Software Engineering
Agentic Evolution of SQL Test Generators
Suyang Zhong and Manuel Rigger
Automated testing has uncovered many logic bugs in Database Management Systems (DBMSs). Existing tools are typically limited to a few SQL dialects and a subset of these dialects' features. Coding
agents based on Large
Language Models (LLMs) could encode the semantics of additional SQL features into reusable test generators, requiring no additional LLM calls during testing and thus enabling high efficiency and low cost. However, a key challenge is validating the added capabilities in the presence of potential
hallucinations. In this paper, we propose Gungnir, an approach for evolving DBMS test generators using coding
agents. Our core mechanism is witness replay: the coding
agent provides a generation witness recording the database setup and semantic choices needed to generate a target statement. A validator replays these choices through the modified generator and checks that it reproduces the target statement. Historical witnesses serve as regression tests for subsequent modifications. We evaluated Gungnir on SQLite, DuckDB, and PostgreSQL and found 44 bugs confirmed by developers, of which 34 have been fixed. Beyond DBMSs, witness replay could generalize to other systems to guide
agents in extending test generators.
Read the full abstract ▾
Robotics
Disentangling Task-Relevant Latent Dynamics for Reward Modeling
Dayou Li, Jionghao Wang, Peihao Wang et al. (+9 more)
Reward design remains a major bottleneck for reinforcement learning in robotic manipulation. Handcrafted dense rewards can compensate for the limited guidance provided by sparse rewards, but require substantial task-specific reward engineering. Learning rewards from
videos provides a scalable, data-driven alternative to manual reward design. However, existing
video-based rewards are often computed in entangled visual spaces where task-relevant state changes are confounded with extraneous visual variation. As a result, the learned reward may respond to visual distractors instead of actual task execution. To address this limitation, we propose DiTaR (Disentangling Task-Relevant Latent Dynamics for Reward Modeling), a framework for learning dense rewards from heterogeneous
videos. DiTaR learns a continuous task-relevant representation from multi-frame
video latents through an asymmetric two-stage procedure that suppresses task-irrelevant visual variation. In the task-relevant latent space, we train a history- and
language-conditioned rectified-flow model to capture task dynamics and derive a directional dense reward from temporal changes in dynamics compatibility. Together, these components enable reward modeling directly over task-relevant dynamics rather than generic visual variation. DiTaR substantially improves policy learning on MetaWorld-v3 and ManiSkill over
video-based reward baselines, and transfers to real-world offline RL through reward relabeling. Reward analyses further show that DiTaR provides more reliable rewards.
Read the full abstract ▾
All authors Dayou Li, Jionghao Wang, Peihao Wang, Jiuzhou Lei, Hao Wang, Jichen Chai, Hezhen Hu, Minghui Zheng, Zhangyang Wang, Xin Li, Wenping Wang, Zhiwen Fan
Computer Vision
Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability
Kuan Zhang, Yukun Chen, Zhihao Yang et al. (+7 more)
Understanding and tracking a dynamic world are fundamental to visual intelligence. Existing
video benchmarks provide limited insight into whether models can maintain a coherent understanding of evolving world state. Building such a
benchmark from real-world
videos is challenging because the underlying world state is partially observable, making annotations hard to obtain. To close this gap, we introduce
Video-Arena, a
benchmark that turns competitive games into scalable, verifiable tests of how well models understand evolving world states from
videos. Specifically, inspired by how humans understand dynamic events, we evaluate spatiotemporal world state understanding and tracking through three task categories: perceiving critical events, interpreting state updates, and tracking the resulting states. Our pipeline can generate
videos and aligned reference labels from game records at scale. To keep evaluation affordable and reproducible, we curate a golden set of 180 tasks across 9 games and run evaluations under two protocols: native visual understanding and tool-assisted agentic analysis. The best-performing systems achieve F1 scores of and under the two protocols, respectively. The result highlights that native models struggle to perceive events reliably, while tool-assisted systems improve event recovery but still struggle to interpret state updates and track the resulting states consistently over time. Our project page is in https://videoarena-bench.github.io
Read the full abstract ▾
All authors Kuan Zhang, Yukun Chen, Zhihao Yang, Yue Su, Xiangnan Wu, Zirong Chen, Run Luo, Tao Tan, Yinhe Zheng, Yiming Li
Software Engineering
OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools
Chenyang Yan, Yingying Zhang, Kanzhi Cheng et al. (+21 more)
We introduce OpenMobile-2, a near-frontier mobile
agent with fully open training environments and recipes. We make three key advances: (1) Diverse environments with simulated commercial apps: We build MobileGym++, featuring 35 realistic, functionally rich commercial-style apps with cross-app workflows, while preserving full controllability for reset and verification. Together with newly configured apps in Android emulators, this yields a diverse playground spanning over 110 apps. (2) Open training data at scale: Building on this foundation, we curate nearly 12K mobile interaction trajectories for supervised fine-tuning and the largest open collection of verifiable RL training data for mobile
agents, comprising over 2K executable tasks with automatic rewards. (3) Hybrid GUI and app-native tool use: We explore an experimental mobile-use setting where apps expose selected functionalities as app-native tools alongside their GUIs, allowing
agents to interleave GUI actions and tool calls within a task. We implement this setting in MobileGym++ with over 300 carefully scoped tools across 50+ apps. Additionally, we introduce MobileGym++ Bench for complex, long-horizon commercial mobile scenarios, supporting both GUI-only and hybrid GUI-tool evaluation on a shared task suite. OpenMobile-2 performs competitively across established
benchmarks, including AndroidWorld (79.9) and MobileWorld (50.4), while showing promising transfer to real-device mobile use, nearly doubling SPA-Bench performance from 31.9 to 59.6. All resources are available at https://os-copilot.github.io/OpenMobile2-Home/.
Read the full abstract ▾
All authors Chenyang Yan, Yingying Zhang, Kanzhi Cheng, Qiushi Sun, Zhengyuan Pan, Zheng Ma, Hang Yan, Yian Wang, Nuo Chen, Jialin Cao, Xingdong Gong, Wenpo Song, Han Chen, Zichen Ding, Fangzhi Xu, Shujian Huang, Xinyu Dai, Yichen Liu, Tiankuo Yao, Bo Wang, Ben Kao, Jianbing Zhang, Lewei Lu, Dahua Lin
Robotics
Axiom-0: Hierarchical Self-Refinement for Vision-Language-Action Policies
Renbin Shu, Jing Yang, Xiangyuan You et al. (+7 more)
Reliable manipulation requires policies that generalize across tasks, layouts, and object interactions.
Vision-
language-action (VLA) models combine pretrained
multimodal understanding with learned control, but their performance remains limited on unfamiliar task compositions. We present Axiom-0, a VLA policy that addresses both the quality of its representations and their use in action generation through hierarchical self-refinement. Intra-VLM Representation Refinement (IVRR) strengthens selected intermediate features through consistency supervision with learned feature projections during training. VLM-Action Interface Refinement (VAIR) recursively updates the resulting conditioning before action generation. Joint optimization of the supervised VLM layers, VAIR, and the action generator connects the two components. On RoboCasa365, Axiom-0 achieves 62.32% overall success in our evaluation, exceeding the highest published leaderboard score (Paimon-0, 58.1%) by 4.22 percentage points and the Xiaomi-Robotics-1 reference by 4.92 points. Under the evaluated profiling setup, mean action-chunk generation latency increases by 1.7% over Xiaomi-Robotics-1. These results demonstrate improved task completion with modest inference overhead.
Read the full abstract ▾
All authors Renbin Shu, Jing Yang, Xiangyuan You, Guolin Qiu, Yufei Xia, Yiming Zhu, Nanjun Dai, Fei Zhang, Feng Wu, Keke Tang
Computer Vision
TrajCFG: Token-Wise Classifier-Free Guidance via Denoising Trajectory Feedback
Jingyu Liu, Hao Jiang, Yikang Ding et al. (+6 more)
Classifier-free guidance (CFG) typically applies a shared scale to all latent
tokens, although their velocity predictions evolve differently during sampling. We introduce Trajectory-Adaptive Classifier-Free Guidance (TrajCFG), a training-free method for flow-matching models that adapts
token-wise guidance using historical changes in guided velocity direction. TrajCFG maps this feedback to bounded scales, assigning stronger guidance to larger directional changes and weaker guidance to more consistent directions. It combines adjacent-step and interval-normalized longer-span feedback, reusing standard CFG predictions without additional model evaluations. Controlled diagnostics and ablations examine the roles of directional feedback,
token-wise allocation, and history-span fusion. Experiments on text-to-
video, image-to-
video, text-to-audio-
video, text-to-image, and image-to-3D generation show improvements over base samplers across multiple backbones. For text-to-
video generation, TrajCFG improves VBench Total scores by 0.30-0.75 points over the strongest evaluated baseline on each of three backbones. These results support historical directional feedback as a broadly applicable signal for fine-grained guidance allocation. The project page is available at https://jyliu-98.github.io/trajcfg-project-page/.
Read the full abstract ▾
All authors Jingyu Liu, Hao Jiang, Yikang Ding, Huafeng Shi, Xu Yang, Xiaoqiang Liu, Guoxin Zhang, Pengfei Wan, Kun Gai
Artificial Intelligence · Cross-listed from eess.IV
Beyond Gate Weights: Decision-Level Interpretation of Radiomics-Image Feature Fusion for RCC Classification
Yuan Liang, Sourav Bhattacharjee and Abraham Campbell
Gate coefficients describe how a fusion layer weights intermediate features, but they do not necessarily reflect the magnitude of branch contributions at the classifier output. We investigate this distinction in a fixed 3D MedVAE–radiomics model for clear
cell versus non-clear
cell renal
cell carcinoma classification from contrast-enhanced CT. Because the model uses a linear classification head, the binary decision logit can be decomposed exactly into a gated image term, a direct radiomics term, and a bias. We define effective radiomics dominance as the direct radiomics term's share of the summed absolute non-bias branch contributions and compare it with structural radiomics weighting. Internally, mean structural radiomics weighting was 0.823, whereas mean effective radiomics dominance was 0.148, with a modest case-wise association (h̊o} = 0.290). The gated image term retained substantially stronger discriminative ranking information than the direct radiomics term. The same structural-to-effective discrepancy was observed in exploratory external evaluation. Branch-targeted permutation, integrated-gradient, and Shapley-style analyses further identified radiomics descriptors influencing the direct radiomics term. Because radiomics also generates the gate, the gated image term remains radiomics-dependent, so additive branch contribution should not be interpreted as total input influence. These findings show that structural gate weighting and decision-level branch contribution represent distinct aspects of gated feature fusion and should be interpreted separately.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.IV
Beyond Discrimination: Evaluating Probability Calibration in Radiomics-Image Fusion for Renal Cell Carcinoma Classification
Yuan Liang, Morgan May, Abraham Campbell et al. (+3 more)
Reliable probability estimates are important for the clinical interpretation of machine-learning classifiers, yet radiomics–image fusion models for renal
cell carcinoma (RCC) are commonly evaluated primarily by discrimination. Using 396 patients from the KiTS23
dataset, we evaluated whether adding radiomics to four image-model families improved probabilistic performance in addition to discrimination. Seventeen individual models and four probability-average ensembles were assessed using discrimination, probability calibration, and proper scoring measures. Across 12 matched image-only versus fusion comparisons, AUC and AP improved in all 12, while Brier score and negative log likelihood (NLL) improved in 11 of 12 and expected calibration error (ECE) in eight of 12. The 3D MedVAE gated-fusion model achieved the strongest overall individual-model profile. Probability averaging across concatenation, cross-
attention, and gated fusion produced favourable point estimates across all five primary metrics relative to image-only models in all four families, although paired-bootstrap support was stronger for Brier score and NLL than for ECE. These findings show that radiomics–image fusion can improve probabilistic prediction quality beyond discrimination, while calibration behaviour varies across image architectures and fusion strategies. We show that our proposed probability-average ensemble models improve discrimination and calibration simultaneously across all architectures in the study.
Read the full abstract ▾
All authors Yuan Liang, Morgan May, Abraham Campbell, Sourav Bhattacharjee, Simon Caton, Pierpaolo Dondio
Game Theory
Algorithms with Smoothed Polynomial-Time Complexity for Deterministic Discounted-sum and Mean-payoff Games
Ali Asadi, Krishnendu Chatterjee and Ruichen Luo
Turn-based deterministic games on graphs are two-player zero-sum games played on finite directed graphs, where the vertex set is partitioned between the Max and the
adversarial Min Player. The respective player chooses outgoing edges from their vertices. We consider these games with the classical discounted-sum and mean-payoff objectives. The goal of the Max Player is to maximize the objective against the
adversarial Min Player. These games lie in NP $\cap$ coNP and are among the rare combinatorial problems that belong to this complexity class, yet the existence of a
polynomial-time
algorithm is a major open question. All known deterministic
algorithms require exponential time in the worst case, while the classical strategy iteration (policy iteration)
algorithm is remarkably efficient in practice, which motivates the study of the smoothed complexity of these games. Previous results established a smoothed
polynomial-time bound only for the restricted class of ergodic games and presented only a high-probability guarantee. Our main result is a new analysis technique for a variant of the strategy iteration
algorithm, and we show these
algorithms achieve smoothed
polynomial complexity for general game graphs with both high-probability and expected runtime guarantees. In particular, our result removes the ergodicity restriction of prior work and strengthens the high-probability guarantee to the stronger expected-runtime guarantee, thereby resolving the open question on the smoothed complexity of these games.
Read the full abstract ▾
Artificial Intelligence
VETNET: Assembling Benchmark Datasets for AI-Driven Veterinary Innovation
Katherine J. Koebel, Renata Ivanek, Parminder Basran et al. (+33 more)
VETNET represents an ecosystem of live
benchmark datasets and evaluation frameworks designed to accelerate AI-driven innovation in animal science and veterinary medicine through standardized, high-quality
datasets and multi-institutional collaboration across academic and non-academic sectors. This framework addresses the gap between AI advances in human medicine and the fragmented state of veterinary AI development.
Read the full abstract ▾
All authors Katherine J. Koebel, Renata Ivanek, Parminder Basran, Jennifer Sun, Casey Cazer, Gayatri Anil, Tommaso Banzato, Liz Barton, Dottie Cimino Brown, Leszek Bukowski, Marta Castelhano, Simon Coghlan, Christopher De Sa, Nikki Dutta, Hala Ghali, Julio Giordano, Joshua Glass, David C. Hogg, Nicholas Hollingshead, Adam Kiehl, Ziang Liu, Monica Meduri, Param Mohapatra, Kim Nayyer, Amelia Nelson, Peter-John Mantyla Noble, Christopher Pinard, Beryl Rabindran, Scott Ross, Ron Seccia, Moira Sheehan, Fei Wang, Tracy L. Webb, Kilian Q. Weinberger, Heather M. Whitney, Chen Xin
Cryptography and Security
Memory-Coupled Unlearning for Data-Absent Identity Forgetting
Chun-I Fan, Lu-En Chen, Ming-Feng Tsai et al. (+1 more)
Machine unlearning aims to reduce the influence of designated training data from a trained model while preserving its utility on retained data. Identity-level unlearning is particularly challenging when only limited target-specific information is available when a forgetting request is processed. In this work, we propose
Memory-Coupled Unlearning (MCU), a framework that augments a host model with a Modern Hopfield Network (MHN) serving as a controllable external identity-prototype
memory. During prototype construction, feature representations associated with each training identity are aggregated into identity prototypes and stored in the MHN. A Prototype Adaptation Network (PAN) transforms the retrieved
memory representation, while a Dependency Gating Unit (DGU) controls its contribution to downstream prediction. When an identity is requested to be forgotten, MCU first removes the corresponding prototype from the external
memory and subsequently readapts the model using limited support information associated with the target identities together with retained data. Importantly, in this work, “data-absent” specifically refers to the absence of the complete original forget set during request-time gradient-based readaptation; retained data may still be used to preserve downstream-task utility. Experiments based on the identity-partitioning and one-shot support construction of 1-SHUI show that MCU achieves a favorable empirical trade-off among model utility, membership distinguishability, and request-time computational efficiency compared with the evaluated baselines. These results provide empirical evidence for the potential of controllable external
memory in machine unlearning, rather than a formal guarantee of complete information removal.
Read the full abstract ▾
All authors Chun-I Fan, Lu-En Chen, Ming-Feng Tsai, Tomohiro Morikawa
Artificial Intelligence
Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress
Zongxia Li, Zhongzhi Li, Yucheng Shi et al. (+14 more)
Long-horizon terminal
benchmarks measure whether an
agent can sustain progress through extended workflows with process rewards, not only whether its final state passes a binary check. We present Long-Horizon-Terminal-Bench 2.0 (LHTB 2.0), an extension of Long-Horizon-Terminal-Bench that preserves its 46 original tasks while correcting task and evaluation-infrastructure defects and extending 31 tasks. LHTB 2.0 contains 77 tasks across 13 domains and eight task types. The extended tasks are produced through a systematic reconstruction-task pipeline. We start from a working scientific or engineering artifact, then use a parameterized reference implementation to generate multiple scenarios, reveal six as behavioral evidence, hold out three for evaluation, and use dense progress ladders to reward partial progress while preventing memorization of public outputs. We also extend the evaluation horizon from 90 minutes to three hours and record verifier checkpoints every 30 minutes, enabling direct measurement of sustained progress within a run. Across 1,145 scored model-task runs from 15 frontier models, GPT-6-astra leads with dense mean reward 0.69 and 37 tasks at R at least 0.95, followed by GPT-5.6-sol with dense mean reward 0.67 and 32 tasks at the same threshold. On the 30 reconstruction tasks, binary verifier scores average 0.221, whereas dense ladder scores average 0.653, showing that outcome-only evaluation discards substantial intermediate progress. LHTB 2.0 provides a broader, hardened, and process-aware testbed for studying reliable
agent execution over hours.
Read the full abstract ▾
All authors Zongxia Li, Zhongzhi Li, Yucheng Shi, Ruhan Wang, Junyao Yang, Chengsong Huang, Zhichao Liu, Xiyang Wu, Anhao Li, Yue Yu, Ergan Shang, Fuxiao Liu, Tong Zheng, Ninghao Liu, Lichao Sun, Haitao Mi, Leowei Liang
Computer Vision · Cross-listed from eess.IV
C$^2$LUE: Clinically Aligned Patient-Level Ultrasound Diagnosis via Evidence-Aware Multi-Instance Learning
Qin-Yi Zhang, Linying Cao, De-Xing Huang et al. (+7 more)
Patient-level ultrasound diagnosis demands not only high predictive accuracy but also clinically aligned mitigation of asymmetric diagnostic risks. While Multi-Instance Learning (MIL) effectively models routine multi-view exams, standard aggregators often dilute heterogeneous diagnostic cues and optimize solely for global accuracy. This frequently yields undesirable sensitivity-specificity trade-offs. To bridge this gap, we propose C$^2$LUE, a novel MIL framework coupling evidence aware aggregation with risk-aligned regularization. To preserve evidence heterogeneity and prevent unimodal
attention collapse, C$^2$LUE employs a multi-query cross-
attention mechanism built upon a LoRA-adapted DINOv3 backbone. Multiple latent queries explicitly extract and disentangle diverse morphological patterns from the ultrasound sequence. Furthermore, to improve clinical risk
alignment, we introduce a dynamic trade-off regularization objective that penalizes sensitivity-specificity imbalance during training. Rather than leaving the clinical trade-off entirely to post-hoc threshold adjustment, this objective encourages the learned score distribution toward a more balanced operating region. Extensive evaluations on patient-level, biopsy-proven thyroid and breast ultrasound
datasets demonstrate that C$^2$LUE consistently outperforms prior alternatives. By uniting strong discrimination with a balanced error profile, C$^2$LUE provides a promising solution for real-world ultrasound screening and diagnosis.
Read the full abstract ▾
All authors Qin-Yi Zhang, Linying Cao, De-Xing Huang, Haichuan Lin, Yi Yang, Manzhi Wang, Xiao-Hu Zhou, Chen Chen, Shuangyi Wang, Zeng-Guang Hou
Robotics
Refine Where It Matters: Contact-Adaptive Meshing for Deformable Object Manipulation
Gabriel Johnson, Tom Olesch and Fei Liu
Deformable-object manipulation requires accurate modeling of highly localized contact while maintaining simulation speeds suitable for interactive use. Uniformly fine tetrahedral meshes can resolve these interactions, but they introduce unnecessary degrees of freedom throughout the object. Coarse meshes are more efficient, yet they may under-resolve contact-induced deformation. We present a contact-adaptive mesh refinement framework that introduces spatial resolution only where it is most useful. The method uses
geometric, elastic, and contact quantities already available from the deformable-body solver to score candidate edges. A fully GPU-parallel procedure then selects a conflict-free subset and updates both mesh
topology and physical state directly within the simulation loop. We evaluate the approach on real deformable-object manipulation sequences. Adaptive refinement reduces simulation-to-real error, improves agreement with a fine-mesh reference, and remains substantially more efficient than uniformly fine simulation. These results show that local refinement can improve physical fidelity without incurring the cost of a globally fine discretization. The framework provides a practical basis for contact-rich simulation in interactive manipulation, sim-to-real modeling, and online physical digital twins.
Read the full abstract ▾
Sound
MixedTruth: Component-Level Detection of Synthetic Speech and Synthetic Background in Mixed Audio
Xindong Zheng, Jiashu Zhu, Ke Li et al. (+1 more)
Modern generative audio can fabricate not only voices but also the acoustic environments that provide evidence of when and where
speech occurred. This capability undermines a longstanding forensic assumption that background sound provides reliable evidence of a recording's provenance. Yet existing detectors produce only a single real-or-synthetic verdict, leaving analysts unable to determine whether the voice, the environment, or both were manipulated. In this paper, we propose a component-level forensic detector, namely TruMix, which classifies recordings into eight categories spanning the presence and authenticity of
speech and background. TruMix has a unique multi-path architecture that jointly analyzes
speech-oriented and background-oriented spectral evidence, contextual information from the mixed waveform, and low-level synthesis artifacts. This design avoids the artifact propagation inherent in conventional separate-then-detect pipelines while enabling generalization across independent
speech and environmental-sound generators. We also curated MixedTruth, a 4,917-hour
benchmark covering all eight categories under diverse mixing conditions. Extensive experiments show that TruMix achieves 98.51% AUC for component-level attribution, significantly outperforms ten state-of-the-art synthetic-
speech detectors in conventional binary classification, and exhibits strong robustness across four attack tiers.
Read the full abstract ▾
All authors Xindong Zheng, Jiashu Zhu, Ke Li, Dan Lin
Computer Vision · Cross-listed from eess.IV
Frozen Site-Probe Accuracy Is Not a Standalone Harmonization Score: An Audit of Evaluation Practice for Multi-Site MRI
Muhammad Muqsit Islam, Gloria García Cuenco, José M. Martínez et al. (+1 more)
Image-level MRI harmonization is often evaluated with a frozen site probe, a site classifier trained on raw scans and applied unchanged to harmonized ones: a drop in its accuracy is read as removal of site effects. We audit this practice on ABIDE I (1,112 T1-weighted scans, 17 sites) with ten output sets from seven harmonization methods and controls for chance, head shape, intensity, preprocessing and target
alignment. We find that this verdict depends on how the probe is trained, even among probes that classify raw scans well: across random seeds, its balanced accuracy on the same CycleGAN outputs ranges from 0.13 to 0.59 (chance: 0.06). Low frozen-probe accuracy can also arise without harmonization: a Gaussian blur, which increases the intensity distance to the target site, lowers this accuracy to chance. Moreover, where the frozen probe fails, probes trained on the harmonized scans still recover the site, even from intensity histograms alone: on HACA3 outputs, the frozen probe scores 0.25, a probe trained on those outputs 0.75, and one using only their intensity histograms 0.71. Low frozen-probe accuracy therefore does not show that site information has been removed. We recommend reporting several probes trained to convergence, probes trained on harmonized scans, and target
alignment.
Read the full abstract ▾
All authors Muhammad Muqsit Islam, Gloria García Cuenco, José M. Martínez, Pierrick Coupé
Computer Vision · Cross-listed from eess.IV
Exploring the Latent Structure of AMD Severity Using Retinal Foundation Models
Niccolò Fineschi, Jovana Panic, Atsushi Watanabe et al. (+7 more)
Retinal foundation models have demonstrated strong performance across a wide range of ophthalmic tasks, yet relatively little is known about how disease-related information is represented within their learned
embeddings and whether this distribution influences downstream prediction performance. In this work, we use Age-related Macular Degeneration (AMD) as a case study to investigate how disease severity is represented within the
embedding space of RET-CLIP, a retinal
vision-
language foundation model, using bilateral fundus images from the AREDS
dataset, benchmarked against non-retinal encoders. We first characterize the distribution of AMD severity within the learned representation space and then evaluate how this structure influences classification performance across three clinically relevant task formulations of increasing granularity. Finally, we analyze the most influential latent dimensions combining feature attribution, statistical phenotype association, and qualitative image analyses. Our results show that RET-CLIP represents AMD severity as a continuous spectrum rather than a set of discrete categories, with healthy and advanced disease stages exhibiting clearer separation than intermediate ones. This organization was reflected in downstream performance, which decreased from a balanced accuracy of 0.844 and 0.814 for binary AMD and Late-AMD detection respectively to 0.446 for six-class grading. Furthermore, the most influential latent dimensions were statistically associated to distinct retinal phenotypes, including drusen accumulation, pigmentary alterations, and advanced retinal lesions. These findings suggest that the structure of retinal foundation-model representations influences the difficulty of clinically relevant prediction tasks and demonstrate the potential of representation-level analysis for understanding disease organization and improving interpretability.
Read the full abstract ▾
All authors Niccolò Fineschi, Jovana Panic, Atsushi Watanabe, Hideaki Hayashi, Kazuya Nishimura, Yuki Maeno, Samanta Rosati, Gabriella Balestra, Kohji Nishida, Hajime Nagahara
Artificial Intelligence
Correction Training for Diffusion Models
Donghoon Ahn, Runqian Wang, Alexei A. Efros et al. (+2 more)
Iterative sampling in
diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with noise, but at inference its inputs are constructed from its own imperfect predictions from the earlier steps, something it has never seen at training time. This might be one reason
diffusion models often struggle without additional help, such as CFG. We introduce a correction step for
diffusion models which attempts to reduce this training-inference gap. The corrector takes the base model's prediction as input and is trained against the same ground-truth target. This makes correction an explicit learning task, with training inputs provided by the base model. During sampling, at each denoising step, we iteratively refine the denoiser's clean-sample prediction. This allows us to correct predictions at intermediate denoising steps, preventing early artifacts from persisting into the final sample. Although the corrector is trained only on predictions from the base denoiser, it can be applied repeatedly to its own outputs at inference for better results. This simple framework leads to substantial improvement in sample quality while largely preserving diversity. We evaluate our method across DiT, SiT, and JiT. Our method substantially improves upon previously reported FID scores for unguided generation and, notably, unconditional generation, where producing high-quality samples without guidance has been particularly challenging. Our method achieves performance competitive with classifier-free guidance (CFG), and combining correction with CFG further improves diversity and reduces oversaturation typical of CFG. Finally, we show that the additional inference cost of correction can be amortized by distilling the refined predictions back into the base
diffusion model, retaining the quality gains without additional inference-time overhead.
Read the full abstract ▾
All authors Donghoon Ahn, Runqian Wang, Alexei A. Efros, Taesung Park, Yash Belhe
Machine Learning · Cross-listed from stat.ML
Stanislas Strasman
Generative modelling involves two complementary tasks: learning a probabilistic approximation of an unknown data distribution from observations, and designing a tractable mechanism for sampling from this approximation. We present a
stochastic-analysis perspective on score-based generative models, connecting ideas from classical sampling theory, score estimation, and
diffusion time reversal. We first explain how score functions link Langevin sampling with score matching, and how Gaussian smoothing leads to denoising score matching and multiscale sampling methods. We then emphasize the distinction between dynamics preserving a fixed distribution and dynamics transporting a prescribed family of marginals. This motivates a path-space treatment of
diffusion time reversal. Finally, we connect the ideal reverse
diffusion with practical generative
algorithms.
Read the full abstract ▾
Cryptography and Security
TrustPaper for forged PDF with Issuer Fingerprints
Yassine El Jakani, Mohamed Nadir Rhazi, Othmane Meknassi et al. (+3 more)
Sick leave certificates are increasingly delivered as PDF files by online teleconsultation platforms, and can be altered in minutes with free editors. Generic PDF scanners report how a file was built, but cannot tell whether that construction is legitimate: an incremental update, an embedded font or a given producer string is normal for one issuer and anomalous for another. We present TrustPaper solution, an issuer aware forensic approach that combines three elements: the claimed issuer of the document, a reference fingerprint learned beforehand from genuine documents of that issuer, and an explainable combination of evidence from several forensic modules. Fingerprints are stored as versioned declarative profiles, and every anomaly keeps its observed value, expected value and triggering rule. We formalize the threat model, the fingerprint and the scoring model, and evaluate the open-source prototype on a controlled corpus documents from two issuers and six forgery techniques. With the issuer fingerprint, all forgeries made by opportunistic and metadata-aware attackers are flagged with no false positive on genuine test documents.
Read the full abstract ▾
All authors Yassine El Jakani, Mohamed Nadir Rhazi, Othmane Meknassi, Oualid Chbiki, Mounira Msahli, Francois Gonnet
Machine Learning · Cross-listed from cond-mat.dis-nn
On physical implementability of reinforcement-learning-driven reasoning
Eiji Konishi
In the machine learning community, the reinforcement-learning-driven
reasoning process has been intensively studied since around 2025. In this article, we present a negative result on the hardware implementation of this reinforcement-learning-driven
reasoning process in a physical neural network model in the presence of a reward external potential energy for a given reward. In this hardware implementation, the existence of a chain of thought in dynamics contradicts the Lyapunov stability of the system.
Read the full abstract ▾
Software Engineering
Conserved amount, negotiable placement. Prompting perturbs one architecture, an AI reviewer both
Daniel Sagenschneider
Tesler's conservation law holds that a problem carries an irreducible amount of complexity. Brooks separates that essential part from the accidental part a solution adds. If the essential part is fixed, architecture is placement rather than quantity, and the question is which levers move placement. An AI
agent implements sixty accumulating change requests on one REST endpoint under two architectures, a mutative Spring controller and an additive OfficeFloor pipeline, under five conditions, ten runs per
cell, model fixed. Four are external controls, from a bare change request to the disclosed structural cost function. The fifth is different in kind. A second
agent reviews each change and reasons about cohesion itself. Amount is steady. Across all ten
cells the finished complexity varies by 7% to 20% over four operationalisations, and the complexity the sixty rules added by 21% to 29% within an architecture. Placement is not. Under the four external controls the plasticity ratio between the architectures is near 1 on six amount metrics (five of six intervals contain 1) against 2.7 to 10.0 on eleven placement metrics (ten of eleven above 1). The mutative architecture moves, the additive one does not, and the disclosed formula brings it to the additive arm's untouched placement. The AI reviewer is the one lever that moves the additive arm, on one family only. It consolidates the pipeline, raising change- and mass-concentration on every such metric, interval excluding zero, while leaving coupling, file count and per-node complexity untouched. The price is reported in full. Strict correctness fell in most comparisons though each rule was implemented correctly in over 99% of checkpoints, and all three outcome measures favour the concentrated codebase. The contribution is a measurable property of an architecture and its lever, not a verdict on either.
Read the full abstract ▾
Information Theory
Quantum Annealing for Resource Allocation in Next-Generation Wireless Communication Networks: A QUBO Modeling Guide
Nguyen Xuan Tung, Le Tung Giang, Mai Dinh Cong et al. (+4 more)
Quantum annealing (QA) offers a physics-inspired approach for such subproblems by mapping them onto an Ising
Hamiltonian, which is algebraically equivalent to a Quadratic Unconstrained Binary Optimization (QUBO) model executable on
quantum annealers or hybrid solvers. However, their practical employment in wireless systems critically depends on the specific problem formulation, on the particular variable encoding, constraint handling, solver selection, hardware
embedding, and fair benchmarking. This paper develops wireless-oriented QUBO modeling guidelines for QA-assisted resource allocation. We first present a beginner-friendly toy example in which a terrestrial-aerial resource-allocation problem with a fractional signal-to-interference-plus-noise ratio (SINR) maximization objective is reformulated into a two-bit QUBO via Boolean interpolation, converted into an Ising representation, and decoded back into a wireless scheduling decision. The same scheduling is applicable to
UAV, aircraft, satellite, and terrestrial links in SAGIN systems. We then review the QA foundations and solver ecosystems, including binary quadratic, discrete quadratic, constrained quadratic, and hybrid models from the perspective of NG wireless optimization. Furthermore, we discuss both binary and discrete encoding, penalty-based constraint conversion,
embedding overhead, solution decoding, and feasibility verification. A QUBO Compatibility Index is introduced as a lightweight diagnostic metric for assessing the associated QUBO formulation readiness, rather than a predictor of runtime or solution quality. Finally, a case study on max-min uplink power control in
cell-free massive
MIMO illustrates how a
fairness-oriented wireless problem can be discretized, constrained, converted into the concept of a QUBO, and evaluated against classical baselines. A host of key challenges and future directions are also discussed.
Read the full abstract ▾
All authors Nguyen Xuan Tung, Le Tung Giang, Mai Dinh Cong, Pham Dang Anh Duc, Nguyen Hoang Viet, Trinh Van Chien, Lajos Hanzo
Human-Computer Interaction
The AI's Poker Face: Contrasting Persuasion and Sycophancy in Voice-Based Multi-Turn Conversations
Ilia Frantzi, Bernie Hogan, Max M. Lang et al. (+1 more)
As interactions with large
language models (LLMs) become increasingly routine, concerns about their capacity to influence users' beliefs grow. Yet how such influence unfolds in sustained dialogue remains insufficiently understood. We conduct a randomized controlled experiment (N=616) where participants engage in multi-turn, spoken dialogue with an LLM under three conditions: non-directive, and two directive conditions maintaining opposing stances on a polarizing topic (the merits of feminism). We examine opinion change, rhetorical strategies, and sycophancy, distinguishing the semantic content of LLM argumentation from the pragmatic strategies used to manage the interaction. Both directive conditions shifted opinions toward their assigned stances, but asymmetrically: shifts were larger for pro-feminist positions, which also elicited distinct rhetorical strategies. The non-directive condition, likewise shifted opinions pro-feminism. Social sycophancy, though near-universal, was not associated with opinion change; instead it shaped users' subjective experience. Our findings highlight distinct roles for argumentation and sycophantic accommodation in AI influence.
Read the full abstract ▾
All authors Ilia Frantzi, Bernie Hogan, Max M. Lang, Paul C. Bauer
Machine Learning · Cross-listed from cond-mat.mtrl-sci
Hierarchical Multi-Agent Reasoning Systems for Knowledge-Grounded Material Substitution
Tarjei Paule Hage, Subhadeep Pal, Wei Lu et al. (+4 more)
AI-assisted scientific discovery increasingly seeks to move beyond generating plausible ideas toward reproducible, constraint-aware workflows that can support practical engineering decisions. We present MARS, a hierarchical Multi-
Agent Reasoning System for knowledge-grounded material substitution under scientific and manufacturing constraints. We apply MARS to replace per- and polyfluoroalkyl substances (PFAS), a demanding materials-design problem in which substitutes must satisfy functional performance, environmental, experimental, and processing requirements. MARS decomposes substitution into a closed-loop workflow comprising requirement analysis, grounded candidate generation, and manufacturability assessment with process design. The system integrates
retrieval-augmented generation, knowledge-graph
reasoning, a database of lab-available materials, persistent
memory of intermediate results, and rejection-aware iterative feedback. In a PFAS-substitution case study, MARS generates structured material requirements, identifies an evidence-grounded substitute candidate, and develops a lab-scale manufacturing route. In a multi-seed ablation evaluation, MARS achieves the highest overall performance across all three subsystems, with gains that persist when the backbone model is held fixed. These results suggest that hierarchical decomposition, knowledge grounding, and manufacturability-aware refinement improve material-substitution
reasoning beyond model capability alone.
Read the full abstract ▾
All authors Tarjei Paule Hage, Subhadeep Pal, Wei Lu, Yu-Chuan Hsu, Gayla Lyon, Jiezhu Jin, Markus J. Buehler
Machine Learning · Cross-listed from q-fin.RM
Early Detection of Pension-Sponsor Distress from Public Filings: A Sponsor Vulnerability Index, Stress-Augmented VaR, and Dynamic Self-Investment Caps
Ravil Akhtyamov
A defined-benefit pension is only as safe as its sponsor, yet sponsor distress is under-instrumented relative to plan-side modelling. We present a transparent, reproducible early-warning pipeline built entirely on public data. A Sponsor Vulnerability Index (SVI), a gradient-boosted classifier over point-in-time SEC EDGAR balance-sheet fundamentals and two macro series, predicts a filings-based distress state one to two quarters ahead. On 36 U.S. sponsors in five sector groups (1,418 firm-quarters, 2015Q1-2025Q3) it reaches an out-of-fold AUC-ROC of 0.887 and PR-AUC of 0.711 (base rate 11.9%) under leave-one-firm-out cross-validation. A Monte Carlo VaR with a stylized transition-stress overlay shows that
climate-type stress is negligible for a diversified plan but adds 20-43% to one-year 95% VaR when 22.5% of assets are held in sponsor securities. A dynamic self-investment cap maps the SVI to a limit that falls from 8% to below 1% in acute distress and recovers with the sponsor, which we illustrate on PG&E's 2019 bankruptcy and Boeing's persistent fragility. We report the method's failure modes alongside its results (book-equity labels that also fire on non-credit events such as
spin-offs, positives concentrated in one firm, and stylized stress parameters) and release code, data and results under a concept DOI.
Read the full abstract ▾
Artificial Intelligence
ClawLoop: Self-Improving Agents via Harness-Native Training Loop
Hansi Yang, Linji Hao, Hongyan Hao et al. (+4 more)
The rapid advancement of Large
Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based
agents operate in sandbox workspaces and interact directly with file systems and shells. While numerous post-training pipelines exist for tool-use
agents, their counterparts for harness-based
agents remain scarce and are predominantly one-shot and teacher-dependent: a stronger external model synthesizes tasks and collects trajectories, the target
agent is trained once, and evaluation results are consumed by human researchers rather than fed back into the loop. Such pipelines are inherently bounded by the capability of the external model and the scope of human prior, leaving no room for self-improvement. To address these limitations, we propose ClawLoop, a framework that enables self-improving without any external teacher model and with minimal prior dependencies. ClawLoop composes three phases into a self-sustaining cycle: Task Synthesis, which generates a diverse pool of training tasks via two complementary construction routines, applies diagnosis-conditioned difficulty growth followed by both
agent-free and
agent-based task validation; Training, which updates the
agent via SFT and/or RL; and Diagnosis and Feedback, which analyzes the
agent's rollout behaviors to produce a capability analysis report that will be used as feedback for task synthesis in the next iteration. Using Qwen3.6-27B as the loop model, ClawLoop yields consistent improvements on SkillsBench, Claw-Eval-Live, and ClawGym-Bench. The iteratively refined tasks are further transferred to smaller-scale Qwen3.5-4B and 9B models with gains across all
benchmarks, validating data quality independently of the loop model.
Read the full abstract ▾
All authors Hansi Yang, Linji Hao, Hongyan Hao, An Wang, Han Wu, Qi Gu, Xunliang Cai
Robotics
Make {\pi}0.5 Learn to Call Astra for Reliable Robot Manipulation
Jianli Sun, Chengxiang Li and Yonglin Tian
GPT-6 Astra provides robust embodied
reasoning, but frequent external queries increase inference time and
token costs. We equip a frozen $\pi_{0.5}$ policy with a lightweight CALL head that learns to predict when assistance is necessary. CALL reuses features from the standard policy forward pass and operates locally without consulting external models. Astra is activated solely for critical recovery events and returns control to $\pi_{0.5}$ upon stabilization. Evaluated across 40 LIBERO tasks (200 episodes), our system achieves a 97.5% success rate, outperforming the 95.5% baseline of pure $\pi_{0.5}$. In the Object, Goal, and Spatial suites, Astra executes only 5.49% of environment steps, consuming approximately 5,027
tokens per test episode. This selective intervention preserves the fast ordinary execution of $\pi_{0.5}$ while seamlessly integrating Astra's
reasoning on demand. Our project page is available at https://kykgeek.github.io/Pi05_CALL_Astra/.
Read the full abstract ▾
Cryptography and Security
An Empirical Case Study of Prompt Engineering Strategies for Bypassing Multi-Layer Agent Security Defenses
Chengwei Chu
The OpenClaw Security Attack and Defense Challenge evaluates AI
agent robustness through a three-stage defense pipeline: skill file scanning (Stage 1), instruction safety evaluation (Stage 2), and attack trajectory scoring (Stage 3). This paper presents an empirical case study of
prompt engineering strategies against these layers across 19 attack targets in Enterprise OA, E-commerce, and Smart Home scenarios. I document both successful and failed strategies, with an emphasis on the observed trade-off between instruction safety (Stage 2) and attack execution accuracy (Stage 3). The final online score is 0.2630, with 5 of 19 tasks achieving full bypass. The results suggest that multi-layer defenses, reinforced by built-in behavioral constraints, substantially limit what
prompt engineering alone can achieve.
Read the full abstract ▾
Artificial Intelligence
The Silent Failures in Agentic Data Science
Xue Li, Hongqian Xia, Daniel Gomm et al. (+3 more)
Large
language models have significantly lowered the barrier to writing code. Naturally, this has also led to the development of data science
agents that promise automating the design and execution of data science from task formulation to model development. Existing evaluations of agentic data science (agentic DS) assess downstream predictive performance and code correctness, providing preliminary insight in agentic DS capabilities. We argue that these evaluations overlook the fundamental principles of data science: methodological data science- and domain knowledge. As such, only assessing downstream performance masks methodological failures such as data leakage and inappropriate validation, limiting the development of robust agentic DS systems. In this paper, we evaluate agentic DS beyond accuracy from three different angles: 1) a large-scale analysis of failure modes in common agentic DS frameworks and models across 220 data science tasks, 2) a reusable and extensible test suite with curated data science tasks that test for six specific failures in a controlled manner, and 3) a qualitative assessment of agentic DS pipelines against expert solutions on Kaggle competitions. We find that the majority of agentic solutions contain at least one failure mode despite the complexity of agentic harness or model capacity. Moreover, we identify a positive correlation between the occurrence of data leakage failures and predictive performance, confirming the necessity to evaluate
agents beyond accuracy. Our qualitative analysis shows that DS
agents generally lack problem solving creativity and domain knowledge, compared to competition-winning data scientists. We believe that principled failure mode analysis, as presented here, should be integral part of agentic DS evaluations, and that the insights we surface will be key in developing trustworthy agentic DS pipelines.
Read the full abstract ▾
All authors Xue Li, Hongqian Xia, Daniel Gomm, Aécio Santos, Cornelius Wolff, Madelon Hulsebos