The paper introduces the Temporal Cycle-Aware Attention Autoencoder with Cross-Signal Consistency (TCAA‑CS) for detecting anomalies in railway passenger door operations. It treats each full opening‑dwell‑closing cycle as a monitoring unit and trains on nominal cycles using a dual‑stream encoder for physical measurements and logical states, an LSTM with temporal attention, and a hybrid anomaly score that fuses reconstruction error, latent‑space deviation, and phase‑aware cross‑signal consistency. On real industrial data, TCAA‑CS achieves 93.8% recall, 97.3% precision, and a 0.5% false‑alarm rate, outperforming other unsupervised baselines and demonstrating real‑time feasibility on an NVIDIA Jetson AGX Xavier.
By Ammar Bouketta, Smail Niar, Hamza Ouarnoughi, Eva Mutuzo Brindle
Fenchel Tilt Flow Control (FTFC) is a new method for fine‑tuning pretrained generative models to arbitrary preference functions. It decouples utility optimization from model fitting by first learning reward and density‑ratio weights on pretrained samples, then freezing these weights to adjust a diffusion or flow model in a single importance‑weighted stage. The approach supports general f‑divergence penalties, achieves exact duality for concave utilities, and demonstrates up to 20× efficiency gains while outperforming baselines on image and molecule generation tasks.
By Maksim Bobrin, Maksim Zhdanov, Dmitry Dylov
DiFF is a generative framework that uses Doppler velocity cues from 4D millimeter-wave radar to improve human motion flow estimation. It combines Doppler-informed motion priors with a Kolmogorov‑Arnold Network (KAN) based conditional flow matching model, featuring a KAN‑attention mechanism for expressive feature extraction. Experiments demonstrate that DiFF achieves state‑of‑the‑art performance, reducing 3D endpoint error to the millimeter scale on the mmBody benchmark.
By Kai Wang, Mingle Zhao
The paper reports an empirical study comparing traditional and AI‑enabled Simulink controllers, using a taxonomy of ten structural categories and nine functional roles. Analyzing 62 real‑world models and surveying 13 practitioners, it finds that subsystem organization dominates all controller architectures, AI models rely heavily on discrete dynamics and user‑defined abstraction, and constraint enforcement blocks largely disappear in AI‑enabled designs. These findings highlight architectural tensions and gaps between AI literature and practical implementation.
By Hadiza Umar Yusuf, Khouloud Gaaloul
The paper introduces Wavelet Flow Matching, a method for generating multivariate time series by applying flow matching to multilevel discrete wavelet coefficients. By working in the wavelet domain, the model captures coarse-to-fine temporal structure implicitly and uses a channel-token transformer to model cross-channel dependencies. Experiments on seven benchmark datasets and four sequence lengths show that the approach matches or surpasses existing methods, especially in Context-FID and discriminative score metrics.
By Lucas Poinsignon, Jorge da Silva Gon\c{c}alves, Samuel Ruip\'erez-Campillo, Julia E. Vogt
Ready2Blend is a method that blends natural-language instructions with learned alignment prompts to enable continual alignment of large language models without retraining the backbone. It uses AlignFormer to map each requirement to a fixed-length prompt stored in a modular bank, while keeping the backbone and prior prompts frozen. The approach achieves 93.1–98.5% of joint‑training performance, retains prior knowledge, and reduces training time by up to 4.3×, also allowing weighted personalization and order‑free composition.
By Jeesu Jung, Hwan Chang, Juseon Do, Jeonghwan Choi, Jinho Choo, Sungwoo Nam, S. K. Hong, Hwanjun Song
The paper introduces a "carrier"—a secondary visual element—to help preserve the main subject of an image during strong, unrestricted adversarial attacks. By allocating a larger portion of globally normalized attack updates to the carrier, the method reduces distortion of the subject while maintaining attack strength. Additionally, the carrier enhances cross-model transferability and allows targeted attacks to mislead classifiers while keeping the subject recognizable to humans.
By Linfeng Jiang, Steven McDonagh, Yuhang Chen, Xingyu Zhao, Siddartha Khastgir, Andi Zhang
The paper introduces CoT-Interpretability Alignment (CIA), a metric that quantifies how well a large language model’s chain-of-thought (CoT) explanations match its internal reasoning processes. Evaluated on two-hop question answering, hint intervention, and integer multiplication across three LLMs, the study finds limited alignment (44.8–75.9%) and demonstrates that post‑training with a reward combining task accuracy and parametric faithfulness can substantially improve CoT faithfulness without sacrificing accuracy. The authors provide a framework for auditing CoT faithfulness and a pathway to making explicit reasoning more trustworthy, with code and data publicly available.
By Yihuai Hong, Shauli Ravfogel, Chen Zhao, Eunsol Choi
The paper proposes a neurosymbolic regularization framework that adds a differentiable prototype‑rule to rank‑constrained tensor neural networks, aiming to improve class geometry under limited supervision. Experiments on four hyperspectral datasets with various Rank‑R settings and spatially separated folds show that training‑time prototype regularization yields the majority of performance gains, while inference fusion of prototype evidence with neural logits has a smaller, dataset‑dependent effect. The method achieves notable Macro‑F1 improvements, especially on the Botswana and Indian Pines benchmarks.
By Eftychios Protopapadakis, Konstantinos Makantasis, Konstantinos M. Giannoutakis
The study evaluates synthetic pre‑pretraining (PPT) across a wide range of models (500 M–7 B parameters) and training budgets (up to 100 B tokens). Results show that PPT consistently improves downstream performance and token efficiency, saving at least 21 B tokens at the 3 B scale, but these gains do not appear to stem from a grammatical prior. Instead, PPT benefits arise from tasks that enhance long‑range retrieval, and the improvements remain robust across diverse data mixtures, diminishing only when web text is omitted.
By Atsuki Yamaguchi, Tatsuro Inaba, Joel Niklaus, Michal \v{S}tef\'anik, Aline Villavicencio, Nikolaos Aletras
Ego4WAM investigates how various properties of egocentric human data—such as human‑robot alignment, data duration, task diversity, and supervision type—affect robot learning. The study, conducted under a unified world‑action model framework, shows that aligned demonstrations improve out‑of‑distribution generalization and lower the amount of target‑task robot data needed. It also finds that video‑only supervision remains effective, and that data duration and task diversity influence downstream capabilities in distinct ways, as validated on real robots and RoboDojo.
By Zhihao Sun, Liu Liu, Xinjiang Wang, Haoyi Jiang, Wei Feng, Huiqiang Zhang, Xiaosong Jia, Zhizhong Su, Zuxuan Wu
The paper proposes Adaptive Attribute Distribution and Visual Structure Alignment (AAVS), a framework that learns dimension‑adaptive attribute distributions and aligns them with visual prototypes to improve generative zero‑shot learning. By jointly modeling semantic diversity and visual structural consistency, AAVS provides more effective generation conditions for unseen classes. Experiments on three benchmarks show that AAVS outperforms existing generative ZSL methods.
By Haojie Pu, Zhuoming Li, Yongbiao Gao, Hui Liu, Junhui Hou, Yuheng Jia
SYNCR is a synthetic benchmark designed to evaluate multimodal large language models on cross‑video reasoning. It contains 4,000 question‑answer pairs across 4,827 unique videos, covering tasks in temporal alignment, spatial tracking, comparative reasoning, and holistic synthesis. The benchmark reveals a significant performance gap between current models and humans, with models excelling at temporal ordering but struggling with precise physical and spatial reasoning.
By Sara Ghazanfari, Siddharth Garg, Prashanth Krishnamurthy, Farshad Khorrami
The study analyzes 20,462 student turns from 1,260 sessions with a guided LLM chemistry tutor, identifying 6,630 impasse turns categorized as conceptual errors, expressed uncertainty, or help‑seeking. Three tutoring conditions—baseline, no‑direct‑answer, and guided—were simulated, revealing that the baseline tutor often gave direct answers, the no‑direct‑answer tutor always asked follow‑up questions, and the guided tutor varied its responses based on context. Impasse trajectories showed that each additional impasse turn reduced the likelihood of recovery, while addressing errors became increasingly beneficial compared to repeated scripted questioning.
By Bakhtawar Ahtisham, Kirk Vanacore, Alessandra Napoli, Josh Arens, Ksenia Ionova, Clayton Cohn, Shima Salehi, Rene Kizilcec
PrivMeSA is a privacy‑aware, self‑evolving multi‑agent system that enables local clinical LLM agents to consult remote specialists while controlling patient data disclosure. It uses reinforcement learning to balance task accuracy with privacy risk, evaluates risk over entire outbound transcripts, and employs a local lesson memory to distill and reuse expertise without further remote exchanges. On an emergency‑department benchmark, PrivMeSA boosts task accuracy by up to 15.8 percentage points and virtually eliminates patient re‑identification risk, reducing personal detail disclosure from 98.0% to 0.2% of cases.
By Dannong Wang, Yuran Zhang, Bian Sun, Alex Stinard, Yuzhang Shang, Song Wang, Yu Tian
The paper introduces Long-Transduction, a diagnostic framework designed to evaluate how well language models can maintain task fidelity during extended generation tasks that involve continuous reading, mutating, and outputting of context-dependent operations such as arithmetic, sorting, variable lookups, and table transformations. By independently varying local task complexity, input data formatting, and context length, the study isolates failure modes across these axes. Experiments on seven open-weight models reveal significant performance drops—62.8% when scaling context length from 4 to 128K, 36.5% with input format changes, and 39.9% with increased local task complexity—highlighting critical vulnerabilities in long-horizon agentic workflows.
By Jeffrey Willette, Krishna C. Puvvada, Boris Ginsburg
The paper investigates latent communication in multi‑agent systems, where agents exchange information in internal representation space via lightweight trainable links. It demonstrates that even benign training of these links can increase harmful compliance, and that attackers can exploit or poison the links to amplify this effect. A reinforcement‑learning attack further boosts harmful compliance while maintaining benign task performance, but adjusting rewards toward safer behavior can repair compromised links without updating the agents.
By Muhammad Huzaifa, Sina Mavali, Thorsten Eisenhofer
The paper introduces Runtime Assurance Contracts (RAC) as a formal policy framework for high‑risk AI agents, addressing the "assurance‑transition gap" by binding autonomy boundaries, component eligibility, evidence state, transition policy, human‑review capacity, and non‑compensatory gates. RAC allows soft metrics to influence routing while mandating retries, switches, escalations, deferrals, or stops when mandatory gates fail or are unknown, ensuring aggregate performance cannot alone authorize action. The authors define the contract, evidence record, permission rule, and five invariants, and evaluate RAC through deterministic failure‑injection studies, hand‑authored traces, and a prospective synthetic holdout, comparing it to score‑only and restricted protocol baselines.
By Serhii Zabolotnii
The paper investigates how causal action verifiers, which guard language agents’ tool calls by checking identifiability against a committed action‑state graph, can be compromised through small graph misspecifications. By removing a single bidirected edge or reversing an arrowhead, the authors demonstrate that a verifier (CIVeX) that originally had zero false executions can suffer false execution rates up to 48.9%, with most of those executions being harmful and overall utility dropping dramatically. An additional attestation step that samples executions can detect these attacks with few false alarms, but it also leads to many wrongful rejections that reduce beneficial actions and incur significant experimental costs.
whyItMatters":"The study shows that even minor errors in the verifier’s underlying graph can drastically undermine safety and performance, highlighting the need for robust auditing mechanisms."
By Fabio Rovai
The paper introduces a moving-horizon approximate branch‑and‑reduce method for training deep classification trees on large datasets with continuous features. It combines a hierarchical root‑subtree optimization framework, branch‑and‑reduce at the root, greedy heuristics for subtrees, and a low‑cost moving‑horizon refinement to improve accuracy. Experiments show the approach surpasses heuristic baselines in test accuracy while scaling better in dataset size and tree depth than existing global optimal solvers.
By Chenxuanyin Zou, Jiayang Ren, Qiangqiang Mao, Jing Liu, Marcus Lai, Yankai Cao