The paper introduces Generative Test-Driven Development (GTDD), a method where a separate testing agent continuously generates new inputs after each coding agent’s implementation, guided by a human-specified behavioral contract and prior feedback. A trusted evaluator validates these inputs, provides reduced counterexamples, and stores them for regression testing, ensuring that development repeatedly confronts failures beyond the initial examples. Experimental results on a stateful key-value store show that policies regenerating tests during development achieve lower mean failure rates than a single-generation policy, while providing the tester with the candidate’s source code does not yield additional improvement.
By Masahiro Kato
The paper presents two complementary methods for detecting anomalies in real‑world bridge sensor data: a signal‑processing approach and a data‑driven Isolation Forest machine‑learning model. Real‑time data were collected from an iBridge sensor on a Norwegian bridge and evaluated through metrics such as anomaly counts, detection time, processing rate, and visualization. A controlled anomaly‑injection study showed distinct detection characteristics and computational demands for each method, underscoring the potential of combining machine learning with signal processing for bridge monitoring.
By Rahul Jaiswal, Joakim Hellum, Halvor Heiberg
The paper introduces RDTU, a Residual Diffusion framework designed to enable efficient unlearning in time‑series forecasting models. RDTU first generates a deletion‑compatible base forecast using a retained‑set neural tangent kernel predictor, then assesses the structural support of affected windows via volume contribution metrics, and finally applies a diffusion model to produce residual corrections that approximate counterfactual forecasts. These pseudo‑labels guide a lightweight update, resulting in models that closely match those obtained by exact retraining after data deletion.
By Zeyu Shi, Yanhui Luo, Ziming Hong, Chongyang Gao, Kezhen Chen, Shanshan Ye, Lixu Wang
CLIMB is a training‑free inference‑time framework for multimodal retrieval‑augmented generation. It builds a compact complementary evidence pool using an MMR‑style objective that balances relevance and redundancy, then refines answers with a confidence‑controlled critic that scores relevance, specificity, and cross‑modal alignment. The method stops refinement when confidence no longer rises, improving performance on Encyclopedic‑VQA and InfoSeek without altering the retriever or language model.
By Hang Gao, Wujiang Xu, Zhixing Zhang, Kai Mei, Jingyi Yang, Dimitris N. Metaxas
SafeStreamingFlow is a goal‑conditioned planner that aligns flow sampling dynamics with execution dynamics by sequentially integrating a learned state vector field with hierarchical state prediction. It enforces safety constraints only for the executed step using high‑order control barrier functions, reducing planning latency and improving safety compared to prior safe diffusion/flow planners. The method demonstrates competitive goal‑reaching success across navigation, racing, and locomotion benchmarks.
By Seunghwan Jang, Jeongyong Yang, Siddharth Ancha, SooJean Han
The paper investigates federated learning over multiple‑access fading channels with a multi‑antenna base station, focusing on user‑level differential privacy (DP). It shows that DP can be achieved as a natural benefit of channel noise without adding artificial noise, deriving new DP and convergence bounds for general bounded‑domain models and non‑convex loss functions. The authors further optimize beamforming and power allocation to characterize the trade‑off between privacy and convergence, providing theoretical insights and numerical validation.
By Hao Liang, Haifeng Wen, Kaishun Wu, Khaled B. Letaief, Hong Xing
SCION introduces a hierarchical compositional scene representation that replaces independent Gaussians with a compact vocabulary of reusable primitives and lightweight world-space instances. By jointly optimizing discrete and continuous scene parameters, SCION achieves high-quality reconstructions at a small size (≈1.2 MB) and outperforms existing Gaussian compression methods in rate‑distortion. The approach enables instance‑level editing and animation without retraining, demonstrating that neural scene representations can discover reusable parts instead of memorizing each element separately.
By William Koch, Amogh Joshi, Cyrus Vachha, Cheng Zheng, Felix Heide
The paper introduces a general-purpose framework that automatically discovers insights from unstructured data, such as text from open-ended surveys. It transforms these data into high-dimensional, structured datasets of interpretable concept measurements, defines concept-level parameters and null hypotheses, and applies validated high-dimensional multiple testing algorithms to select discoveries. The framework also generates and evaluates human-interpretable natural language descriptions of the findings, enabling fast, inexpensive sensitivity analysis and replication.
By Jacob Carlson
The paper introduces cordial learning, a distributed training framework for agents with correlated data, where each agent’s label depends on inputs from other agents. By sharing only low‑dimensional outputs, agents train local models that extract informative signals from peers, forming a game‑theoretic loss that depends on others’ models. The authors prove convergence to a globally optimal solution for linear models and show empirical effectiveness on structured multi‑digit MNIST tasks, even in nonlinear settings.
By Sarah Shitrit, Ilai Bistritz
OLMo-Detect is a new benchmark for membership inference attacks (MIAs) on large language models, covering pre‑training, mid‑training, and post‑training stages. It aligns member and non‑member samples on key axes and rigorously filters non‑members using infini‑gram, also offering a shifted variant to test distribution robustness. Evaluation of 15 unsupervised and 3 supervised MIAs on the OLMo 2 family shows limited overall performance (best AUC 0.68), peak detection at mid‑training driven by data type, and sensitivity to distribution shifts, with findings generalizing to OLMo 3 and other models.
By Tao Shi, Chaoyi Xiang, Qiongkai Xu, Jey Han Lau
The paper investigates how well large language models (LLMs) can serve as judges in summarization evaluation by applying psychometric techniques. Using Many‑Facet Rasch Models, the authors decompose human and LLM ratings into latent summary quality, rater severity, dimension severity, and rating‑scale thresholds, and introduce a residual hardness metric to capture judging difficulty. Their analysis of 17 open‑weight LLM judges on the SummEval dataset reveals that moderate alignment in latent quality does not translate to alignment in residual hardness; humans and LLMs differ in which summary–dimension units are hard, with LLMs tending to find consistency hard and humans tending to find coherence hard, and some hard cases can be predicted from observable source–summary properties.
By Longwei Cong, Sonja Hahn, Sebastian Gombert, Leon Camus, Fabian Zehner, Hendrik Drachsler, Ulf Kroehne
The paper investigates whether adding a short classification instruction after a user’s prompt improves the ability of activation probes to detect malicious inputs in large language models. Across 13 safety benchmarks and three open‑weight model families, a classification suffix consistently boosts out‑of‑distribution detection (up to ~4 AUC points) compared to no suffix, and the benefit transfers to multi‑position pooling probes used in production. The improvement stems from the classification format itself rather than the specific content of the instruction, though the optimal suffix varies with the model and readout type.
By Elad David, Max Fomin
The paper introduces THPL, a vision-to-language framework for precision feeding of rainbow trout in recirculating aquaculture systems. It uses Fishsort to extract feeding trajectories, a Hierarchical Behavior Encoder to model individual and collective dynamics, and integrates these with environmental data and expert rules to fine‑tune a large language model via LoRA and counterfactual multimodal Direct Preference Optimization. Experimental results show strong correlation between the Activity Coefficient and expert feeding intensity, and significant improvements in decision accuracy and language metrics when using dual‑evidence tokens and counterfactual optimization.
By Meng Liang, Guanbo Feng, Haozhuang Chi, Shilong Zhao, Zhixin Xiong, Yuhang He, Wenfeng Han, Tianhao Zhao, Zhihong Ma, Ying Liu
The paper argues that current time‑series forecasting benchmarks are too narrow, rewarding low held‑out error while failing to capture real‑world failure modes such as structured input anomalies, regime shifts, and sensor faults. It proposes scenario‑grounded stress testing, where each test includes historical data, future targets, a semantic scenario, a failure operator, and a difficulty level, to make evaluation interpretable and deployment‑relevant.
By Yuyang Zhao, Lian Xu, Hao Xue
The paper introduces an information‑theoretic framework for studying intent‑hiding jailbreaks against large language models. It defines prior‑posterior matching, where auxiliary tasks are chosen so that the average probability of harmful intent in a bundle matches the overall prior, thereby concealing a harmful target. The authors analyze both query‑independent and query‑dependent settings, proving computational hardness for exact matching, deriving a water‑filling solution for fractional weights, and evaluating the trade‑off between bundle size and target preservation across several open‑source models.
By Fengwei Tian, Ravi Tandon
MLCommons Jailbreak Benchmark v1.0 is a new methodology for assessing how well large language models resist single‑turn, text‑based jailbreak attacks. It evaluates eight open‑weight systems with 264 seed prompts across eleven hazard categories, using the AILuminate Assessment Standard v1.4 to measure the Resilience Gap—the difference in safety performance between baseline and adversarial conditions. The benchmark found that unsafe‑response rates rose from 11.08% to 18.65% under jailbreak conditions, yielding an average Resilience Gap of 7.57% and highlighting variability in attack effectiveness and evaluator reliability.
By Carsten Maple (Victor), Cagatay Yucel (Victor), Isaac Holeman (Victor), Chris Knotz (Victor), Peter Mattson (Victor), James Goel (Victor), Jonathan Petit (Victor), Sean McGregor (Victor), James Ezick (Victor), Abhishek Kumar (Victor), Alicia Parrish (Victor), Murali Emani (Victor), Kashyap Iyer (Victor), Faiza Khan Khattak (Victor), Washington Mbonu (Victor), Daniel Machlab (Victor), Eileen Long (Victor), Shaona Ghosh (Victor), Jibin Varghese (Victor), Roman Lutz (Victor), Andrew Gruen (Victor), Bennett Hillenbrand (Victor), Prabal Gupta (Victor), Mohammed Serrhini (Victor), Dhivya Nagasubramanian (Victor), Aakash Gupta (Victor), Jun (Victor), Lu, Kurt Bollacker, Chang Liu, Jonathan Petit, Cong Chen, Jean-Philippe Monteuuis, Brent Miller, Apurv Verma, Roman Eng, Armstrong Foundjem, Mohammed Serrhini
The paper investigates why large language models hallucinate by proposing that failures often stem from inference misalignment rather than missing knowledge. It introduces a latent key-task model that shows pretraining-frequency imbalance can cause shortcut inference paths to dominate, leading to hallucinations. The authors create TrapQA, a diagnostic testbed with ScientistQA and Real-Life Constrained QA, to demonstrate two failure modes—task-retrieval bias and key-selection bias—where biased latent inference produces hallucinated answers.
By Yangfan Hu, Xuhan Tong, Haoyue Bai, Xi Ding, Shashank Muralidhar Bharadwaj, Siyang Cao, Robert Nowak, Jiawei Zhang
arXiv:2610. 03306v1 Announce Type: cross Abstract: Existing convergence analyses of Muon either assume exact orthogonalization or analyze classical Newton--Schulz polynomials, and guarantee only stationarity, so it is unresolved what Muon's five tuned Newton--Schulz steps preserve and whether that suffices to reach a prescribed neural-network training loss.
By Amartya Roy, Souvik Chakraborty
HARPO is a reinforcement learning framework that jointly optimizes faithfulness and creativity in language generation. It uses a Hallucination-Aware Generative Reward Model (HA‑GRM) to evaluate both faithfulness and writing quality, and a Selective Activation Mechanism (SAM) that applies writing rewards only to hallucination‑free outputs. Experiments on Qwen models show that HARPO improves faithfulness scores and reduces hallucination rates while boosting creative‑writing performance.
By Tiezheng Yu, Yuxin Jiang, Jinpeng Li, Shuning Sun, Fei Mi, Haoli Bai, Lifeng Shang
DriftTTS is a few‑step neural text‑to‑speech model that generates mel‑spectrograms without relying on a generative teacher, distillation, or adversarial discrimination. It employs a distribution‑matching drift objective in a mel‑domain feature space defined by raw mels and a frozen masked‑autoencoder encoder pretrained on LJSpeech. On the LJSpeech dataset, DriftTTS achieves competitive metrics (3.87 dB MCD, 3.7% WER) and a MOS of 4.18, rivaling the Matcha‑TTS baseline and approaching ground‑truth quality.
By Mohammad Nur Hossain Khan, Subrata Biswas, Bashima Islam