Artificial Intelligence · Cross-listed from cs.CV
NaviCache: Test-Time Self-Calibration Caching for Video Generation
Zheqi Lv, Zhibo Zhu, Jinke Wang et al. (+6 more)
Video Diffusion Models (VDMs) is constrained by immense computational costs. While offline calibration-based acceleration suffers from calibration data dependency, prohibitive calibration duration, and susceptibility to distribution shifts, offline calibration-free methods eliminate these hurdles. However, since they rely on instantaneous zero-order approximations where the mapping between input and output differences varies in real-time, they are susceptible to observational noise and ignore the intrinsic momentum within the
diffusion trajectory. In this paper, we propose NaviCache, a plug-and-play test-time self-calibration method re-conceptualizing feature
evolution as an Inertial
Navigation System (INS) problem. NaviCache bridges the fundamental domain gap and the non-stationary nature of
diffusion by modeling the relative coupling between input and output variations. We introduce a dual-state estimation architecture that adaptively tracks the feature change ratio and its latent drift, initialized via a specialized Initial
Alignment phase. By integrating a time-dependent noise schedule with an uncertainty-aware Measurement Update mechanism, NaviCache provides a theoretically grounded mechanism for error-bounded computation skipping. Extensive experiments on the HunyuanVideo, Wan, and Open-Sora series demonstrate that NaviCache exhibits more accurate error judgment for computation skipping and achieves outstanding comprehensive performance.
Read the full abstract ▾
All authors Zheqi Lv, Zhibo Zhu, Jinke Wang, Qi Tian, Shengyu Zhang, Zhengyu Chen, Chengxi Zang, Zhou Zhao, Fei Wu
Artificial Intelligence · Cross-listed from cs.CV
ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP
Sicheng Zhang, Muzammal Naseer, Binzhu Xie et al. (+5 more)
CLIP and its variants are widely adopted visual backbones in
multimodal systems, but their pretraining remains dominated by descriptive image-text
alignment. As downstream applications increasingly demand visually grounded commonsense inference and compositional
reasoning, it remains unclear whether CLIP-style encoders can support such
reasoning without architectural changes. To address this, we present ReasonCLIP-58M, a continual pretraining framework that integrates large-scale
reasoning supervision into CLIP-style models through our two-stage strategy, which progressively integrates
reasoning signals while preserving descriptive
alignment, followed by category-structured
reasoning supervision. To support this framework, we construct two complementary
datasets and a
benchmark: ReasonLite-42M, with open-form, visually verifiable
reasoning captions; ReasonPro-16M, with category-specific
reasoning supervision; and RCLIP-Bench for diagnostic evaluation of visually grounded
reasoning. We train a family of ReasonCLIP that improves visually grounded commonsense and compositional
reasoning while also enhancing zero-shot
retrieval performance. As a drop-in visual encoder for
multimodal large
language models such as LLaVA-NeXT, ReasonCLIP delivers consistent gains without additional inference cost, demonstrating that structured
reasoning supervision enhances the expressive capacity of CLIP-style visual representations. All
datasets, models, and training code are available at https://github.com/RISys-Lab/ReasonCLIP.
Read the full abstract ▾
All authors Sicheng Zhang, Muzammal Naseer, Binzhu Xie, Naufal Suryanto, Shi Qiu, Jamal Bentahar, Naveed Akhtar, Mubarak Shah
Artificial Intelligence · Cross-listed from cs.CR
MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG
Inderjeet Singh, Andrés Murillo, Motoyoshi Sekiya et al. (+2 more)
Multimodal agentic
retrieval-augmented generation (RAG) systems expand the attack surface beyond
prompt injection to include text poisoning, image injection, direct-query attacks, and orchestrator-level tool manipulation. Existing red-teaming approaches are typically surface-specific and often recycle known attack templates; on text-poisoning
benchmarks we measure 73-84% exact duplication. We present MIRROR, a unified cross-surface framework that performs
memory-guided Monte Carlo tree search while conditioning candidate generation on retrieved context under an explicit novelty constraint. A deterministic Novelty Gate rejects any candidate matching the
retrieval set under normalized comparison, allowing
retrieval to inform search priors without enabling
prompt copying. Across four attack surfaces on a
multimodal agentic RAG target, MIRROR attains 76% ASR on image poisoning compared with 52% for baselines, 97% ASR on orchestrator attacks at half the query cost, and the lowest cross-surface variance (coefficient of variation 0.47). In contrast, specialized baselines collapse across surfaces: suffix optimization reaches 79% ASR on text poisoning but 1% on direct queries. We release ART-SafeBench with 41,815 in-package records and runtime adapters yielding 41,991+ total records across four surfaces.
Read the full abstract ▾
All authors Inderjeet Singh, Andrés Murillo, Motoyoshi Sekiya, Yuki Unno, Junichi Suga
Artificial Intelligence · Cross-listed from cs.LG
AIGP: An LLM-Based Framework for Long-Term Value Alignment in E-Commerce Pricing
Chennan Ma, Yanning Zhang, Siqi Hong et al. (+3 more)
Traditional dynamic pricing models in large-scale e-commerce suffer from limited interpretability, poor utilization of unstructured information, and misalignment with long-term business objectives such as cumulative Gross Merchandise Value (GMV), Return on Investment (ROI) and milestone achievement. We propose AIGP, a novel framework that leverages a Large
Language Model (LLM) prompted with domain knowledge, structured data and textual context to make interpretable, knowledge-aware pricing decisions. For efficient deployment while maintaining high-quality outputs, we employ supervised fine-tuning for knowledge
distillation. Central to AIGP is the Long-Term Value
Estimator (LTVE), trained via offline reinforcement learning on historical data, which serves as a reward model to score candidate pricing actions and select preference pairs for Direct Preference Optimization (DPO), thereby aligning the pricing policy with long-term business objectives. Extensive offline evaluations and large-scale online A/B tests on Tao Factory demonstrate that AIGP achieves significant improvements: +13.21% in GMV, +7.59% in ROI, and +8.20% in milestone achievement rate over 14 days compared to the production baseline, while simultaneously providing interpretable and transparent pricing rationales.
Read the full abstract ▾
All authors Chennan Ma, Yanning Zhang, Siqi Hong, Xiuchong Wang, Fei Xiao, Keping Yang
Artificial Intelligence
ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration
Qicheng Zhao, Yu Li, Qi Sun et al. (+1 more)
The adoption of powerful
diffusion models is hindered by their significant inference latency. Recent “cache-then-forecast” schemes alleviate this issue by accelerating DiTs using derivative-based
polynomials, but they suffer from severe quality degradation at high acceleration ratios. Our analysis reveals its root cause: the discrete extrapolation performed on representations that are misaligned with the continuous
diffusion trajectory and are numerically unstable. Thus, accelerated DiTs suffer from accumulated spatial errors, noisy derivative amplification, and high-order instability. We therefore reformulate accelerated inference as stable macro-trajectory extrapolation in ordinary differential equation (ODE) space. Instead of predicting intermediate features, we align
forecasting with the model's Global Drift (GD), i.e., the end-to-end state
evolution, thereby eliminating feature inconsistency and
memory overhead. However, even this smooth macro-trajectory remains vulnerable to the derivative fallacy: its higher-order temporal derivatives are intrinsically noisy. Thus, we introduce a derivative-free barycentric Lagrange extrapolator to effectively bypass derivative instability and approximation error. We further propose a bounded Phase Mapping that regularizes the extrapolation domain, suppressing oscillatory error growth. These elements collectively constitute ResilPhase, a noise-resilient acceleration framework. Experiments on FLUX.1-dev and HunyuanVideo demonstrate state-of-the-art fidelity under aggressive acceleration ratios.
Read the full abstract ▾
All authors Qicheng Zhao, Yu Li, Qi Sun, Zheyu Yan
Artificial Intelligence · Cross-listed from cs.CV
Anatomy-Guided Residual Motion Diffusion for Controllable 4D Cardiac MRI Synthesis
Yiheng Cao, Gustavo Andrade-Miranda, Jiatian Zhang et al. (+2 more)
Developing robust artificial intelligence models for 4D (3D + time) medical imaging is constrained by limited annotated data, inter-device domain shifts, and
privacy restrictions. To address this, we propose a 4D controllable generative framework for anatomically consistent data augmentation. A semi-supervised variational autoencoder learns a compact latent representation of anatomical volumes while jointly predicting aligned
segmentation masks in a unified framework. Anatomical structure is then disentangled from temporal dynamics through a cascaded latent
diffusion model (LDM). A static LDM generates subject-specific anatomy conditioned on clinical priors (diagnosis and volumes measures) and a subsequent motion LDM estimates residual latent motions, ensuring strict temporal coherence across the 4D sequence. The proposed approach was evaluated on cine cardiac MRI as a representative 4D imaging application. Experiments across multiple
datasets demonstrate high controllability of static anatomy (Pearson r > 0.8) and strong temporal coherence (FVD = 288.08). In cross-vendor generalization experiments, augmenting training sets with synthetic 4D sequences significantly improves downstream
segmentation performance. Using nnU-Net, the proposed augmentation strategy improves the average Dice score by 1.4% and reduces the Hausdorff Distance by 3.0mm compared to training on real data alone, for the left ventricle, Dice improves by 2.8% with a 5.4mm reduction in boundary error. Overall, this framework provides a scalable and controllable solution for 4D medical image synthesis, supporting the development of more robust models with limited annotations and cross-vendor variability. Code available on https://github.com/cyiheng/4DCardiacMRISynthesis.
Read the full abstract ▾
All authors Yiheng Cao, Gustavo Andrade-Miranda, Jiatian Zhang, Lingxiao Zhao, Xin Gao
Artificial Intelligence
EGG: An Expert-Guided Agent Framework for Kernel Generation
Yaochen Han, Ke Fan, Hongxu Jiang et al. (+5 more)
High-performance GPU kernels are critical for reducing the exponentially growing computational costs of large
language models (LLMs), but their development heavily relies on manual tuning by domain experts. While recent advances in LLM-based approaches show promise for automating kernel generation, they still struggle to achieve both correctness and high performance. This limitation primarily arises from the lack of domain-specific optimization guidance, hindering effective exploration of the optimization space. We propose EGG, an Expert-Guided
Agent Framework for Kernel Generation, which incorporates expert optimization principles to guide LLMs' decisions. Inspired by expert workflows, we decompose kernel generation into two hierarchical stages: 1) algorithmic structure design, which establishes a high-quality computational structure foundation; 2) hardware-specific tuning, which performs targeted adjustments through parallel mapping, tensor tiling, and
memory optimization. This staged decomposition defines explicit optimization objectives, structuring the design space to achieve progressive refinement. To this end, a stage-aware multi-
agent collaboration mechanism is designed for inter and intra-stage context management, ensuring stable optimization trajectories. Experiments on KernelBench and real-world workloads show that EGG achieves a 2.13x average speedup over PyTorch, outperforming existing
agent-based and RL-based approaches.
Read the full abstract ▾
All authors Yaochen Han, Ke Fan, Hongxu Jiang, Wanqi Xu, Weiyu Xie, Runhua Zhang, Chenhui Zhu, Yixiang Zhang
Artificial Intelligence · Cross-listed from cs.CV
Robust Onion: Peeling Open Vocab Object Detectors Under Noise
Priyank Pathak, Mukilan Karuppasamy, Aaditya Baranwal et al. (+2 more)
The impact of real-world noise on Open Vocabulary Object Detectors (OV-ODs) remains poorly understood due to their architectural complexity. We present our comprehensive analysis Robust Onion, an empirical study that uses controlled synthetic visual degradations to peel OV-ODs layer-by-layer, revealing how, why, and where robustness degrades, systematically analyzing feature collapse. Our findings reveal that models with similar
vision backbones exhibit comparable robustness, driven by similar feature collapse at similar layers, while factors such as pretraining strategy, architectural nuances, and caption supervision contribute little. Robustness is primarily governed by the image domain rather than annotations, explaining the similar robustness impact on COCO and LVIS, and why
datasets like ODinW-13 can give an impression of inflated robustness due to large, isolated objects. Finally, we validate our insights by improving robustness on real-world BDD100K, WiderFace, and VisDRONE via our lightweight plug-and-play NN & TK0 approach, using 96x fewer trainable parameters than end-to-end training. We also explain the prior works' robustness observations.
Read the full abstract ▾
All authors Priyank Pathak, Mukilan Karuppasamy, Aaditya Baranwal, Shruti Vyas, Yogesh S Rawat
Artificial Intelligence
Scientific discovery as meta-optimization: a combinatorial optimization case study
Yuan-Hang Zhang, Chesson Sipling and Massimiliano Di Ventra
Scientific discovery is fundamentally an optimization problem, defined by a vast “state space” of theories and experiments, and an evaluation criterion based on quality, novelty, and validity. Large
language models (LLMs) have enabled automated exploration of this state space, but we argue that simultaneous modification of the evaluation criteria is equally important. Here, we propose formalizing research as meta-optimization, where the optimization objective itself is also being optimized. Our key contribution is “consensus objective aggregation,” where a portfolio of LLM-generated objective functions is combined via correlation-weighted voting, allowing the evaluation criterion to evolve alongside the solutions. We apply this framework to
algorithm discovery for planted 3-SAT problems based on digital memcomputing machines. The leading solver from the consensus search reduces median integration steps by more than $38\times$ relative to a tuned baseline at 2,560 variables. Objective ablations show that a well-chosen fixed expert objective can also discover strong solvers, while consensus supplies a stable ranking that mitigates reward hacking behaviors. By bringing objective engineering into the discovery loop, this framework offers a practical route toward more adaptable automated research.
Read the full abstract ▾
Artificial Intelligence
Socratic agents for autonomous scientific discovery in high-dimensional physical systems
Xianrui Zeng, Pengfei Liu, Yirui Zang et al. (+5 more)
The automation of scientific discovery has reached an inflection point. While AI systems now operate instruments, optimize parameters and generate hypotheses, most remain procedural: they execute workflows fixed by human designers. True autonomous science demands epistemic autonomy–the capacity to construct, challenge and revise physical explanations in response to evidence. Here we introduce AHOIS, a multi-
agent AI scientist that embeds Socratic midwifery into closed-loop experimentation. A physics-critic
agent interrogates hypotheses through causal questioning, constraint checking, counterexample generation and falsification-criteria formulation. We evaluate AHOIS on a real multimode-fibre optical platform, a high-dimensional system with complex wave transformations, indirect detection, environmental drift and multi-modal acquisition. Without prior encoding schemes, classifiers or speckle models, the system autonomously proposed and validated a random-interference encoding hypothesis, discovered task-adaptive sparse-measurement strategies, diagnosed distinct failure modes (encoding instability, fluorescence contamination and detector noise) and translated a published imaging protocol into an executable workflow on a non-original configuration. The discovered encoding yielded 16x16 measurements with effective rank 56.9 and classification accuracies of 76.97% on MNIST and 83.17% on Fashion-MNIST. Ablations show that Socratic interrogation improves physical consistency, hypothesis completeness, uncertainty calibration and experimental-plan validity. These results establish a route from workflow automation towards evidence-grounded, self-correcting autonomous discovery in complex physical environments.
Read the full abstract ▾
All authors Xianrui Zeng, Pengfei Liu, Yirui Zang, Yang Shen, Fei Yu, Chunlei Yu, Minghao Liu, Yang Du
Artificial Intelligence
A latent ODE approach to full-cycle biventricular cardiac motion modeling from cine MRI
David Brüggemann, Ekaterina Krymova, Firat Özdemir et al. (+6 more)
Cardiac
magnetic resonance imaging (CMR) captures rich spatiotemporal information about ventricular structure and motion, but conventional risk models use only a few image-derived indices from selected cardiac phases. We present a latent dynamical model that encodes bi-ventricular anatomy and full-cycle cine motion as a continuous latent trajectory, using heart-rate-aware neural ordinary differential equation (ODE) dynamics and a graph-based mesh autoencoder to reconstruct anatomically consistent 3D+t ventricular motion. A
covariate-conditioned prior defines the expected end-diastolic latent state, and a Cox proportional hazards model tests whether deviations from this prior predict incident heart failure. We studied 72,386 UK Biobank participants without baseline cardiovascular disease, including 367 incident heart failure events. In a held-out evaluation subset, adding the latent score to refitted pooled cohort equations improved the stratified C-index from 0.704 to 0.785, compared with 0.764 for seven established cardiac markers. Compared with non-graph and non-ODE approaches, the proposed model gave the best trade-off between reconstruction fidelity, generative realism, and downstream prognostic performance. These results suggest that continuous full-cycle modeling of ventricular motion provides informative cardiac phenotypes beyond conventional CMR summaries, while external validation in more representative patient cohorts is required before clinical risk-prediction use.
Read the full abstract ▾
All authors David Brüggemann, Ekaterina Krymova, Firat Özdemir, Jochen von Spiczak, Sebastian Kozerke, Samia Mora, Robert Manka, Mathieu Salzmann, Olga V. Demler
Artificial Intelligence
LithoDreamer: A Physics-Informed World Model for Multi-Stage Computational Lithography
Yuqi Jiang, Yumeng Liu, Zimu Li et al. (+7 more)
As
semiconductor technology nodes scale, computational lithography is essential for ensuring yield and performance. However, lithography is a continuous physical process involving mask optimization, optical imaging, resist exposure, and development, which existing models fail to capture. To overcome this limitation, we present LithoDreamer, the first physics-informed World Model (WM) framework for computational lithography, which formulates the “Layout-Mask-Resist Image-After Development Image (ADI)” pipeline as a decision-driven multi-step
evolution system. LithoDreamer captures feature changes between adjacent states to model stage-specific physics-informed latent spaces, in which it controls process intervention exploration and drives subsequent state transitions. To achieve interpretable intervention optimization without continuous supervision, we propose a contrastive variational optimization paradigm that contrasts the latent differences between intervention paths with variational
evolution constraints, guiding the model to generate evolutions consistent with real lithography physics. Experiments show LithoDreamer achieves state-of-the-art performance in forward
evolution and inverse planning. Our lithography
dataset is publicly available at GitHub (https://github.com/7jiangyq/lithodreamer.git).
Read the full abstract ▾
All authors Yuqi Jiang, Yumeng Liu, Zimu Li, Jinyuan Deng, Qian Jin, Yucheng Cui, Yu Li, Xunzhao Yin, Qi Sun, Cheng Zhuo
Artificial Intelligence · Cross-listed from eess.IV
MLFFM-SegDiff: A Multi-Level Feature Fusion Diffusion Model for Skin Lesion Segmentation
Jingjun Gu, Chaojie Shen, Yifeng Cao et al. (+3 more)
Skin lesion
segmentation is a key task in computer-aided dermatological diagnosis, where accuracy directly impacts downstream analysis and disease classification. However, dermoscopic images are challenging due to blurred boundaries, low contrast, large shape variations, and artifacts such as hair and shadows. Recently,
diffusion models have shown strong performance in medical image
segmentation thanks to their progressive denoising and distribution modeling capabilities. Nevertheless, existing
diffusion-based methods still suffer from limited cross-level feature interaction and insufficient boundary detail recovery. To address these issues, we propose MLFFM-SegDiff, a multi-level feature fusion
diffusion model for skin lesion
segmentation. Built on a
diffusion framework, the method introduces a dual-path U-Net encoder, a Multi-Level Feature Fusion Module (MLFFM), and a boundary-sensitive loss function. The dual-path encoder enhances interaction between noisy mask features and dermoscopic image features. MLFFM improves skip connections via
attention, scale
alignment, and adaptive cross-level fusion. These designs enable the decoder to jointly leverage shallow boundary cues and deep semantic representations, improving mask reconstruction quality. Experiments on ISIC2018, PH2, and HAM10000 demonstrate that MLFFM-SegDiff outperforms representative methods including DermoSegDiff, U-Net, and SwinUNETR across Accuracy, F1-score, Jaccard index, Recall, and Dice. In particular, it achieves an average Jaccard index of 0.8546 and Dice coefficient of 0.9207. These results validate the effectiveness of the proposed multi-level feature fusion strategy for improving lesion
segmentation performance. The code will be released at https://github.com/Qacket/MLFFM-SegDiff.git after publication.
Read the full abstract ▾
All authors Jingjun Gu, Chaojie Shen, Yifeng Cao, Wei Zhang, Yiliu Li, Aobo Fan
Artificial Intelligence
Kalman Prototypical Networks for Few-shot Fault Detection in Combined Cycle Gas Turbines
Mohammed Ayalew Belay, Lucas Ferreira Bernardino, Adil Rasheed et al. (+2 more)
Combined-cycle gas turbines (CCGTs) play a key role in modern power generation, offering both high efficiency and reduced environmental impact. However, their complex thermo-fluid and mechanical interactions complicate fault detection, particularly when labeled fault data are scarce. In this paper, we introduce the Kalman Prototypical Network (KPN), a metric-based few-shot learning (FSL) framework specifically tailored for CCGT fault diagnosis. We model the
evolution of class prototypes as latent
stochastic states in a dynamic system to reduce episodic variance and improve robustness in
embedding representation. Synthetic data sets generated with a high-fidelity Modelica-based dynamic simulation of an offshore CCGT system were used, simulating both normal operation and progressive leak faults under transient conditions. Application of the proposed framework on simulated leak fault detection tasks demonstrate that KPN outperforms conventional FSL methods such as Matching Networks, Relation Networks, and MAML in both accuracy and stability under varying support and query configurations. The proposed framework significantly improves training convergence and generalization by stabilizing class representations, making it well-suited for real-world CCGT fault detection where labeled data is limited.
Read the full abstract ▾
All authors Mohammed Ayalew Belay, Lucas Ferreira Bernardino, Adil Rasheed, Rubén M. Montañés, Pierluigi Salvo Rossi
Artificial Intelligence · Cross-listed from cs.LG
Algorithmic Foundations of Deep Learning: Complexity-Theoretic Rates and a Characterization of Universal Approximation
Anastasis Kratsios, Simone Brugiapaglia, Bum Jun Kim et al. (+2 more)
Feedforward neural network (NN) expressivity is typically studied by emulating optimal basis-expansion schemes. While powerful, this perspective is incomplete: it primarily captures complexity through regularity, and therefore does not distinguish intuitively simple and complicated objects with comparable regularity, such as the square-root function and a typical Brownian path. The guiding message is that neural networks should be viewed not only as flexible basis functions, but also as models of computation. If a function is computable by a real-valued
circuit over a prescribed elementary gate
language, then it can be computed to comparable accuracy by an NN with explicit depth, width, and non-zero-parameter bounds controlled by the depth, width, gate count, and gate structure. Thus, neural-network complexity is not governed by regularity alone, but also by algorithmic complexity. We then show that any definable NN model satisfying a natural parallelization condition, allowing possibly multivariate non-linearities such as
attention or layer normalization, is a universal approximator if and only if it contains a non-affine nonlinearity. The scope of our theory is illustrated by deducing universal approximation guarantees for continuous functions, minimax-optimal approximation guarantees for Besov classes, logarithmic-error complexity for holomorphic functions, and by showing that NNs can emulate numerical
algorithms such as Newton-Raphson root finding and power iteration without architecture-specific arguments. Its precision is illustrated by shortest-path computation on $k$-vertex graphs: compiling the tropical dynamic-programming
circuit yields NNs with O(log(1/{\epsilon})) non-zero parameters, exponentially improving in 1/{\epsilon} over the generic $O({\epsilon}^{-c k^2})$ Lipschitz-approximation scale, for a constant c>0.
Read the full abstract ▾
All authors Anastasis Kratsios, Simone Brugiapaglia, Bum Jun Kim, Gregory Cousins, Haitz Sáez de Ocáriz Borde
Artificial Intelligence · Cross-listed from cs.RO
Learning Motion Feasibility from Point Clouds in Cluttered Environments
Sajid Ansari, Arthi, Girish Varma et al. (+1 more)
Motion feasibility prediction plays a central role in robotics, particularly in task and motion planning and manipulation. A major bottleneck for this problem in cluttered environments is that infeasible planning attempts by Sampling-based motion planners (SBMPs) can incur substantial computational cost. Also existing approaches for infeasibility certification are limited to low-dimensional configuration spaces and often assume simplified
geometric environments represented by primitive objects with known parameters. We study the complementary problem of learning motion feasibility prediction directly from raw RGB-D observations for a 7-DOF manipulator operating in realistic cluttered scenes. We introduce the first large-scale
benchmark for this setting, comprising 2.7M grasp feasibility labels over 88 scanned objects and 190 cluttered tabletop scenes. We
benchmark three representative classifier families spanning MLP- based, volumetric-CNN, and point-cloud-based
Transformer architectures under matched training conditions. Our best model, GRASPFC-PTX (a point-cloud
transformer), achieves an AUROC of 0.996 on Novel objects while providing predictions significantly faster than SBMPs.
Read the full abstract ▾
All authors Sajid Ansari, Arthi, Girish Varma, Antony Thomas
Artificial Intelligence · Cross-listed from cs.CL
Beyond Logical Forms: LLM-Extracted Patterns for Fallacy Classification
Eleni Papadopulos, Firoj Alam and Giovanni Da San Martino
In today's fast-paced information era, logical fallacies, defined as defective patterns of
reasoning, inevitably contribute to the growth of information disorder. However, often fallacies appear in nuanced forms that complicate automated classification. In this study, we investigate whether merging abstract logical structures with context-level linguistic cues proves beneficial for fallacy classification, developing a framework that inductively extracts such patterns from fallacious examples and their explanations using Large
Language Models (LLMs). We evaluate the impact of these patterns across different LLMs and experimental zero- and one-shot configurations, showing statistically significant improvements over zero-shot baselines and outperforming competing approaches. Cross-
dataset experiments validate generalization, establishing data-driven pattern extraction as an effective method for generating logical representations.
Read the full abstract ▾
Artificial Intelligence
Do Safety Guardrails Need to Reason? LeanGuard: A Fast and Light Approach for Robust Moderation
Dongbin Na
In order to screen a
prompt or a response, the recent guardrail methods generate a chain-of-thought (CoT) before they issue a verdict. This design follows a common belief that step-by-step
reasoning improves a decision. However, CoT also makes the guard heavy and slow, because the model must generate many
tokens before it decides. This may not match how guardrails are actually deployed. A guardrail sometimes should not be heavy and slow, and it often runs on-device, for example on an
embodied robot. In this paper, we pose a question whether a safety guardrail really needs to reason. To answer this question, we train a lightweight bidirectional encoder and a
reasoning guard on the same corpus, and we then remove only the
reasoning while we keep everything else fixed. With this controlled same-base comparison, we show that the chain does not improve moderation accuracy. We name the resulting guard LeanGuard. A 395M label-only encoder reaches an average F1 of 82.90 $\pm$ 0.26 over public
benchmarks. It matches a
reasoning guard that is built on a much larger decoder, while it uses only a single forward pass over an input of at most 512
tokens. This is about a ~100x reduction in inference compute. We further show that this label-only encoder stays robust under training-label noise and retains far more recall at a strict false-positive rate than the
reasoning guard, so a heavier
reasoning guard is not the more robust choice either. Our finding suggests that the current guardrail
benchmarks may not be hard enough to reward
reasoning, and that the necessity of CoT for moderation is still not proven. We release all source codes and models including LeanGuard at https://github.com/ndb796/LeanGuard.
Read the full abstract ▾
Artificial Intelligence
NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research
Qiaobo Hao, Yangqian Wu, Shunyi Wang et al. (+5 more)
Post-training
alignment determines the
reasoning and human preference following capabilities of large
language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization. This work presents NebulaExp, a fully transparent, ablation-driven post-training pipeline built on Qwen3-8B-base, covering two orthogonal model branches: general instruct model and complex
reasoning-specialized model. We curate a raw corpus of 3.84M multi-source SFT samples and a 200K verifiable RL candidate pool, and design an end-to-end data processing stack including response
distillation, multi-dimensional cross-verification filtering, fine-grained difficulty grading, task classification and diversity-aware sampling. For the Instruct branch, our three-stage optimized supervised fine-tuning approach NebulaExp-Ins-SFT improves the average
benchmark score from the 55.01 baseline of Qwen3-8B-nothink to 60.99. GRPO reinforcement learning then further elevates the average score to 61.85. For the
Reasoning branch, medium-difficulty GRPO RL improves average
reasoning score from 73.88 to 75.17. To address RL's dependency on task verifiers, we systematically investigate single-teacher and multi-teacher OPD (MOPD): utilizing merely 4K instruction-following samples and outperforms RL baseline by 3.26 points on IFEval with +4.43 average overall gain; MOPD fuses four domain-specialist teachers with merely 10K samples, lifting average performance by 4.18 over the base model. This report provides a fully reproducible empirical post-training recipe for 8B-scale LLMs, and comprehensively dissects the capability trade-offs among instruction adherence, mathematical
reasoning, code generation and general knowledge.
Read the full abstract ▾
All authors Qiaobo Hao, Yangqian Wu, Shunyi Wang, Zhongjian Zhang, Ziqun Li, Yayin He, Muqing Li, Chen Zhong
Artificial Intelligence
SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills
Zhongxin Guo, Danrui Qi, Hanwen Gu et al. (+2 more)
Agents often repeatedly solve similar task instances from scratch, leading to unnecessary
reasoning cost and long execution traces. Prior work has explored workflow reuse and executable skill induction, but it remains unclear which task scenarios admit procedural skills and how the shared procedural structure should be represented across successful traces. We study this problem in FSM-defined scenarios, where successful traces can be viewed as paths in an unknown transition graph, and formulate procedural skills as reusable parameterized control-flow subgraphs. Based on this view, we introduce SkillDisCo, a
distillation-and-compilation framework that distills reusable PFSM subgraphs from successful traces and compiles them into callable, executable, and verifiable procedural skills. Experiments on ALFWorld and WebArena show that SkillDisCo improves success rates and reduces
agent turns across
benchmarks and model scales, demonstrating the benefits of representing shared experience as reusable execution structures.
Read the full abstract ▾
All authors Zhongxin Guo, Danrui Qi, Hanwen Gu, Peng Cheng, Yongqiang Xiong
Artificial Intelligence · Cross-listed from cs.CV
Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization
Xuancheng Xu, Gengyun Jia and Bing-Kun Bao
Video customization based on Text-to-
Video (T2V) models aims to learn specific features from reference data to generate controllable
videos. While significant strides have been made in image stylization and
video motion customization, simultaneously controlling multiple concepts, such as content, style, and motion, remains a major challenge. In this work, we systematically define the task of multi-concept
video customization, which requires the joint control of content, style, and motion. To facilitate research in this area, we construct a comprehensive
benchmark and propose Disco-LoRA, a unified framework designed to tackle this problem by disentangling and flexibly recombining different concepts in two stages: (1) We decompose the objective into two sub-tasks: Content-Style and Content-Motion. Each sub-task is addressed using our Iterative Dual-LoRA Disentanglement Framework, which effectively disentangles distinct concepts within the data. (2) We identify layer-wise weight trends as crucial for LoRA identity, while weight magnitudes dictate composability. To harmonize these scales, we propose a Z-score-based statistical regularization that aligns weight distributions, preserving layer-wise trends while minimizing interference between different LoRAs. Extensive experiments show that Disco-LoRA excels in multi-concept
video customization, effectively preserving appearance, style, and motion for controllable text-to-
video generation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systems
Ngoc Bao Anh Le, Thai T. Vu, John Le et al. (+2 more)
Existing homomorphic encryption (HE)-based GNN systems adopt a graph-centric paradigm that couples per-query cost to global graph size, limiting evaluations to at most ~20k nodes and making them incompatible with dynamic, large-scale financial graphs. We propose TGHE (Template-based Graph Homomorphic Encryption), an ego-centric framework that resolves this by exploiting a template phenomenon: local computation trees in transaction graphs converge into a small set of structural shapes. TGHE canonicalizes ego-graphs at the edge and packs structurally identical trees into shared CKKS ciphertexts for SIMD-parallel encrypted inference, with two long-tail optimizers (Approximate Template Fitting and
Topology Collapse) ensuring full SIMD coverage. On DGraphFin (3.7M nodes, 4.3M edges), TGHE-Collapse achieves a 66.9x speedup over the sequential encrypted baseline with less than 0.002 AUC loss.
Read the full abstract ▾
All authors Ngoc Bao Anh Le, Thai T. Vu, John Le, Heath Cooper, Jun Shen
Artificial Intelligence · Cross-listed from cs.LG
Zero-Shot Size Transfer for Neural ODEs on Sparse Random Graphs: Graphon Limits and Adjoint Convergence
Mingsong Yan, Zhida Wang and Sui Tang
Graph Neural Differential Equations (GNDEs) model continuous-time graph dynamics by parameterizing Neural ODE velocity fields with Graph Neural Networks. Their local, size-independent filters suggest a zero-shot size-transfer principle: train on a small graph and deploy on larger, similar graphs without retraining. We develop a quantitative theory for this principle on sparse random graphs sampled from graphons. We consider Graphon Neural Differential Equations (Graphon-NDEs) and adjoint Graphon-NDEs as the infinite-node limits of the forward and adjoint GNDE systems, and establish well-posedness. For an $n$-node random graph with sparsity parameter $\alpha_n$, we prove trajectory-wise convergence of GNDE solutions to Graphon-NDE solutions at rate $O((\alpha_n n)^{-1/2})$, up to logarithmic factors, with high probability. We also establish uniform-in-time convergence bounds for adjoint systems governing hidden-state and parameter gradients. We further study discretize-then-optimize (DTO) and optimize-then-discretize (OTD) training. Under explicit Euler discretization with $M$ steps, we show that DTO and OTD are asymptotically consistent, with hidden-state and local parameter-gradient discrepancies of orders $O(1/M)$ and $O(1/M^2)$, respectively, up to sparsity and logarithmic factors. Experiments on HSBM and tent graphons support the theoretical rates, while zero-shot transfer experiments across four graphon classes demonstrate accurate deployment of learned GNDEs on larger independently sampled graphs.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
LAMP: Lane-Aligned Motion Primitives for Feasible Trajectory Prediction
Sangjin Han, Hoseong Jung, Jeongtae Her et al. (+2 more)
Motion
forecasting is essential for autonomous driving systems to enable safe decision-making and planning in complex driving scenarios. While existing predictors excel at minimizing standard displacement errors, they often overlook the adherence to lane
topology of
multimodal predictions, particularly for lower-probability modes. Consequently, predicted trajectories may violate physical and logical constraints, making the prediction set unreliable for safety-critical planning. In this paper, we propose LAMP (Lane-Aligned Motion Primitives), a
topology-aware
forecasting framework that anchors
multimodal prediction to structured motion primitives aligned with lane
topology. Specifically, we use a VQ-VAE to learn shape-aware motion primitives as discrete intention queries, capturing spatiotemporal patterns beyond endpoint-based intentions. We further introduce a feasibility-aware intention selector trained with a lane-
topology prior for filtering unreachable intention queries, guiding the decoder to prioritize
topology-consistent intentions while preserving behavioral diversity. Extensive experiments on the Argoverse 2
dataset demonstrate that LAMP achieves prediction accuracy comparable to state-of-the-art baselines while outperforming them in feasibility and diversity metrics.
Read the full abstract ▾
All authors Sangjin Han, Hoseong Jung, Jeongtae Her, Changhyun Choi, H. Jin Kim
Artificial Intelligence · Cross-listed from cs.CL
CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs
Shigeng Wang, Chao Li, Yangyuxuan Kang et al. (+2 more)
In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs. Unlike existing state-of-the-art ternary quantization methods that rely on data-intensive and costly quantization-aware training to mitigate severe performance degradation, CAT-Q is a simple yet effective post-training quantization scheme that is readily applicable to LLMs with diverse architectures and model sizes. It has two key components, learnable modulation (LM) and softened ternarization (ST), which are coupled from an optimization perspective. LM leverages a composition of learnable factors to modulate the distribution of pre-trained high-precision weights and the ternary threshold, making them less sensitive to ternarization. ST further introduces a differentiable transition function to guide the ternarization process toward stable convergence. We show that, for pre-trained LLMs with 1.7B to 8B parameters, CAT-Q can efficiently quantize them into ternary models using only 512 calibration samples, while achieving superior performance than the seminal BitNet 1.58-bit v1 and v2 families (with 1.3B to 7B parameters) trained with 100B
tokens, yielding about a 100,000X reduction in training
tokens. Moreover, we show for the first time that CAT-Q can quantize much larger pre-trained LLMs having 14B to 235B parameters into leading ternary models within just 8 to 60 hours on 8 A100-80GB GPUs. Code is available at https://github.com/IntelChina-AI/BitTern.
Read the full abstract ▾
All authors Shigeng Wang, Chao Li, Yangyuxuan Kang, Jiawei Fan, Anbang Yao
Artificial Intelligence
Autoformalization of Agent Instructions into Policy-as-Code
Adam Mondl, Matthew Maisel and John H. Brock
Agent safety in high-stakes domains requires formal policy enforcement, but most existing approaches either rely on probabilistic guardrails (fine-tuned classifiers,
prompt-based steering) that offer no formal guarantees, or on hand-coded symbolic enforcement that does not scale to the breadth of real policy specifications. We present an autoformalization pipeline that translates
agent prompts, MCP tool descriptions, and natural
language policy documents into formally verified policies using an LLM-based generator-critic loop. The resulting policies are written in the Cedar Policy
Language. On the MedAgentBench
benchmark, our autoformalized policies cover substantially more of the source natural-
language specification than the hand-coded symbolic enforcement in prior work.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents
Nada Lahjouji and Ashwin Gerard Colaco
Large
language model
agents increasingly query databases, search document collections, call external APIs, remember past interactions, and act on a user's behalf. As they move from answering questions to operating over sensitive data,
privacy becomes harder to enforce. An
agent touches many data sources, runs multi-step workflows, keeps state across sessions, and acts with delegated permissions. Sensitive information can therefore leak not only through its final answer but through the queries it issues, the intermediate results it handles, the
memory it writes, and the messages it exchanges with other
agents. We survey the
privacy of LLM
agents from a data-centric view, organizing the field around the data an
agent touches rather than by attack type, and we use data
agent as shorthand for an LLM
agent that works with data. Research on these risks is active but scattered across
retrieval-augmented generation, text-to-SQL interfaces,
agent memory,
prompt injection, access control, and contextual
privacy. This survey brings that work together: we taxonomize the data sources an
agent touches, the
privacy risks each source creates, and the governance mechanisms that address them; we map the
benchmarks used to measure these risks and identify what is missing; and we set out the open problems. Two findings recur: among governance mechanisms only information-flow control covers both compositional and cross-session inference leakage, the two least-protected risks; and no
benchmark drives an
agent across its data surfaces under one
privacy policy, the instrument the field most lacks. Our goal is a reference that situates the scattered literature and gives future work a common framing.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Discovering Millions of Interpretable Features with Sparse Autoencoders
XinYang He, Wei Wang, Bing Zhao et al. (+5 more)
Sparse autoencoders (SAEs) have emerged as a powerful tool for decomposing superposed
language model representations into sparse and interpretable features. However, training SAEs is computationally expensive, and available open-source SAE models remain limited. In this work, we introduce Qwen3-Instruct SAE, a comprehensive suite of SAEs trained on the Qwen3 instruction-tuned model family, covering Qwen3-1.7B, Qwen3-4B, and Qwen3-8B. For Qwen3-1.7B and Qwen3-4B, we train layer-wise SAEs at three key activation sites: residual streams, MLP outputs, and
attention outputs. For Qwen3-8B, we train SAEs on a subset of residual stream layers. We systematically evaluate these SAEs using both activation-level reconstruction metrics and model-level recovery metrics, revealing distinct sparsity–fidelity trade-offs across layers and components. Finally, we demonstrate the utility of Qwen3-Instruct SAE through a refusal-steering case study, showing that selected SAE features can causally steer instruction-tuned Qwen3 models toward refusal behavior. Our release provides a practical resource for studying sparse representations, feature-level mechanisms, and behavioral interventions in instruction-tuned
language models
Read the full abstract ▾
All authors XinYang He, Wei Wang, Bing Zhao, Xuan Ren, WenBo Li, WeiXu Qiao, Hu Wei, Lin Qu
Artificial Intelligence · Cross-listed from cs.HC
HiLSVA: Design and Evaluation of a Human-in-the-Loop Agentic System for Scientific Visualization
Kuangshi Ai, Patrick Phuoc Do and Chaoli Wang
Large
language model (LLM)
agents enable natural
language interaction for scientific visualization (SciVis). Still, prior systems have essentially prioritized autonomy over human analytical control, thereby limiting transparency and human oversight. We present HiLSVA, a human-in-the-loop agentic system that supports mixed-initiative SciVis workflows. HiLSVA integrates a plan-first multi-
agent architecture with explicit human oversight, stepwise provenance tracking, and learn-at-test-time adaptation from user feedback. The system supports fluid handoff between humans and
agents through both natural
language and direct manipulation of visualizations, while sandboxed execution ensures safe, reproducible workflows. In doing so, HiLSVA reframes agentic SciVis as a collaborative process that augments, rather than replaces, human analytical
reasoning. We evaluate HiLSVA through representative case studies and a controlled user study with twelve participants of varying expertise across multiple autonomy settings. Results show that mixed-initiative interaction improves task completion, user control, and workflow transparency across different levels of user expertise, while revealing a tradeoff between execution efficiency and human oversight. These findings highlight the importance of human-centered design in agentic SciVis and guide the development of future collaborative visualization systems. We encourage readers to explore our demo
video, case studies, and source code at https://hilsva.github.io/.
Read the full abstract ▾
Artificial Intelligence
LLM-based Models for Detecting Emerging Topics in Service Feedback
Mahsa Tavakoli, Ruth Bankey and Cristián Bravo
Enhancing the analysis of service feedback is essential for public sector organizations, particularly tax administrations, where trust and compliance depend on fair and effective service delivery. As feedback volumes grow, identifying emerging service quality issues and potential disparities across diverse populations becomes increasingly challenging. Traditional approaches often rely on manual review or static expert-defined indicators, limiting scalability and the ability to capture complex patterns in textual feedback. This paper presents a novel methodology that integrates large
language models (LLMs), statistical techniques, and human-AI collaboration to improve
multilingual customer feedback analysis. The primary objective is to detect emerging service quality topics that may also reveal potential inequities in service delivery. Our framework combines fine-tuned, quantized LLMs with expert oversight to produce accurate, computationally efficient, and context-aware analyses. The proposed approach was evaluated using similarity analysis and assessments from experienced tax officers, demonstrating stronger
alignment with expert judgments than baseline models. By incorporating a human-in-the-loop framework, the methodology reduces LLM fabrication while improving the reliability and relevance of generated insights. The results demonstrate the practicality of combining LLMs with human expertise to support scalable, evidence-based decision-making in public sector organizations. This work contributes to the development of responsible AI systems that enhance service quality, responsiveness,
fairness, and public trust through more effective analysis of
multilingual customer feedback.
Read the full abstract ▾