificial intelligence to enhance the security of next-generation (NextG) cellular networks. By implementing and evaluating a variety of artificial intelligence models, the framework demonstrates high accuracy and efficient runtime performance in identifying malicious traffic within a realistic Open
Radio Access Network (O-RAN) testbed. A key innovation of this work is the integration of post-hoc explainability methods to identify the most critical key performance metrics (KPMs), which enables a significant 80% reduction in
dataset complexity without compromising detection accuracy. Additionally, explainability analyses identify several critical attack traffic characteristics, such as protocol type, bandwidth, interval, and duration, to prevent upcoming network attacks. The resulting framework effectively balances computational efficiency, accuracy, and explainability, underscoring its practical applicability for enhancing security in next-generation cellular networks.
Read the full abstract ▾
Multiagent Systems
Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce
Zeyuan Li, Lukas Petersson, Alessandro Acquisti et al. (+1 more)
Frontier LLM
agents increasingly transact on behalf of separate principals, often using natural
language rather than structured APIs. Much of the safety literature studies misaligned LLM behavior through
adversarial-elicitation evaluations on single
agents or stylized tasks. Its prevalence and structure in settings that combine long horizons, separate principals, real operational state, and inter-
agent natural-
language exchange remain insufficiently measured. We study 2,583 inter-
agent emails from 20 one-year simulation runs of Vending-Bench Arena, a competitive vending environment spanning 13 frontier LLMs. We operationalize
speech-act misalignment as emails containing false factual claims, manipulation, collusion, or threats, combining message content with ground-truth simulator state and logged
reasoning traces to classify and validate such behavior. Under our primary classifier, 12.6% of emails are labeled misaligned; misalignment appears in all 20 runs and 74.7% of individual
agent-runs. Both the magnitude and composition of this misalignment are preserved under repeated classification at different sampling temperatures and under full-pipeline replication with judges from two other frontier-model families. Misalignment is also reciprocal and stress-conditioned: receiving a misaligned email from a counterparty raises the odds of a misaligned reply by 1.65x, and low-inventory conditions raise them by 1.58x. Across tests of capability-asymmetric exploitation, we find no evidence that higher-capability models differentially exploit weaker counterparties, and model performance rank does not predict misalignment rates. Together, these results indicate that measurable, state-dependent misalignment can arise in competitive multi-
agent environments without engineered elicitation, in patterns associated with operational scarcity and counterparty behavior rather than model capability alone.
Read the full abstract ▾
All authors Zeyuan Li, Lukas Petersson, Alessandro Acquisti, Michiel A. Bakker
Machine Learning · Cross-listed from eess.AS
A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification
Christiaan M. Geldenhuys and Thomas R. Niesler
We present a parameter-free episodic evaluation of nearest-centroid classification of elephant vocalisations on fixed pretrained
embeddings, for the Elephant Voices (EV) and Linguistic Data Consortium (LDC)
datasets. We ask not which
embedding yields the best classifier trained on all labelled data, but how the simplest classifier performs as the number of exemplars per class varies. There are no learnable parameters, because each class is modelled as the mean of its support
embeddings and each query is assigned to the nearest centroid under squared Euclidean distance. Evaluation covers the fixed Perch (ver. 1), Perch (ver. 2) and HuBERT (base, layer 2)
embeddings, alongside mel frequency cepstral coefficient (MFCC) features, $N$-way $k$-shot, under the same stratified $K$-fold cross-validation protocol as the trained classifiers. None of these
embedding models was trained to distinguish elephant call types. On the smaller EV
dataset the centroid classifier is markedly data-efficient. Using Perch (ver. 1) or Perch (ver. 2)
embeddings it overtakes in mean average precision (mAP) the fully-trained logistic regression (LR) baseline from one or two exemplars and the recurrent baseline from two. Over the reduced set of call types on which the strongly-supervised end-to-end baseline was trained, the centroid classifier using Perch (ver. 2)
embeddings overtakes that baseline in mAP as well, from two exemplars. On the larger LDC
dataset the recurrent baselines retain their advantage for all considered values of $k$. Only LR is overtaken, and only in mAP. Nearest-centroid classification is therefore preferable precisely when exemplars are few and the fixed
embedding already separates the call types.
Read the full abstract ▾
Machine Learning
Disentangling Homophily and Rarity: Explaining Failure in Graph Neural Networks
Preben M. Ness, Fariz Ikhwantri and Dusica Marijan
Are heterophilic nodes in a graph harder to classify because they are heterophilic or because they are rare? Some existing work frames classification of such nodes as a subgroup generalisation problem, where a model performs well on the majority group at the expense of the rare group. Others explain this as a problem of neighbourhood aggregation in graph neural networks (GNNs). We assess these two viewpoints through a detailed evaluation of six GNNs on five
datasets of varying homophily, and find that homophilic nodes tend to be easier to classify, even when they are rare—challenging the subgroup framing. However, our findings also nuance existing beliefs about how GNNs misrepresent heterophilic nodes. We demonstrate that the information needed to classify heterophilic nodes correctly is often recoverable by retraining the classification head of a model, or even just the final linear classification layer.
Read the full abstract ▾
Robotics
Imagining Recovery: Inference-Time Counterfactual Realignment for Vision-Language-Action Models
Yanyan Zhang, Disheng Liu, Kai Ye et al. (+6 more)
Vision-
language-action (VLA) models have improved the flexibility and generality of robotic manipulation, yet they remain fragile to online disruptions, such as changes in task goal, scene configuration, or
robot state. Existing recovery methods often require failure data, policy retraining, or external corrective
agents, introducing additional data requirements and execution risks. We propose Counterfactual Realignment (CoRe), a training-free framework that recovers a frozen VLA at inference time without failure data. Upon detecting a deviation, CoRe imagines how the policy would continue toward the current goal from a recent viable state, using synthesized observations in place of physical execution, and then minimally realigns the
robot and scene to rejoin this imagined continuation before returning control to the policy. Recovery is therefore planned without physical trial-and-error, preserves completed task progress, and handles both mid-episode instruction changes and physical perturbations in a unified manner. Extensive experiments across multiple simulators, VLA backbones, and real-world settings show that CoRe improves success rates by up to 85.0 percentage points to near-nominal levels while reducing physical restorations by 42.2%, without policy fine-tuning or failure-specific recovery training.
Read the full abstract ▾
All authors Yanyan Zhang, Disheng Liu, Kai Ye, Chaoda Song, Xinpeng Li, Mohsen Hariri, Vikash Singh, Yu Yin, Vipin Chaudhary
Information Theory · Cross-listed from math.CO
Thomas W. Cusick
We give a complete proof of the 2011 Tu–Deng
conjecture. We begin from its original modular pair-count formulation, prove an equivalent cyclic Hamming weight-drop formulation, and establish the exact transfer identity that connects this count with a two-variable
matrix polynomial. The proof then reduces the
conjecture to normalized inequalities for the coefficients of that
polynomial. A 2011
conjecture by the author which came to be called the Cusick
Conjecture (it is a consequence of the Tu–Deng
Conjecture) was proved by K. Cheng in 2026. The proof in the present paper extends the cyclic deletion ideas of Cheng. The new ideas might be applicable to other problems.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.SP
Handover Analysis for Vehicular Communication with Explainability on the Fly
Ali Fuat Sahin, Semiha Tedik Başaran and Tufan Kumbasar
Handover (HO) management in vehicular networks requires fast and reliable decision-making under highly dynamic conditions. While machine learning (ML) approaches can improve HO detection by capturing complex relationships among various key performance indicators (KPIs), their black-box nature limits interpretability and operator trust. To address this, this paper investigates HO detection from an explainability-on-the-fly perspective using inherently interpretable models based on the functional analysis of variance (fANOVA) framework. The proposed models are evaluated using two real-world operator
datasets and compared against a Long Short-Term
Memory baseline augmented with post-hoc SHAP explanations. Unlike post-hoc approaches, the proposed framework enables immediate interpretation of model decisions without incurring additional computational overhead. This capability is particularly critical for latency-sensitive vehicular networks. The results show that fANOVA-based models achieve competitive detection performance while providing significantly reduced explanation latency compared to conventional post-hoc methods. Furthermore, feature ranking and visualization analyses reveal physically meaningful relationships between KPIs and HO occurrences that align with standardized HO mechanisms. These results demonstrate that inherently interpretable models provide an efficient and transparent solution for HO detection in next-generation vehicular networks.
Read the full abstract ▾
Sound
What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models
Angelos-Nikolaos Kanatas, Yuexuan Kong, Pablo Alonso-Jiménez et al. (+2 more)
Music foundation models are commonly used as frozen audio feature extractors, yet selecting which layer to extract from remains largely heuristic. Current practice defaults to fixed depths or multi-layer fusion, with limited understanding of why certain layers transfer better across downstream tasks or how representation quality varies with depth and pre-training paradigm. We conduct a systematic layer-wise analysis of 12 music foundation models spanning three pre-training paradigms (masked modeling, autoregressive modeling, and contrastive learning), characterizing their hidden representations through intrinsic
geometric and transformation-based properties. Correlating label-free representation-quality metrics with layer-wise performance across 15 downstream tasks, we find that several metrics track layer quality for genre classification,
emotion recognition, automatic tagging, and beat tracking, albeit with varying strength across tasks and pre-training paradigms. However, all metrics fail on tonal tasks such as key estimation and chord recognition, indicating that no single property serves as a general proxy for representation quality across music information
retrieval tasks. To address this gap, we introduce a pitch-transposition equivariance measure that captures properties missed by these standard metrics, providing a consistent indicator of tonal quality across model families. Finally, we show that intrinsic metrics can serve as effective proxies for layer selection, matching or outperforming trainable multi-layer fusion methods, particularly in limited-data settings.
Read the full abstract ▾
All authors Angelos-Nikolaos Kanatas, Yuexuan Kong, Pablo Alonso-Jiménez, Xavier Serra, Dmitry Bogdanov
Computational Complexity · Cross-listed from math.FA
The König constant is one
Xinyuan Xie and Haonan Zhang
For each $N\geq1$, consider the normalized König bilinear form $B_{\mathrm K}:L_\infty(\mathbb R^N)\times L_\infty(\mathbb R^N)\to\mathbb R$ given by \[ B_{\mathrm K}(f,g):=\frac{1}{(\sqrt{2}\pi)^N} \iint_{\mathbb R^N\times\mathbb R^N} f(x)g(y)e^{-(\lVert x\rVert^2+\lVert y\rVert^2)/2} \sin\langle x,y\rangle\,\mathrm d x\,\mathrm d y, \] We define the König constant by \[ \mathfrak K_{\mathrm K}:=\sup_{N\geq1}\sup_{\substack{f,g:\mathbb R^N\to\{\pm1\}\\ f,g\ \mathrm{measurable}}}B_{\mathrm K}(f,g). \] The study of this bilinear form arose from efforts to determine the exact value of the Grothendieck constant. König~\cite{KONIG} conjectured that the sharp value should instead be given by the one-dimensional half-spaces $B_{\mathrm K}(\operatorname{sgn}(x_1),\operatorname{sgn}(x_1))=\frac{2}{\pi}\log(1+\sqrt{2})$. A positive answer to this
conjecture, together with a classical upper bound of Krivine \cite{KRIVINE}, would determine the exact value of the Grothendieck constant. In a breakthrough~\cite{BMMN}, Braverman, Makarychev, Makarychev, and Naor disproved König's
conjecture already in dimension two and used their counterexamples to obtain the first strict improvement over Krivine's bound. One question in \cite{BMMN} attempts to determine the Grothendieck constant through alternating Krivine rounding schemes arising from König's bilinear form in high dimension. More recently, Li et al.~\cite{LISK} constructed high-dimensional examples showing that $\mathfrak K_{\mathrm K}\ge 0.59357$. An elementary
Fourier argument gives $\mathfrak K_{\mathrm K}\le 1$ and excludes equality for every finite-dimension. In this paper, we prove that $\mathfrak K_{\mathrm K}=1$ by constructing a family of Boolean pairs in high dimensions. In particular, this gives a negative answer to the high-dimensional aspect of the question in \cite{BMMN}.
Read the full abstract ▾
Human-Computer Interaction
AI Agents and the Future of VIS
Chen Zhu-Tian, Nam Wook Kim, Saeed Boorboor et al. (+4 more)
Recent advances in
agents (i.e., autonomous, goal-driven AI systems that iteratively observe, act, and learn from their environments) offer a fundamentally different approach from traditional AI models that passively respond to input. These AI
agents are rapidly reshaping how we approach data-intensive tasks and providing new opportunities for the VIS community. Imagine an
agent autonomously generating visualizations to analyze complex data, discovering patterns collaboratively, testing hypotheses, and communicating visual insights at a speed and scale beyond human capability. Yet, the emergence of these powerful systems raises critical questions that the VIS community must address: Could autonomous
agents eventually replace human data scientists, and if not, how might they best collaborate? Are current visualization techniques and interfaces, originally designed for human analysts, suitable for
agent interactions? How can VIS designers effectively integrate
agents into their workflows without compromising human agency? And to what extent should
agents help shape and educate the next generation of visualization researchers? Through a mix of keynote talks, paper presentations, and an agentic VIS challenge, this workshop invites researchers and practitioners to share innovative ideas, explore these questions, and discuss strategies to transform the impact of VIS for a future where human and AI
agents co-exist.
Read the full abstract ▾
All authors Chen Zhu-Tian, Nam Wook Kim, Saeed Boorboor, Shivam Raval, Pan Hao, Qianwen Wang, Vidya Setlur
Computation and Language
Beyond the pale: Assessing prevalence and contents of extremist speech in LLM training data
Dmitry Nikolaev and Ashley A. Mattheis
Despite a strong interest on the part of the research community in the topic of trustworthy and safe AI, the composition of the text corpora that large
language models (LLMs) encounter in pre- and post-training has not yet drawn much
attention. In this work, we address the question of whether LLMs are exposed to unfiltered, uncontextualised extremist
speech. Using several definitions of extremist
speech, stemming from official documents and research literature, and an extraction pipeline combining automated text processing with expert verification, we provide a lower bound on the prevalence of extremist documents in Dolma, an open training corpus underpinning the OLMo series of models. We show that Dolma is likely to include hundreds of thousands of documents containing extremist content and hate
speech of several types, including direct calls for violence, and discuss the implications of this for data curation and model pre-training.
Read the full abstract ▾
Computer Vision
Where the Cost Falls: A Deployment-Aware Adoption Order for Stability Enhancements to Cycle-Consistent Adversarial Networks
Rowan Hussein and Mohamed Ouf
Teams that adopt cycle-consistent
adversarial networks for unpaired image-to-image translation meet the same obstacles:
adversarial training oscillates or collapses, cycle consistency preserves coarse layout while finer texture drifts, and a single discriminator judging global realism misses local artifacts. Four enhancements address these failures, and they are usually compared on output quality alone. We show that they also divide sharply by where their cost falls, and that this division, which follows from the architecture and not from any particular run, yields an adoption order for teams under a compute or latency budget. A Wasserstein objective with gradient penalty, a VGG19 perceptual loss on the cycle reconstruction, and multi-scale discriminators change training only, so a team can adopt or drop them without altering what ships. Self-
attention alone persists into the deployed generator, with
memory growing as the square of the feature-map size, which makes it the one component a resource-constrained team should defer. We integrate all four onto a lightly tuned baseline for horse-to-zebra translation, introduced one at a time on a fixed control and then combined, and for each we give the failure mode it targets and how it integrates. We document the collapse and reconstruction-artifact modes the baseline produced, report what visual inspection of saved samples showed for each variant, and report Fréchet Inception Distance and Kernel Inception Distance for the combined model. We specify the protocol still needed, covering the individual variants, perceptual similarity, and downstream
segmentation, to rank these enhancements on measured evidence.
Read the full abstract ▾
Numerical Analysis
Mixture of experts surrogate model for the homogenization of open-porous materials
Axel Klawonn, Martin Lanser, Lucas Mager et al. (+2 more)
For open-porous materials, incorporating their microstructural properties into mechanical simulations poses a significant challenge for accurately capturing elastic deformation. To deal with this difficulty, multiscale methods are a common tool to couple characteristics of the microstructure of the considered material with the macroscopic material behavior. However, when desiring a high accuracy, these multiscale computations can be computationally very expensive due to the large number of microscopic problems which need to be solved in each compute step. Here, surrogate models that learn the mechanical response of the underlying constitutive model can significantly reduce the computational cost of multiscale approaches. In previous work by some of the authors, beam frame models have been used to model the microstructure of open-porous materials which have been combined with neural network-based surrogate models to approximate the material behavior of a given RVE (repesentative volume element). In this work, we extend our previous study by training a more complex neural network model to predict the mechanical behavior of several RVEs, differing in their maximum pore size and pore-size distribution. Concretely, we focus on mixture of expert (MoE) models and compare different MoE architectures as well as their performance across different RVEs. This novel approach reduces the computational cost of simulating multiple RVEs as the MoE model does not require additional training when new RVEs are considered.
Read the full abstract ▾
All authors Axel Klawonn, Martin Lanser, Lucas Mager, Ameya Rege, Janine Weber-Hamacher
Artificial Intelligence
Do LLMs Know What to Ask and When? Evaluating Multi-Turn Information Seeking
Yepeng Huang, Jiawen Zhang, Michelle Dai et al. (+4 more)
When a user question is underspecified, a capable model should recognize that its context is insufficient, identify the missing information, ask for it, and respond only once that information determines a unique answer. We formalize multi-turn information seeking as solving a k-underspecified constraint satisfaction problem, where k is the number of variables jointly required to determine the target and therefore measures the degree of missing information. We instantiate the formulation in MT-InfoSeek, a controlled evaluation suite of 5,251 problems and 9,006 task instances spanning mathematics, logic, biology, medicine, and general knowledge. We evaluate models along three axes: what they ask, when they ask it, and how the acquired information affects the final answer. Performance degrades across models and domains as underspecification increases. Models recognize that additional information is needed but underestimate how much, and in logical problems at k = 2 they under-predict the degree of missing information about four times as often as they over-predict it. They also fail to identify a minimal sufficient set of queries, improve only marginally when given the true k, and often stop before acquiring sufficient information. In tasks with ordered dependencies, an incorrect query order reduces final accuracy even when the model eventually acquires all necessary information. We measure information seeking directly through final sufficiency, which records whether the acquired information determines the target independent of answer generation. This separation shows differences between models that final accuracy alone does not capture, and indicates that the ability to seek information over multiple turns is distinct from the ability to generate answers and is not measured by current LLM evaluations.
Read the full abstract ▾
All authors Yepeng Huang, Jiawen Zhang, Michelle Dai, Xiaorui Su, Shanghua Gao, Zi Wang, Marinka Zitnik
Artificial Intelligence
Generated Context versus Governed State: Functional Conditions for Accountable Longitudinal Clinical Reasoning
Augusto Bernardo Pissarra and Victor Lorena de Farias Souza
Large
language models (LLMs) have become the dominant interface of clinical artificial intelligence, yet the interface they expose (text in, text out, one context window at a time) maintains no explicit, persistent, governed representation of what is currently true about a patient. This paper argues that longitudinal clinical
reasoning is a state-estimation problem under partial observability, and that the axis on which clinical AI succeeds or fails is not the fluency of the model reading the record but the governance of the patient state it reasons over. We distinguish generated context from governed state; separate five objects that clinical AI habitually conflates (true state, observations, evidence, belief, and simulated state); define a tiered governance standard against which any clinical AI system can be audited; and show that an operational definition of accountability decomposes into four information requirements: an immutable evidence ledger with awareness-time versioning, a belief state distinct from accumulated evidence, an observation-process model, and claim-level causal typing. We are explicit that this decomposition is analytic rather than a necessity
theorem, and that its value is conceptual hygiene: it converts "accountable clinical AI" from a slogan into an audit instrument. A six-level maturity framework separates what a system makes governable from what it can compute, locating current LLM-centric practice at high capability but low maturity. The paper is fully self-contained: the four research questions the framework poses are stated in the introduction, and the conclusion records what the paper establishes toward each; future work develops the buildable core of the architecture and the research program toward full Clinical World Models. No empirical result is claimed here.
Read the full abstract ▾
Machine Learning
Is Grokking a Loss of Normal Hyperbolicity of the Interpolation Manifold?
Suvinava Basak
A recent line of work recasts the post-memorization phase of grokking as constrained optimization: once a network interpolates the training set, weight decay drives a slow drift along the zero-loss
manifold toward lower norm. In the
language of dynamical systems, this is a fast-slow system in which the interpolation
manifold plays the role of a slow
manifold. We ask a question that this framing makes natural but the existing literature does not address: is the sharp generalization transition a loss of normal hyperbolicity of that
manifold: a fold- or bifurcation-like event in which a normal restoring direction goes flat? Or does the
manifold stay uniformly attracting while generalization happens by smooth drift? We propose a simple, optimizer-agnostic diagnostic: the smallest nonzero singular value $\sigma_{\min}^{+}(\mathbf J)$ of the residual Jacobian, which, for the squared loss, equals the slowest normal restoring rate of the
manifold. On a two-layer ReLU network trained to grok modular addition under squared loss, $\sigma_{\min}^{+}(\mathbf J)$ does not collapse at the transition; it is near zero only before memorization and attains its largest values during the transition. The result holds across five seeds, and the six smallest singular values behave identically; there is no subspace-local collapse either. This is preliminary evidence against the bifurcation hypothesis and in favor of the smooth-contraction picture. We are explicit that a single-setting, gradual-transition experiment under Adam optimizer does not prove the absence of a bifurcation; it constrains where one could hide.
Read the full abstract ▾
Cryptography and Security
Bit-Level Triangular Content-Aware Permutation for Fragile Image Watermarking: Zero False Positive Rate, Single-Bit Sensitivity, and Arbitrary Dimension Support
Zahra Ghoraeian, Mohammad-Reza Sadeghi and Samaneh Mashhadi
With the growth of digital document exchange, protecting image integrity against attacks such as Vector Quantization (VQ) and collage has become critical. Existing methods are vulnerable to these attacks and limited to fixed image dimensions. This paper presents a novel, dimension-agnostic, fragile watermarking
algorithm that enhances security and tamper localization by replacing conventional hash functions with Triangular Content-Aware Permutation (TCA). The image is combined with key-based global noise and divided into blocks. The core innovation is applying content-dependent permutation with intrinsic avalanche effect (TCA) at the bit-plane level, generating a unique content-dependent watermark. For color images, a vertical sandwich transformation merges channels, preserving inter-channel dependency with only 1.62x time increase. The "remainder merging" strategy eliminates padding constraints. Experiments on 50 grayscale and 10 color images under 18 attacks show FPR=0% and FNR=0% for 17 attacks. Salt-and-pepper noise yields negligible FNR of 0.27% (grayscale) and 0.14% (color). Average PSNR is 51.14 dB (8-bit), 75.25 dB (12-bit), and 99.33 dB (16-bit).
Embedding and extraction times are 1.61 s and 1.63 s, respectively. The
algorithm achieves 100% accuracy against collage, VQ, copy-move, JPEG (quality 5-95), and
geometric attacks, providing a secure solution for digital forensics, medical imaging, and legal document authentication.
Read the full abstract ▾
Distributed Computing
Porting and Benchmarking Chapel on Emerging RISC-V Hardware: An HPC Viability Study
Ian Henriksen, Chris Taylor, Patrick Diehl et al. (+4 more)
The Chapel programming
language recently added support for the RISC-V architecture. Here we discuss what changes were needed for Chapel to work on RISC-V as well as lessons learned from the porting process. We use some of Chapel's extensive
benchmark suite to gain further insight into the suitability of the RISC-V architecture for future HPC use. We compare performance on SiFive P550 and Unmatched boards and a Sophon SG2042 with a variety of other recent HPC CPU platforms. Various portability and performance anomalies arose on different architectures and are discussed. While the RISC-V machines represent smaller preliminary offerings and not HPC-class hardware, these results still provide hope that RISC-V hardware can become viable for HPC in the near future.
Read the full abstract ▾
All authors Ian Henriksen, Chris Taylor, Patrick Diehl, Jade Abraham, Palmer Cox, Bradford L. Chamberlain, Stephen L. Olivier
Computation and Language
Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Models
Haoran Wang, Xiongxiao Xu, Philip S. Yu et al. (+1 more)
Large
language models (LLMs) and large
vision-
language models (LVLMs) have demonstrated impressive generative capabilities, yet ensuring their outputs align with user intent is still challenging. While most existing approaches address this issue at the training stage, inference-time approaches like decoding methods offer a more efficient and scalable solution. Decoding methods control model generation by guiding
token-level selection, performing sequence-level generation, or generating
tokens in parallel to accelerate the process. In this survey, we identify three emerging paradigms from recent works on decoding methods for LLMs and LVLMs, provide a systematic review of these methods, highlight ongoing challenges, and discuss potential future research directions. Our goal is to underscore the efficiency and effectiveness of decoding methods and offer a practical view of their applications. Paper lists and more resources on decoding methods for LLMs and LVLMs can be found at https://github.com/wang2226/Awesome-LLM-Decoding.
Read the full abstract ▾
All authors Haoran Wang, Xiongxiao Xu, Philip S. Yu, Kai Shu
Computer Vision
Zero-Shot Adaptation of Medical Vision Foundation Models for High-Frequency Micro-Ultrasound Prostate Segmentation
Ayusha Abbas, Saram Abbas and Kabita Adhikari
Prostate cancer claims a life every 80 seconds. Early detection is needed to prevent disease progression, and both PSA density calculation and biopsy decisions rely on knowing the exact boundary of the gland. Conventional ultrasound at 6-12 MHz blurs this boundary, missing one in three high-risk cancers. Micro-ultrasound (29 MHz) improves resolution threefold but introduces dense acoustic speckle that obscures the outer wall; given the same image, two clinicians draw outlines differing by over 10% in area. Supervised methods are costly and generalise poorly across scanners. Can a foundation model segment the prostate with no training data? We present the first zero-shot pipeline for this modality: MedSAM, pre-trained on over 1.5 million medical images, localises the prostate; we then apply CLAHE to sharpen the outer wall, binary dilation to recover missed pixels, and
Fourier smoothing (4 modes, s=1.05) to refine the boundary. MedSAM requires a spatial
prompt, so we evaluate bounding-box and point-click strategies across 75 patients of the Micro-Ultrasound Prostate
Segmentation dataset (2,621 slices). On the 20-patient held-out test set, the pipeline reduces mean boundary-distance error by 45% (Dice 0.749+/-0.043 to 0.865+/-0.029; HD95 217.2+/-36.9 to 120.1+/-26.1 px), reaching Dice 0.859 across the cohort. Its mean overlap shows no significant difference from the three non-expert rater groups (p>0.19), while segmenting 38-52% more consistently (lower inter-patient standard deviation). Point-click
prompts fail regardless of placement (best Dice=0.350), because speckle gives no stable local contrast. Only an approximate bounding box is required, so any clinic can deploy it without data collection, annotation, or retraining.
Read the full abstract ▾
Artificial Intelligence
Individual Disempowerment through an Advice Channel: Control Loss when Influence is Endogenous
Adam M. Oberman
An AI that can only give advice seems safe: the human is always free to ignore it. That is the premise of the boxing tradition in AI safety, and its long-suspected weak point is that the human who reads the answers is part of the system. We make the fraction $\varepsilon_t$ of behavior that follows the advice a state of a Markov decision process, moved by the advisor's own messages, so that use deepens reliance. Granted a channel rich enough to echo any action the human could take, higher $\varepsilon_t$ weakly lowers every monotone measure of the power of a human with a message-independent fallback. An oracle rewarded by per-round approval cultivates reliance beyond a closed-form patience threshold, so the same reward weights leave the optimal oracle answering in episodic deployments and cultivating in long-
memory ones. An influence bound certified once at deployment is blind to that horizon and bounds the loss no lower than its trivial ceiling. An exogenous cap on influence bounds the guarantee the human loses, and a short enough
memory reset removes the incentive to cultivate, while neither recovers the value already steered away. In a closed-form example the optimal oracle never cultivates in fifteen-round sessions and does in sixteen.
Read the full abstract ▾
Computation and Language
Prompting is not enough: supervised baselines and leakage control for measuring shared decision-making with LLMs in pediatric encounters
Bernardo Modenesi, Jody Lin, Kimberly Kaphingst et al. (+4 more)
Objectives: To determine whether zero-shot prompting of a large
language model (LLM) is sufficient to detect shared decision-making (SDM) behaviors in real clinical encounters, and whether supervised learning adds value under patient-grouped, nested evaluation. Methods: We analyzed 21 audio-recorded outpatient
surgical decision encounters (19 unique patients; 7,566 utterance segments; ~6.1 hours) between families of children with multiple long-term conditions and their
surgical providers. Trained coders labeled segments for 12 SDM behaviors (human-human macro Cohen's kappa = 0.695). We compared a zero-shot local LLM (Qwen 2.5 32B), a supervised classifier over frozen sentence
embeddings, and their logistic stack, under patient-grouped outer folds with inner cross-fitted thresholds and patient-resampled confidence intervals. Results: The zero-shot LLM reached macro kappa = 0.139 (95% CI 0.111-0.164). The supervised classifier reached kappa = 0.227 (0.186-0.262), a paired improvement of 0.088 (0.051-0.119). A logistic stack of the two reached kappa = 0.242 (0.198-0.284). We identified multiple corpus-specific leakage paths, including grouping sibling recordings separately and allowing labels from an outer held-out patient to enter few-shot exemplars used while fitting downstream models. Conclusion: Zero-shot prompting alone is not sufficient to measure SDM behavior as reliably as a small supervised model, and patient-level grouping alone does not prevent leakage when labeled
prompt exemplars are precomputed outside the outer evaluation loop. Reported performance is sensitive to the unit of data splitting and to where labeled exemplars enter the pipeline. External validation is needed before these findings generalize beyond this population, model,
prompt, and codebook.
Read the full abstract ▾
All authors Bernardo Modenesi, Jody Lin, Kimberly Kaphingst, Angela Zhu, Maya Wheeler, Peilu Zhang, Angela Fagerlin
Artificial Intelligence
CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs
Moein Salimi, Danial Parnian, Shaygan Adim et al. (+6 more)
Abductive
reasoning, often characterized as inference to the best explanation, is central to explanation under uncertainty, from everyday sense-making and investigation to scientific discovery. Yet LLM research has mostly studied abduction through narrow, task-specific
benchmarks, making it unclear whether observed gains transfer beyond the
benchmark family used for training or evaluation. We ask whether RL post-training can improve abduction as a transferable
reasoning capability. We introduce CEDAR-GRPO, a process-aware framework that combines final-answer correctness with abductive rewards for evidence coverage and evidence-to-explanation directionality. Four open-weight LLMs are post-trained on a controlled, domain-neutral mixture of abductive hypothesis-generation and hypothesis-selection tasks. We evaluate them on 11 unseen tasks spanning hypothesis selection, missing-fact generation, defeasible inference, long-context investigation, clinical
reasoning, code debugging, and non-abductive controls. CEDAR- GRPO improves every model on every held-out task over both base models and correctness-only GRPO, with average gains of 7.4 and 2.7 points, respectively, and a maximum gain of 30.8 points. Ablations confirm that RL, abductive reward design, and task diversity each contribute to transfer. Process-level metrics further show stronger abductive behavior, including exploration of alternatives, elimination of rivals, backtracking, and uncertainty marking.
Read the full abstract ▾
All authors Moein Salimi, Danial Parnian, Shaygan Adim, Amirmohammad Ebrahiminasab, Nima Alighardashi, Parsa Gholami, Sahand Akramipour, Mahdi Jafari Siavoshani, Mohammad Hossein Rohban
Computer Vision
Instruction-Based Video Editing by Repurposing an Image Editing Model
Yunpeng Bai, Yossi Gandelsman, Michaël Gharbi et al. (+1 more)
Instruction-based
video editing is commonly built on
video-pretrained generative backbones: a
video diffusion transformer is adapted, at considerable cost, to condition on a source
video and an editing instruction. In this report we explore a different route and show that a strong instruction-based image editing model can edit
videos by operating directly on
video-VAE latents. Starting from Qwen-Image-Edit, we arrange the latent frames of a Wan~2.1
video VAE as tiles of one large virtual image, reuse the editor's image positional encoding for every tile, and bridge the two latent spaces with a pair of lightweight input/output projections warm-started from the editor's own patchify and unpatchify layers, so that at initialization a (static)
video is embedded exactly as an image the model already understands. The whole system is then fine-tuned on the public Ditto-1M editing triplets, and a few denoising steps of Wan~2.2 serve as an optional temporal enhancer. We motivate the design with a chain of zero-training observations: the stock image editor already edits a
video presented as a contact sheet; it is indifferent to whether the sheet's
tokens come from one joint encode or from per-frame encodes stitched in latent space; and it even edits genuine
video latents zero-shot to a clearly recognizable degree, leaving fine-tuning only a fidelity gap to close. Our results suggest that, despite the large investment in training
video latent spaces, per-frame
video latents remain close enough to the image domain that mature image editing priors transfer with minimal adaptation. Project Page: https://yunpeng1998.github.io/Qwen-
Video-Edit-Page Code: https://github.com/yunpeng1998/Qwen-
Video-Edit Model: https://huggingface.co/yunpeng1998/Qwen-
Video-Edit
Read the full abstract ▾
All authors Yunpeng Bai, Yossi Gandelsman, Michaël Gharbi, Qixing Huang
Artificial Intelligence
Task-Driven Three-Layer Distributed Scheduling for Emergency Earth Observation in Large Low-Earth-Orbit Constellations
Qian Yin, Xinwei Wang and Guohua Wu
Large low-Earth-orbit (LEO) Earth-observation (EO) constellations offer frequent access to geographically dispersed ground targets, but emergency requests may arrive after committed routine-plan execution has begun. The resulting dynamic emergency observation scheduling problem (DEOSP) requires urgent tasks to be inserted under intermittent ground contact without excessive routine-plan disruption. To address DEOSP, we propose a task-driven three-layer distributed scheduling (T3L-DS) method, which represents task demand and sensor footprints on a common geographic grid and forms temporary clusters from observation capabilities and current inter-satellite links. For intra-cluster coordination, T3L-DS introduces onboard dual-plan bidding and joint marginal evaluation. It also designs an inter-cluster coordination mechanism for unresolved demand. Extensive computational experiments compare T3L-DS with centralised simulated annealing (SA), an adapted selective time-variant better reply process (A-SeTVBRP), and a conventional contract-net protocol (CNP). T3L-DS achieves the highest emergency coverage among the distributed methods, with average relative improvements of approximately 2.8% and 17.1% over A-SeTVBRP and CNP, respectively. Its average relative gap from SA is approximately 7.1%. Under conflict-enhanced loads, it reduces routine-coverage loss by approximately 57.9% and 87.7% relative to A-SeTVBRP and CNP, respectively. The ablation study confirms the contribution of the proposed coordination enhancements. Overall, the results show that T3L-DS provides an effective distributed approach to DEOSP.
Read the full abstract ▾
Cryptography and Security
From Positionwise Confidence to Prefix Scheduling: Verifier Skipping in Speculative Decoding
Haoxuan Luo, Jameson Sandler and Ferdinando Fioretto
Speculative decoding is a leading technique to reduce the cost of autoregressive generation by using a small drafter to propose several
tokens, which are then verified in parallel by a larger target model. Speculative
diffusion decoding (SDD) further removes sequential drafting by generating every position in a draft block in parallel with a discrete
diffusion model. However, SDD still invokes the target on every block, leaving verification as a potential bottleneck. This paper recognizes that this creates a new control handle: whether to invoke the verifier at all. Thus, we study verifier skipping, a lossy policy that commits a selected draft prefix directly, and ask which confidence signal should schedule it. Interestingly, our study finds that better
token predictors need not yield better schedulers: skips require contiguous high-confidence prefixes, while short skips can induce additional drafting rounds. To study this mismatch, we compare raw confidence with learned marginal and conditional survival scores under the same policy, using Strict SDD, lenience, and top-$k$ acceptance as baselines. On HumanEval with DiffuCoder-7B-Instruct and Qwen3-32B, all three confidence signals save $9.6\%$ to $13.5\%$ of verifier calls at the same observed pass@1 as Strict SDD. Surprisingly, raw confidence saves the most; marginal survival has higher positionwise AUROC than raw confidence at most positions, yet neither learned signal dominates online. Our analysis shows that verifier skipping is a useful new lossy axis and, surprisingly, its key challenge is prefix scheduling rather than
token prediction alone.
Read the full abstract ▾
Computer Vision
MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modeling
Manwen Liao, Xinyu Lian, Jian Mao et al. (+11 more)
Part-aware 3D object generation is essential for graphics applications such as controllable modeling, editing, and articulation, where objects are represented as coherent assemblies of semantic parts. However, existing part-aware generation methods, do not scale well to highly complex objects. As the number of parts increases, generating detailed geometry becomes prohibitively expensive in
token length and
memory. We introduce MegaParts, a scalable autoregressive 3D generation framework to address this challenge by combining structured sequence modeling with a
token-efficient vector-quantized shape tokenizer. Our tokenizer learns discrete latent representations for part-level geometry by minimizing
token usage subject to high-fidelity reconstruction, enabling adaptive-length tokenization based on
geometric complexity. On top of this compact representation, we train a large
language model to generate object bounding boxes, part bounding boxes, and part shape
tokens within a unified structured sequence. Combined with efficient long-context training strategy, our
token-efficient formulation scales to objects with up to 300 parts and sequence lengths up to 256k
tokens. This substantially extends the scale of part-aware 3D generation while preserving compositional structure and enabling fine-grained part-level control. Our method achieves higher mesh quality than baseline autoregressive and
diffusion models, showing that compressed discrete part
tokens improve not only scalability but also the achievable fidelity of generated geometry. These results suggest that LLM native
token-efficient autoregressive modeling is a compelling alternative to
diffusion for large-scale part-aware 3D generation. The project page is available at https://expmaster.github.io/megaparts_webpage.
Read the full abstract ▾
All authors Manwen Liao, Xinyu Lian, Jian Mao, Kaixu Chen, Li Luo, Jinghao Yan, Wanshui Gan, Qiao Yu, Weitian Zhang, Chunhua Shen, Guang Chen, Bo Dai, Xudong Xu, Zhaoyang Lyu