Artificial Intelligence
How Small Can You Go? A Controlled Study of LoRA Rank, Target Modules, and Quantization Trade-offs for Text-to-SQL on a 60M-Parameter Model
Mahendra Singh Rathor and Anagheem Azzam
Parameter-efficient fine-tuning (PEFT) and low-bit quantization are now standard tools for adapting
language models under tight compute budgets, yet their interaction is most often studied on billion-parameter models where the design space is expensive to explore. We ask a complementary question: on a specific, fully reproducible 60M-parameter encoder-decoder model (T5-small) and a single-table text-to-SQL
benchmark (WikiSQL), how much task accuracy does each efficiency knob actually cost? We run a controlled, single-variable study over (i) LoRA rank r in {2, 4, 8, 16, 32}, (ii) the set of adapted modules, and (iii) numerical precision. We report task accuracy alongside system-level metrics including trainable parameters, peak training
memory, inference latency, and throughput, and frame adaptation as a constrained trade-off rather than an accuracy-only objective. Our results show that LoRA with r=16 recovers within 11.6 percentage points of full fine-tuning accuracy (59.6% vs. 71.2% exact-match) while training fewer than 1% of parameters and consuming 31% less peak GPU
memory. Within this setting, rank beyond r=16 yields no measurable accuracy gain. QLoRA with INT8 and NF4 quantization achieves comparable accuracy (52.8% and 53.2%) at dramatically lower
memory cost (0.60 GB each), demonstrating a compelling trade-off for
memory-constrained deployments. All code, configurations, and logs are released for full reproducibility.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
IRIS: Reusable Identity Representations from Frozen LLMs for Entity Alignment
Xinran Liu, Shengtao Li, Shouqian Shi et al. (+2 more)
Entity
alignment (EA) identifies entities across knowledge graphs (KGs) that refer to the same real-world object. Conventional EA methods mainly exploit explicit graph structures and textual fields, which often provide insufficient semantic understanding to recognize the same entity under heterogeneous descriptions and distinguish it from semantically similar entities. Although large
language models (LLMs) offer deeper entity understanding, existing LLM-based EA methods largely use this capability for auxiliary generation or candidate-conditioned decisions. Consequently, such understanding is not distilled into a stable and directly comparable identity space, leaving
alignment tied to specific KG pairs or candidate sets and requiring repeated processing as the matching context changes. To address these limitations, we propose IRIS (Identity Representations from Internal States), a training-free framework that constructs for each entity an iris-like signature encoding its distinctive and stable identity characteristics. IRIS derives these signatures by eliciting identity-oriented contextual representations from a frozen LLM, thereby forming a shared space in which each entity is encoded once and can be aligned across different KGs through direct similarity comparison, without pair-dependent representation construction or candidate-wise LLM inference. Across four established EA
benchmarks and two frozen LLM backbones, the best IRIS variants achieve Hits@1 scores of 100.00, 99.38, 98.31, and 97.99 on D-Y-15K V2, DBP-WIKI, ICEWS-WIKI, and ICEWS-YAGO, respectively.
Read the full abstract ▾
All authors Xinran Liu, Shengtao Li, Shouqian Shi, Ge Wang, Xin-Wei Yao
Artificial Intelligence
Matrix-Free Photoacoustic Image Reconstruction via Sensor-Token Self-Attention
Mary John, Shibili Said, Imad Barhumi et al. (+2 more)
Photoacoustic
tomography (PAT) combines the optical absorption contrast of biological tissue with the spatial resolution of ultrasound, yet recovering the initial pressure distribution from sparse-view sensor measurements remains an ill-posed inverse problem. Iterative compressive-sensing solvers and unrolled deep networks both retain a dependence on the system
matrix at inference, which leaves real-time clinical reconstruction computationally expensive. This paper proposes the Sensor
Attention Network (SAN), a
Transformer-based architecture that treats the full time series of each sensor as a
token and maps raw measurements directly to the reconstructed image without invoking the system
matrix at inference. For training and benchmarking, an analytical k-space H-
matrix is constructed and validated against the k-Wave pseudo-spectral solver under matched geometry, achieving a mean per-sensor Pearson correlation of 0.919 +/- 0.049, with k-space apodization and Gaussian temporal damping acting synergistically to reduce the energy-normalized mismatch by 49%. Trained with a vessel-weighted loss on 488 augmented samples and evaluated on 46 held-out samples against ISTA, split-Bregman total variation (SBTV), and learned ISTA (LISTA), SAN attains the highest mean SSIM (0.522) and PSNR (22.09 dB) and the lowest NMSE (0.233). Paired t-tests and Wilcoxon signed-rank tests confirm the superiority of SAN over LISTA on PSNR, NMSE, and Pearson correlation at p < 1e-8, and over ISTA and SBTV on all fidelity metrics. By bypassing the H-
matrix at inference, SAN reduces reconstruction time by at least an order of magnitude, supporting real-time PAT reconstruction.
Read the full abstract ▾
All authors Mary John, Shibili Said, Imad Barhumi, Sherzod Turaev, Mohamed Yahia
Artificial Intelligence · Cross-listed from cs.CV
The LAIA Dataset: Labelled Attention for Intelligent Automobiles
A. Contreras, D. Porres, R. Abad et al. (+5 more)
The development of autonomous vehicles (AVs) usually relies heavily on data-driven artificial intelligence (AI) models that require large volumes of sensor data with ground-truth annotations. While modular architectures are widely used, end-to-end driving paradigms offer a promising alternative by directly mapping sensor inputs to control actions. However, their adoption is limited by challenges in interpretability and explainability. To address this, we present LAIA (Labelled
Attention for Intelligent Automobiles), a novel synthetic
dataset designed to enrich end-to-end driving research with human
attention data. Collected using the CARLA simulator in closed-loop environments, LAIA comprises over 15 hours of driving from 44 participants across carefully crafted scenarios designed to evoke natural responses. Each sequence includes RGB images under six weather conditions, semantic and instance
segmentation, depth, optical flow, CAN bus signals, and synchronized eye-tracking data. LAIA enables applications including training
attention-aware end-to-end AI drivers, predicting driver behavior, developing methods to detect anomalous driver-
attention patterns, and improving model explainability. In this work, we use LAIA to compare human
attention with the perceptual
attention emerging in our end-to-end driving models, thereby providing insight into their behavior.
Read the full abstract ▾
All authors A. Contreras, D. Porres, R. Abad, P. Cano, A. Levy, G. Villalonga, A. M. López, A. Hernández-Sabaté
Artificial Intelligence · Cross-listed from eess.SP
CORF-GS: Real-Time Wireless Radiance Field Reconstruction via Coupled Optical-RF Gaussian Splatting
Jinya Zhang, Jiajia Guo, Chao-Kai Wen et al. (+1 more)
Recent advances in 3D Gaussian Splatting (3DGS)-based wireless radiance field (WRF) reconstruction provide an efficient solution for wireless channel modeling. However, existing WRF reconstruction methods rely on pre-collected observations and offline optimization, and thus struggle to provide real-time channel knowledge. To bridge this gap, we propose CORF-GS, a real-time WRF reconstruction framework that processes sequential optical and
radio frequency (RF) keyframes. Specifically, CORF-GS constructs a unified Gaussian representation for optical and RF with shared geometry and modality-specific appearance, allowing high-resolution optical images to provide structural priors for WRF reconstruction. When a new keyframe arrives, CORF-GS first employs optical-guided Gaussian sampling to densify the WRF in under-represented regions. Since light and
radio waves may respond differently to the same object surfaces due to wavelength mismatch, relying solely on optical guidance may neglect RF-informative areas. Therefore, CORF-GS performs coupled optical-RF optimization to jointly refine the shared Gaussians. Compared with the existing two-stage training pipelines, this prevents WRF from passively adapting to a frozen optical geometry and encourages the shared Gaussians to adapt to both optical structures and RF power distributions. Simulations show that CORF-GS achieves state-of-the-art RF spectrum synthesis quality and reduces the reconstruction time by $6.4\times$ compared with existing WRF methods.
Read the full abstract ▾
All authors Jinya Zhang, Jiajia Guo, Chao-Kai Wen, Shi Jin
Artificial Intelligence
Agent Skills Matter: Inferring Proprietary Skills from Execution Trajectories
Jianing Geng, Ruiqi He, Zekun Fei et al. (+6 more)
Agent skills package reusable procedures that improve downstream performance. Their lightweight, portable form enables marketplace monetization and private deployment behind cloud-hosted
agent interfaces, giving providers incentives to keep high-value skills proprietary. Yet hiding the artifacts does not conceal their behavioral effects, which remain observable in execution trajectories and form a behavioral side channel. We define this exposure as Skill Leakage: reconstructing proprietary skills from trajectories elicited by benign queries, without reference answers or success labels. We introduce SigLeak, a black-box framework that exploits recurring skill signatures in
agent behavior. It constructs diverse, decision-rich diagnostic tasks, contrasts matched skill-enabled and skill-disabled trajectories, and iteratively refines a reconstructed skill from the isolated patterns. Across five scenarios, three model families, and three
agent frameworks, SigLeak outperforms or matches three baselines in nearly every setting. It raises the success rate by 6.88 percentage points over the skill-disabled reference on average and achieves the highest overall SkillSim, our metric for coarse- and fine-grained semantic similarity. These results show that benign execution trajectories can expose proprietary procedural knowledge. The code is available at https://anonymous.4open.science/r/SigLeak-D1DB.
Read the full abstract ▾
All authors Jianing Geng, Ruiqi He, Zekun Fei, Biao Yi, Xuansheng Wu, Ruijie Wang, Zheli Liu, Xia Hu, Qingkai Zeng
Artificial Intelligence
Distilling Temporal Search and Reasoning: Evolving LLMs for Future Prediction via Harness-Assisted Efficient Data Synthesis
Wanxu Cai, Zhengyu Chen, Huaisheng Zhu et al. (+3 more)
Future event prediction carries broad social impact yet remains challenging. SOTA approaches augment LLMs with external
agent frameworks whose predictive capability vanishes once the harness is removed. While recent Tool-Integrated
Reasoning (TIR) internalizes deep search for multi-hop
retrieval of facts,
forecasting further demands temporal search and
reasoning over historical trends and dynamic shifts. The key obstacle is data: historical queries induce temporal leakage that degrades
forecasting into
retrieval. Prior works either freeze information gathering with static observations, or rely on rejection sampling or unresolved fresh queries that discard vast amounts of data, degrading synthesis efficiency. We propose a time-truncation harness that enforces a temporal cut-off at every turn, enabling TIR-style sampling from historical events, reducing temporal leakage and reliance of rejection sampling or unsolved queries, increasing the sampling efficiency. We further build a large-scale corpus and a process-based metric and show that our harness naturally induces a broader temporal breadth of search and raises the proportion of high-quality data, further increasing the efficiency and reducing the reliance on complex rubrics.
Distillation experiments show that students trained on harness-intervened data achieve the best performance, demonstrating harness-assisted model evolving that turns higher quality temporal search and
reasoning data into a parametric advancement of the students.
Read the full abstract ▾
All authors Wanxu Cai, Zhengyu Chen, Huaisheng Zhu, Wei Wang, Jingang Wang, Qiang Xu
Artificial Intelligence
From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios
Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz et al. (+1 more)
Given a model that is already trained, which features does it rely on causally versus spuriously? Existing methods require access to the training procedure and cannot answer this post-hoc. We introduce the Normalised Sensitivity Ratio~(NSR), a post-hoc, model-agnostic diagnostic for this question under a structured-shift regime: environments differ primarily in the mean of spurious features while the causal mechanism and causal marginals remain stable, as in multi-site clinical data or multi-batch genomics. Within this regime, causal features induce constant model sensitivity across environments while spurious features track shift. NSR formalises this as the squared coefficient of variation of per-environment sensitivity. Under a linear structural causal model (SCM) with $K\ge3$ non-degenerate environments, NSR achieves exact identification (
Theorem~1). We fully characterise failure: weak shifts ($O(\varepsilon^4)$ collapse), degenerate geometry, and proxy attenuation ($O((1-\alpha)^4)$), giving practitioners quantitative criteria for assessing whether the regime holds. Finite-sample rates are $O_p(n^{-1})$ under the null and $O_p(n^{-1/2})$ under the alternative. Experiments confirm all theoretical predictions on synthetic data (area under the ROC curve [AUROC] $= 1.000$ under conditions satisfying the regime), show consistent rankings across five model families (Kendall $\tau\ge0.529$), and recover six of eight causal features on bike-sharing data (Precision@7 $= 0.75$) without modifying any trained model.
Read the full abstract ▾
All authors Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz, Sotirios Tsaftaris
Artificial Intelligence · Cross-listed from cs.CV
Less is More: Modality-Decoupling for General AIGC Audio-Video Detection
Jielun Peng, Yabin Wang, Yaqi Li et al. (+3 more)
Generative AI has rapidly expanded audio-visual forgery beyond human-centric deepfakes into general scenes. Existing AIGC detection methods assume audio-visual content correspondence, identifying forgeries by spotting cross-modal inconsistencies. However, we empirically find that this assumption does not consistently hold in general scenarios. We argue that, for general audio-visual AIGC detection, decision-level fusion is a more robust alternative to feature-level fusion. Therefore, we propose DAV-Det, a decoupled audio-visual AIGC detection system that independently models forensic evidence from each modality. The visual detector leverages multi-granularity representations at global, patch, and segment levels to capture spatial forgery cues, while the audio detector exploits both temporal and spectral irregularities via a gated temporal-spectral dual-branch architecture to model acoustic artifacts. Our method ranks 1st in the General AIGC Audio-
Video Detection Challenge of the IJCAI-ECAI 2026 DDL 2.0 Workshop, with a final score of 0.8460. Code is available at https://github.com/tuffy-studio/DAV-Det.
Read the full abstract ▾
All authors Jielun Peng, Yabin Wang, Yaqi Li, Jincheng Liu, Xiaopeng Hong, Athanasios V. Vasilakos
Artificial Intelligence · Cross-listed from cs.CV
Visual prompt engineering for video models
Robert Geirhos, Yuxuan Li, Thaddäus Wiedemer et al. (+7 more)
In the age of foundation models, a model is only as good as its
prompt. For this reason,
prompt engineering has become an essential technique for improving
language model performance. Since
video models are currently becoming foundation models for visual tasks (e.g., visual
reasoning), we here ask whether they similarly benefit from visual
prompt engineering: automatically modifying the task image to improve model performance. For example, for a visual physics
reasoning task ("Where does the ball land, after passing a set of obstacles?"), an abstract sketch-like scene can be turned into a photorealistic version with a simple call to an image editing model. We find that visual
prompt engineering, or VIPE for short, improves
video reasoning performance across tasks. In fact, for
video models, visual
prompt engineering can be even more effective than classic text-based
prompt engineering or test-time scaling. Ultimately, just as text-based
prompt engineering systematically improves
language model performance, visual
prompt engineering can serve as a simple, compute-efficient approach to elicit better visual
reasoning performance from
video models. Example
videos on our project page at https://visual-
prompt-engineering.github.io/.
Read the full abstract ▾
All authors Robert Geirhos, Yuxuan Li, Thaddäus Wiedemer, Neha Kalibhat, Zi Wang, Mani Malek, Oyvind Tafjord, Kevin Swersky, Been Kim, Priyank Jaini
Artificial Intelligence
Entangled by Design: Spurious Intra-Variable Signal Routing in Tabular In-Context Learners
Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz et al. (+1 more)
Consider a model trained at a single hospital to predict patient recovery, where the measured feature $X$ bundles the patient's true health signal ($C$) with a systematic artefact from that hospital's equipment ($S$). Within that hospital, the artefact correlates with outcomes through unmeasured confounders such as patient demographics; an in-context learner rationally routes predictions through $S$, not $C$, and fails silently when deployed at a new hospital with different equipment. We formalise this as spurious routing in composite representations: when a feature $X = [C;\,\alpha S;\,\eta]$ encodes a causal signal $C$ and a spurious signal $S$ in distinct subspaces, the ICL cannot determine which drives predictions. We prove that under ridge ICL, a linear in-context learner, this routing is unavoidable regardless of context size; TabPFN, a state-of-the-art pretrained tabular ICL model, shows qualitatively consistent behaviour empirically. We derive a closed-form characterisation, $\mathrm{CSR} \propto \rho_S/\rho_C$, confirmed at $r = 0.997$ for linear ICL and $r = 0.979$ for TabPFN. Contrary to intuition, larger context sharpens commitment to the dominant in-context signal, amplifying spurious routing by up to $1.74\times$; in the high-spurious corner, more expressive models show greater vulnerability empirically ($+2.22$ CSR gap at high
entanglement). We introduce two lightweight mitigations: environment-stratified context construction and S-swap augmentation, that require only weak environment labels and no knowledge of the causal partition. S-swap reduces spurious routing by $74\%$ for linear ICL and $98.8\%$ for TabPFN, with TabPFN's causal sensitivity increasing $8.4\times$ simultaneously: the model does not become agnostic, it reroutes through the causal signal.
Read the full abstract ▾
All authors Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz, Sotirios Tsaftaris
Artificial Intelligence · Cross-listed from cs.LG
Multi-Scale Structural Features for Continual, Comprehensible Visual Recognition in a Developmental Learning Framework
Zeki Doruk Erden
Contemporary machine learning struggles to learn continually, reuse prior knowledge, and expose a comprehensible internal structure. A recently proposed developmental, gradient-free learning framework addresses these limitations by learning a discrete, topological model of its inputs through local variation and selection, yielding an inherent continual-learning guarantee: new observations refine existing structure without overwriting past knowledge, and without replay buffers or predefined task boundaries. Its extension to visual inputs demonstrated this principle on shape recognition, but relied on a feature representation of limited expressivity that capped recognition accuracy. We introduce a new visual feature representation that encodes shape structure across multiple scales, capturing edge and contour features together with their spatial relations, and integrate it with the network-refinement learning process; we further improve the learning dynamics and the read-out used to predict from the learned model. The study targets two-dimensional shape, with class-incremental MNIST as a controlled, interpretable
benchmark in which continual-learning behavior can be measured directly. Our approach substantially increases accuracy over the prior representation, matching or exceeding replay- and regularisation-based baselines at comparable storage while storing no past data, and preserves the framework's defining behavior: earlier-learned classes are retained as new ones are introduced, with no destructive adaptation, and the learned representations remain human-interpretable. What separates the methods is retention: the baselines surrender most of a just-trained class within its own cycle and relearn it afterwards, which ours does not. The significance lies in the manner of learning. The system integrates information one sample at a time while provably preserving its responses to...
Read the full abstract ▾
Artificial Intelligence
Are the High-weight Neurons the Important Ones in Image Classification Neural Networks?
Qitao Chen, Dongfu Yin, Xirui Yang et al. (+2 more)
As neural network models for image classification advance,
neurons play critical roles in
pruning,
backdoor defense, and interpretability. Yet existing work lacks clarity on the weight-importance relationship. We address this with a
neuron importance assessment method using three experiments: quantifying overlap between high-weight and accuracy-impacting
neurons, analyzing high-weight
neuron perturbation effects, and testing post-retraining accuracy after high-weight
neuron ablation. Experiments on CIFAR-10 and Mini-ImageNet reveal key patterns. Overlap analysis shows top 10% high-weight
neurons overlap with important ones by only about 25% at maximum, dropping further in subsequent intervals. Perturbation tests find top 10% high-weight
neurons cause 45-80% accuracy degradation under certain operations compared to 3-7% for random perturbations, but a third of them show minimal impact. Ablation-retraining results show removing top 10% high-weight
neurons leaves accuracy 10-20% below baseline with no recovery, while ablating top 0.1% allows near-full recovery. Notably, some low-weight intervals show 10-17% degradation when perturbed, comparable to mid-range high-weight
neurons. These results confirm not all high-weight
neurons are important: their importance is nonlinear. Low-weight
neurons also contribute significantly. This challenges weight-importance equivalence, offering refined
neuron role insights. It supports applications like encryption prioritizing critical high-weight
neurons and
pruning removing non-critical ones, advancing neural network analysis.
Read the full abstract ▾
All authors Qitao Chen, Dongfu Yin, Xirui Yang, Zhaoye Li, Liang Xiao
Artificial Intelligence · Cross-listed from cs.CV
Argus-Unified: Towards A Compact and Economical Unified Model for Image Understanding and Generation
Weiming Zhuang, Jiabo Huang, Jingtao Li et al. (+4 more)
Unifying visual understanding and generation in one model holds immense promise, but remains challenging and expensive due to heavy compute and data demands and conflicts between the visual features needed for these two capabilities. To address these challenges, we present Argus-Unified, a compact, effective and unified
multimodal model built with low demand on computation and data. Instead of aligning modalities from scratch, Argus-Unified effectively leverages pretrained
vision-
language models (VLMs) that provide strong
multimodal priors. Specifically, we introduce hybrid visual
tokens that preserve continuous
tokens for understanding while learning discrete
tokens for generation from a frozen unified
vision encoder. Our training pipeline includes two stages: the first stage learns a quantizer and image decoder on top of the frozen
vision encoder, the second stage trains the LLM initialized from a pretrained VLM for the unified
multimodal modeling. Using by far the least amount of data (15.6M) and the lowest cost (~$2,000), we demonstrate that unified
multimodal models can be trained economically while achieving strong performance in both understanding and generation. Notably, our model attains state-of-the-art
multimodal understanding on GQA, POPE, and VQAv2, and competitive generation quality compared to models with dedicated
vision encoders (e.g., Janus, Janus-Pro), all at ~10x lower cost and with ~5x less data. We envision Argus-Unified as a useful baseline that lowers the development barrier for unified models.
Read the full abstract ▾
All authors Weiming Zhuang, Jiabo Huang, Jingtao Li, Zhizhong Li, Chen Chen, Sina Sajadmanesh, Lingjuan Lyu
Artificial Intelligence · Cross-listed from cs.CV
ReLATE: Reliability-Guided Evidence Fusion for Robust UAV–Satellite cross-view Geo-Localization
Haochen Jiang, Jialei Pan, Yuzhe Sun et al. (+4 more)
Unmanned aerial vehicle (
UAV)-satellite cross-view geo-localization matches
UAV images against satellite imagery and has achieved impressive accuracy on clean (non-degraded) image
benchmarks. In real-world flights, however,
UAV observations are frequently affected by adverse weather, illumination changes, platform motion, sensor noise, and compression, while the robustness of existing methods under such degradations remains largely unexamined. In this paper, we present UAVSat-Deg, a large-scale robustness
benchmark for degraded
UAV-satellite geo-localization, comprising University-1652-Deg and SUES-200-Deg. UAVSat-Deg covers 27 corruption types, including 19 core and 8 compound corruptions, at three severity levels, supports bidirectional drone-to-satellite and satellite-to-drone
retrieval as well as multi-height
UAV acquisition, and contains more than 11.7 million pre-generated corrupted test images. Benchmarking representative methods under this protocol reveals substantial robustness gaps, particularly under severe and compound corruptions. To address this problem, we propose ReLATE, a Reliable Evidence Learning framework with Adaptive
Token Evidence Regulation, which realizes reliability-adaptive feature fusion during descriptor construction. ReLATE estimates a structure-smoothed reliability field over visual
tokens, aggregates trustworthy local evidence, and adaptively integrates it into query-derived representations; the regulated query representations are then combined with the CLS-
token and GeM-pooled branches to form the final cross-view descriptor. Across both test sets and
retrieval directions, ReLATE achieves the best average corrupted-test performance among the compared methods while maintaining competitive accuracy on clean images. The code and
dataset will be available at https://github.com/JHC626/ReLATE.
Read the full abstract ▾
All authors Haochen Jiang, Jialei Pan, Yuzhe Sun, Zhe Dong, Lecheng Ren, Yanfeng Gu, Tianzhu Liu
Artificial Intelligence · Cross-listed from cs.CV
I2VShield: An Efficient Proactive Defense Framework against DiT-based Image-to-Video Models
Yimao Guo, Zuomin Qu and Wei Lu
The rapid advancement of
video generation models has led to the increasing misuse of image-to-
video (I2V) models. Although substantial progress has been made in detecting AI-generated
videos, proactive defenses against I2V models remain underexplored. In particular, current proactive defenses against I2V models predominantly rely on gradient-based
adversarial attacks, which require defenders to possess GPUs with substantial
memory resources (VRAM) to generate
adversarial examples. To address this issue, we propose I2VShield, a
privacy protection method based on generative
adversarial attacks tailored to
Diffusion Transformer (DiT)-based I2V models. The proposed method primarily consists of two components: (1) a text-adaptive perturbation generation framework integrating
adversarial learning to mitigate computational overhead while maintaining visual imperceptibility; and (2) an untargeted
Multimodal Attention Disruption (MAD) attack that exploits the inherent vulnerabilities of DiT-based I2V models, maximizing the deviation of the internal
attention features from their clean states. Extensive experiments demonstrate that our approach achieves highly competitive protection performance across various
datasets and mainstream DiT-based I2V models, particularly in disrupting spatiotemporal coherence, while substantially reducing computational costs.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.AR
At-the-Roofline Sparse Tensor Contractions on Vector Processors for Transformer Inference
Bowen Wang, Chi Zhang, Diyou Shen et al. (+3 more)
Fine-grained weight
pruning and activation sparsification have emerged as effective approaches for reducing the compute and
memory cost of inference for
Transformer models. In the moderate-sparsity regime, Gustavson's dataflow provides a natural execution model for exploiting both activation and weight sparsity on vector processors through metadata-driven indexed accumulation. However, existing RVV architectures lack native support for this pattern, forcing kernels to rely on software index decoding and L1-backed indexed
memory operations that keep sparse tensor contractions far below their roofline performance bound. We present Ventaglio, a runtime-configurable sparse execution unit coupled with RVV ISA extensions that drives sparse tensor contractions toward their roofline through indexed gather-accumulate-scatter support. Integrated into an open-source vector processing cluster and implemented in 12nm FinFET, Ventaglio accelerates sparse tensor contraction kernels by $6.9\text{--}7.4\times$ over optimized RVV baselines, with only $3.1\%$ area overhead for a cluster of tightly-L1 coupled vector processing elements. We build a performance-accurate instruction-level model of the Ventaglio extension, calibrate it against RTL implementation, and leverage it for scale-out performance analysis on a large $4\times4$ multi-cluster system. Using a DuoGPT-pruned LLaMA-3-8B model with practical $40\text{--}60\%$ dual sparsity, Ventaglio achieves $2.40\text{--}5.25\times$ and $2.06\text{--}3.16\times$ speedup over dense baselines during prefill and autoregressive decoding, respectively.
Read the full abstract ▾
All authors Bowen Wang, Chi Zhang, Diyou Shen, Renzo Andri, Navaneeth Kunhi Purayil, Luca Benini
Artificial Intelligence · Cross-listed from cs.CV
A Distributional Robustness Margin For Pathology Foundation Models
Clément Grisi, Jeroen van der Laak and Geert Litjens
Pathology foundation models encode non-biological variation introduced by tissue preparation, staining and scanning, enabling shortcut learning that undermines generalisation across institutions. The Robustness Index (RI) was proposed to assess whether local representation geometry is dominated by biological or non-biological variation. However, its construction suffers from structural limitations that make cross-model comparison unreliable, calling for a more principled metric. We introduce the Cross-confounder Robustness Margin (CRoMa), a signed, per-sample margin that measures whether samples sharing the same biology but different confounder lie closer than samples sharing the same confounder but different biology. It is defined for every sample, allowing models to be compared on the same cohort and robustness to be analysed as a distribution rather than reduced to a single pooled score. We evaluated CRoMa across 20 tile-level encoders on three
benchmarks. Rankings by median CRoMa were highly consistent across
benchmarks (Spearman rho ~ 0.90), yet every encoder retained confounder-dominated samples, whose prevalence and severity varied markedly. Similar patterns emerged for four slide-level encoders evaluated on a separate
benchmark, extending the analysis beyond tile-level representations. Higher median CRoMa was associated with smaller shortcut-induced performance losses in downstream linear probes, supporting its use as a representation-level indicator of shortcut susceptibility.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from math.NA
Automated Numerical Stability Analysis of Deep Learning Operators
Xinye Chen
Finite-precision arithmetic unavoidably introduces numerical approximation errors. Numerical computations may use insufficient precision or an improper formulation, which leads to numerical instability. In this paper, we introduce a unified software tool for
stochastic numerical validation of deep-learning operators. The tool follows CESTAC on supported exposed operations and uses an operator-level data-perturbation approximation for GEMM-like kernels. Our developed software not only enables numerical validation with a single computation pass but also detects the sources of numerical instability and provides numerical stability monitoring during deep learning training and inference. We verified its effectiveness on the detection of polluted operators with injected numerical instabilities across various tasks. We believe that our developed method and tools provide valuable insights into developing numerically stable computing kernels, which are particularly critical for numerically stable and efficient deep learning training and inference.
Read the full abstract ▾
Artificial Intelligence
CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model
Minhyeok Lee, Chiyoung Kim, Chanhoe Gu et al. (+5 more)
Vision-
Language-Action (VLA) models translate natural-
language commands into
robot action sequences, but leading systems on the LIBERO-Plus robustness
benchmark use three- to seven-billion-parameter backbones whose
memory demands can exceed embedded robotic budgets. We present CoTinyVLA, a 0.9B-parameter action model on a Qwen3.5-0.8B backbone that obtains that robustness by structuring supervision instead of enlarging the model. Three components target different axes of the problem: dual-view temporal input of 16 history frames per step with textual camera and time markers; hierarchical chain-of-thought (CoT)
distillation from a 35B teacher into an episode-level Plan and a chunk-level Think span over task phase, gripper state and next subaction; and paraphrase augmentation expanding 40 base commands into 800 variants. On LIBERO-Plus, spanning 10,030 perturbed tasks across seven perturbation dimensions, CoTinyVLA reaches 90.8% on Spatial, 87.3% on Object, 86.6% on Goal and 80.7% on Long, leading the strongest 7B baseline on all four suites by 4.7, 2.8, 15.9 and 3.0 points, with every margin interval excluding zero. The gains concentrate on the hardest axes of the
benchmark: across the eleven published baselines none exceeds 53.2% on
Robot Initial States in any suite, whereas CoTinyVLA reaches 73.6% on Goal against 39.9% for the strongest baseline. Ablations show the three components to be separable by perturbation axis, and at a matched image budget how frames are divided between the two cameras and across time accounts for 8.6 points on its own. Closed-loop inference peaks at 2.25 GiB of allocated GPU
memory, and paired interventions show the episode Plan to be load-bearing: replacing it with an empty or contradictory span costs 40 to 45 points of success. Structured supervision thus lets a 0.9B backbone exceed all of them. Code: https://github.com/BrainJellyPie/CoTinyVLA
Read the full abstract ▾
All authors Minhyeok Lee, Chiyoung Kim, Chanhoe Gu, Seongrok Kim, Sanghyuk Roy Choi, Donghwan Hwang, Donghun Ryu, Seokhyun Kim
Artificial Intelligence
PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents
Korosh Vatanparvar, Ashutosh Joshi, Maria Xenochristou et al. (+11 more)
Health AI is evolving from answering questions to agentic systems that converse with patients, reason about health records, and act on their behalf. Primary care guards against diagnostic errors and unsafe care;
agents assisting in this domain warrant evaluation against the same risks. Current
benchmarks focus on medical knowledge, assessed through isolated question-answering or clinician-facing tasks. PatientAgentBench
benchmarks patient-facing agentic healthcare; it evaluates a foundation model, wrapped in an
agent with a sandbox of healthcare tools, conversing with a simulated patient. Each conversation is scored by an LLM-as-a-Jury across six dimensions via over a hundred conversation-agnostic, clinician-grounded criteria. To validate
alignment, licensed clinicians annotated shared conversations, yielding 79-93% adjacent agreement between jury and expert raters, on par with or exceeding clinician inter-rater agreement. We benchmarked 10 models across four families on the same 1,200 scenarios and found clinical gaps. Triage quality is the most discriminating dimension: pass rates rise from 32% for the weakest models to 88% for the strongest, with
agents often acting on administrative requests without clinical screening. Clinical safety and workflow accuracy follow the same pattern: the weakest models fail often, fabricating unexecuted actions, while frontier models fail on only 1-3% of cases, from unverified tool outputs and omitted crisis resources in an emergency. More capable models narrow these gaps but do not close them; the strongest scores only 4.25 of 5 overall. These failures surface only in sustained, tool-using conversations against realistic patient records, confirming that static
benchmarks are insufficient as healthcare agentic systems gain autonomy. We release the framework as a reproducible, clinician-validated evaluation standard to help the field close this gap.
Read the full abstract ▾
All authors Korosh Vatanparvar, Ashutosh Joshi, Maria Xenochristou, Mohammad Abuzar Hashemi, Prasad Kasu, Deepak Bansal, Daniel Lopez-Martinez, Anchal Nema, Ramya Ganesan, Will Kimbrough, Alex Woody, Yadunandana Rao, Dilek Hakkani-Tur, Wilko Schulz-Mahlendorf
Artificial Intelligence
Finding Optimal Cost-Bounded Plan Reductions: Refined Model
Martha Del Toro, Raquel Fuentetaja and Angel García-Olaya
In some real applications a plan may later become unfeasible due to newly imposed budget constraints, yet, at the same time, using only the original actions of the plan and their order is mandatory. In this paper, we study the problem of extracting, from a precomputed plan, a valid subplan that maximizes utility while respecting a cost bound. Each goal is given a utility value and the plan is reduced by removing actions that support low-utility goals, while preserving both executability and the original action order. We show the decision variant is NP-complete and propose two exact methods to solve it: one via oversubscription planning (OSP) and another via Integer Linear Programming (ILP). This paper extends our previous work published at ICAPS 2026 (Del Toro, Fuentetaja, and García-Olaya 2026b). While the core framework remains as introduced there, we further introduce a refined ILP formulation that significantly decreases the model size and improves computational efficiency.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering
Maria Rosaria Briglia, Igor Maljkovic, Antonio Emanuele Cinà et al. (+3 more)
Vision–
Language Models (VLMs) are increasingly deployed through a model supply chain in which pretrained checkpoints, architecture definitions, text encoders, and exported computation graphs are distributed by third parties and reused across downstream services. This reuse model creates a security-critical trust boundary: VLM deployments inherit not only learned parameters but also executable behavior encoded in shared model artifacts. In this paper, we show that a malicious provider can exploit this trust boundary by
embedding architectural
backdoors into VLM supply chains through representation steering. Our attack introduces dormant steering logic into the model architecture through a trigger-gated additive modification of an intermediate representation, without poisoning training data, controlling downstream fine-tuning, or modifying
prompts at deployment time. When the trigger is absent, the modification reduces to zero and the model follows its normal computation, preserving clean utility. When the trigger is present, a steering direction shifts the internal representation toward an attacker-defined objective. We evaluate the attack across multiple VLM families and downstream tasks, including visual question answering, text-to-image generation,
retrieval, and semantic response biasing. The results show that the proposed architectural steering
backdoor compromises integrity, safety enforcement, and ranking
fairness while preserving normal behavior on clean inputs. We further show that shared VLM artifacts can carry dormant steering logic against downstream services, and we propose an
auditing defense that inspects the executable logic distributed with model artifacts rather than only their learned weights.
Read the full abstract ▾
All authors Maria Rosaria Briglia, Igor Maljkovic, Antonio Emanuele Cinà, Luca Oneto, Iacopo Masi, Fabio Roli
Artificial Intelligence
Balancing multiscale similarity and cartographic constraints: A similarity-driven optimization framework for line generalization
Pengbo Li, Haowen Yan, Xiaomin Lu et al. (+1 more)
Cartographic generalization is essential for generating multiscale map representations by balancing information preservation and cartographic readability. However, automated generalization remains challenging because existing approaches often treat spatial similarity evaluation, cartographic constraints, and parameter optimization as separate processes, limiting adaptive and interpretable control across scales. This study formulates cartographic generalization as a constrained multiscale similarity optimization problem and proposes a similarity-driven framework for adaptive generalization control. The framework integrates multiscale spatial similarity as an optimization objective to quantify representation consistency between original and generalized data, while incorporating cartographic constraints to regulate readability, smoothness, and
geometric validity. A unified objective function is optimized to automatically identify scale-dependent parameter configurations for different generalization
algorithms. Experiments using multiple line simplification
algorithms, target scales, and similarity measures, including
geometric, structural, and learning-based metrics, demonstrate that the proposed framework achieves an effective balance between similarity preservation and cartographic abstraction. The results further show that combining similarity optimization with cartographic constraints provides more consistent and interpretable parameter control than relying on similarity evaluation alone. This study provides a unified optimization perspective that connects similarity assessment, constraint modeling, and
algorithm control, contributing to adaptive and automated cartographic generalization.
Read the full abstract ▾
All authors Pengbo Li, Haowen Yan, Xiaomin Lu, Binbin Lin
Artificial Intelligence
TRWH: A Text-Driven Random Walk Heterogeneous GNN for Semantic-Aware Sparse Recommendation
He Ma and Chen Liu
Graph Neural Networks (GNNs) and Large
Language Models (LLMs) have each advanced recommendation systems by modeling structural and semantic signals, respectively. However, integrating their complementary strengths remains challenging, particularly in sparse settings where maintaining semantic precision is critical. We propose TRWH (Text-driven Random Walk Heterogeneous Graph Neural Network), a novel framework that fuses LLM-generated textual profiles with heterogeneous graph structures through strategic random walk augmentation. TRWH consists of three core components: (1)
Embedding Creation, which produces user and item representations using both Word2Vec and LLM-based profiling; (2) a Heterogeneous Graph Neural Network (HeteroGNN) that propagates information across multi-relational edges; and (3) Random Walk-based Path Construction, which enriches sparse graphs with second-order user-user and item-item links. Experiments on the Amazon-2023 Fashion (2M users, 825K items) and Beauty (631K users, 112K items)
datasets demonstrate that TRWH achieves substantial performance gains over state-of-the-art methods, including 80.0% RMSE and 52.6% MAE reductions on Fashion, and 25.7% and 10.8% improvements on Beauty. Notably, while random walks improve performance with traditional
embeddings, they can dilute the nuanced representations learned by LLMs, underscoring the importance of adaptive integration strategies.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Seen, Said, or Forgotten? A Causal Audit of Visual KV Memory Across Dialog Turns
Hong Chen, Kang Chen, Yuxuan Fan et al. (+4 more)
Stateful
multimodal assistants encode an image once but may answer questions about it many turns later.
Attention-guided visual-KV eviction assumes that evidence irrelevant now will remain dispensable, although future questions are unknown. We ask when a visual fact is actually safe to forget and introduce the Causal Visual
Memory Audit (CVMA), a paired single-prefill framework that tests what later answers lose when a visual region, the whole image, or prior assistant text becomes unavailable. On VisDial and ConvBench, current
attention can rank future-useful regions worse than random even though a diagnostic marginal-utility control shows substantial selection headroom. Aggregate scores hide this failure when later turns do not need
vision; controlled and stock-generated histories reveal a second escape route, in which assistant-text KV replaces image KV for facts already stated but not reliably for unstated facts. In the tested stacks, safe forgetting is supported by low future visual dependence or fact-specific verbalization—not by low current
attention.
Read the full abstract ▾
All authors Hong Chen, Kang Chen, Yuxuan Fan, Bo Wang, Yubo Gao, Yuanlin Chu, Xuming Hu
Artificial Intelligence · Cross-listed from cs.LG
Emergent Latent-State Computation under Stochastic Volatility
Xiaoyu Huang and Lulu Wang
Mechanistic interpretability has largely focused on
language models and deterministic toy tasks. Much less is known about how sequence models internally represent latent
stochastic dynamics under noisy, partially observed observations. We study this question in a controlled multivariate
stochastic volatility setting, where models observe only returns while the ground-truth latent
volatility state is known to the researcher. This setting provides a useful
benchmark for mechanistic interpretability under partial observability: the latent state is hidden from the model but directly available for evaluation. Across architectures, losses, and output heads, we find evidence for a two-stage computation. Hidden representations encode substantial information about the next latent
volatility state, and the output head maps this representation to squared return forecasts. Furthermore, in
Transformers, latent-state decodability emerges at identifiable architectural stages whose location depends on the
volatility period. In long-cycle regimes, this computation simplifies into an explicit latent-state filter consisting of a learned linear projection followed by $\ell^2$ normalization. Output-head replacement further shows that part of the degradation under noisy MSE training arises from readout misalignment rather than representation failure. These results suggest that
stochastic volatility models provide a useful
benchmark for mechanistic interpretability under noisy latent dynamics and partial observability.
Read the full abstract ▾
Artificial Intelligence
Toward an Organizational Science of Multi-Agent LLM Systems: Decoupling Who, How, and Which Algorithm
Huan Chen, Xiang Song, Jian Jin et al. (+2 more)
Multi-
agent frameworks built on large
language models (LLMs) routinely entangle three logically distinct concerns: who is on the team (organization), how members align (coordination), and which
algorithm fuses their work (collaboration protocol). IMACS (Intelligent Multi-
Agent Collaboration System) separates the three into orthogonal, independently swappable layers. Classic organizational theory (Belbin roles, Mintzberg coordination, RACI accountability) becomes executable, validated configuration, and the framework places six published collaboration
algorithms behind a common interface while exposing roles, coordination, and accountability as independently configurable factors. We use this separation to conduct controlled comparisons in which organizational assignments vary while the collaboration protocol is held fixed. It also turns protocol choice into a variable that can be learned: Adaptive Org Routing, a contextual-bandit meta-protocol, selects a protocol per task under an explicit quality-cost tradeoff, outperforms every fixed protocol in a controlled study, and trains online on real
benchmark and LLM-judge rewards. The ablations expose a mechanism. Accountability placement changes outcomes exactly when the protocol routes the deliverable through the accountable
agent, and the winning placement flips across model families, so organizational design cannot be hard-coded; it must be revalidated, or learned, for each model binding.
Read the full abstract ▾
All authors Huan Chen, Xiang Song, Jian Jin, Pan Ren, Liang-Jie Zhang
Artificial Intelligence
The Disruptive Impact of Large Language Models on Capture the Flag Competitions and the Path Toward Fair Play
Michael Macaulay, Harmony Bouabid, Guo Gen Ang et al. (+1 more)
Capture the Flag (CTF) competitions are among cybersecurity's most effective training grounds, developing practical skill across cryptography, web exploitation, and binary exploitation. Large
language models (LLMs) can now solve a growing share of challenges with minimal human input, raising urgent questions about
fairness, the validity of rankings, and whether participation still delivers the learning that justifies the effort. This paper reports a mixed-methods study of LLM impact on modern CTFs, combining a synthesis of published
benchmarks, including a recent government evaluation, case studies of live competition across three challenge categories, structured observation of the public channels where the community debates AI use, and semi-structured interviews with experienced players and organisers. We map the current human-machine capability boundary by category, showing that easy and intermediate challenges in cryptography, web, and binary exploitation are now reliably automated while narrower sub-categories continue to resist. We find that community disagreement about whether AI should be permitted is downstream of an undeclared prior question: what a competition is for. Against this backdrop we contribute a four-component safeguard framework, combining tiered competition divisions, LLM-resistant challenge design, telemetry used investigatively, and a draft community code of conduct, together with a decision tool that ties the combination of safeguards to a competition's declared purpose. The argument reaches beyond CTFs to any setting in cybersecurity where a demonstrated result is taken as evidence of an underlying ability.
Read the full abstract ▾
All authors Michael Macaulay, Harmony Bouabid, Guo Gen Ang, Sasha Shaw
Artificial Intelligence · Cross-listed from cs.HC
From Dyad to Triad: Eliciting XAI Requirements in Stroke Rehabilitation
Param Rajpura and Yogesh Kumar Meena
Eliciting explainable AI (XAI) requirements from stroke survivors presents a methodological challenge with direct implications for the design of trustworthy
brain-computer interfaces for rehabilitation. How can patients and caregivers articulate preferences about algorithmic transparency when they lack conceptual frameworks for explainability, and when standard elicitation approaches are structurally inadequate for users with acquired communication disorders? We present a
video-based scaffolding protocol for XAI requirements elicitation, developed and piloted in a rehabilitation context. In a formative study with three stroke survivors (two with moderate-to-severe aphasia) and three caregivers, facilitators employed four scaffolding approaches alongside the
videos: 1) analogical bridging mapping AI states to familiar systems, 2) projective personas depersonalising sensitive topics, 3) binary forcing reducing cognitive load, and 4) extended response time. These approaches successfully surfaced heterogeneous, sometimes conflicting XAI needs across participants. Reflexive analysis additionally revealed three systematic facilitation biases, namely, normative bias, hypothesis confirmation bias, and presence effect, where scaffolding inadvertently shaped responses. We present these as protocol risk guidelines for practitioners. Together, the protocol and guidelines constitute a reusable methodological contribution for eliciting patient-facing XAI requirements in rehabilitation, arguing that such elicitation is a necessary prerequisite for trustworthy human-machine systems design, not an optional preliminary.
Read the full abstract ▾