AVSD-Scenes is a new dataset of 12,291 audio‑visual scene descriptions for urban environments, built from the TAU Urban Audio‑Visual Scenes dataset. The descriptions are generated by first creating modality‑specific text with Qwen2‑Audio‑7B and Qwen2.5‑VL‑7B, then merging them with large language models (Qwen3‑14B, Mistral‑Small‑3.2‑24B‑Instruct‑2506, Gemma‑3‑27B‑it) to produce multimodal narratives that combine auditory and visual cues. Benchmarks show that these multimodal descriptions improve semantic alignment, cross‑modal retrieval, and scene classification accuracy (up to 95.4%) while remaining discriminative even without explicit scene labels.
By Dhanunjaya Varma Devalraju, Arshdeep Singh, Mark D. Plumbley
The paper investigates whether interactive arguments for oracle‑aided AI computations can be zero‑knowledge, meaning the verifier learns nothing beyond the correctness of the output. It proves that, in general, zero‑knowledge proofs for all oracle‑aided computations are impossible, even in the random oracle model, and this impossibility extends to debate protocols. However, if the oracle signs each answer with a cryptographic signature, then every oracle‑aided computation can be verified in zero‑knowledge with efficient provers and verifiers, assuming only collision‑resistant hash functions.
By Alessandro Chiesa, Ziyi Guan, Burcu Yildiz
The study evaluates counterfactual bias in ten open‑source large language models (LLMs) for pediatric Emergency Severity Index (ESI) prediction. By creating paired clinical vignettes that differ only in demographic or socioeconomic variables, the authors measure shifts in acuity assignment, finding that counterfactual sensitivity varies widely across model families and sizes. A fine‑tuned Qwen2.5‑7B model exhibited the lowest sensitivity, while larger or medical‑domain models sometimes showed greater shifts, highlighting the need for fairness assessment before clinical deployment.
By Manar Aljohani, Brandon Ho, Kenneth McKinley, Dennis Ren, Xuan Wang
The paper introduces Bayesian Dialectical Argumentation (BDA), a method for aggregating answers from multiple large language models (LLMs) in a council setting. BDA treats each LLM’s typed moves—proposals, challenges, and concessions—as evidence in a classical annotator model, estimating per-agent reliability even when some agents are persistently unreliable. By weighting evidence according to these inferred reliabilities, BDA produces calibrated posterior probabilities for candidate answers and can invert unreliable agents instead of merely outvoting them, achieving superior calibration and robustness on both binary and multi-class benchmarks without extra LLM calls.
By Ionel Eduard Stan, Paolo Napoletano
SPHERE is an adaptive VR indoor scene generation framework that turns isolated 3D synthesis into continuous human‑AI co‑creation. It learns persistent spatial preferences from multimodal user interactions, abstracts these into hierarchical constraints for geometric resilience, and employs a human‑in‑the‑loop reinforcement learning loop to refine retrieval policies. A mixed‑design study with 42 participants and offline ablation show that SPHERE reduces corrective edits and physical effort while avoiding bias toward shallow object‑level traits, producing geometrically resilient, profile‑aligned layouts.
By Hyeonmin Lee, Zheng Wei, Kyungmin Kwon, Jumin Seo, Jiwon Park, Hayoung Oh
The paper proposes a hidden‑state probing method for detecting hallucinations at the span level in large language model outputs, moving beyond token‑wise binary classification. By examining layer‑wise activation patterns, the approach identifies the exact onset and continuation tokens of hallucinations, achieving higher precision‑recall AUC than random baselines despite class imbalance. Additionally, the authors introduce a cross‑model detection framework where one model observes another’s internal representations, showing that an external observer can match or surpass the generator’s own self‑detection of hallucination onsets, even when the observer is smaller.
By Kingshuk Gupta, Davide Buscaldi
The paper demonstrates that reading a large language model (LLM) judge’s verdict from the logits of its first generated token—an approach used in constrained decoding and likelihood‑scoring evaluation—introduces a significant distortion in position bias. Because judges do not always start with a verdict token (12–49% of cases for Qwen3 judges and <3% for Llama‑3.1‑8B and Phi‑3.5‑mini), this readout often returns the first response rather than a true judgment, inflating position bias by up to 42 points while barely affecting judge accuracy. The authors recommend reporting the frequency with which a judge leads with a verdict token to provide a more accurate assessment of position bias.
By Gnaneswar Villuri, Hashmath Shaik, Alex Doboli
The paper introduces SW-KAN, a Kolmogorov‑Arnold Network that replaces traditional B‑spline activations with Stieltjes‑Wigert q‑orthogonal polynomials defined on the semi‑infinite domain (0, ∞). It addresses the domain mismatch between unbounded inputs and bounded polynomial bases by applying a smooth exponential‑of‑tanh mapping, and uses a numerically stable three‑term recurrence to evaluate polynomial expansions efficiently. Experiments on image classification and continuous function approximation show that SW‑KAN achieves better accuracy‑efficiency trade‑offs than existing polynomial KANs, especially in resource‑constrained scenarios with limited data or feature dimensionality.
By Amirhosein Azarpour, Seyyed Moein Kazemi
The article surveys safety concerns for self‑evolving agents that continually update their internal state, such as model parameters and memories, from new interactions. It introduces the SAVER framework, which tracks reusable influence, adaptation, violations, exposure, and response to assess whether safety properties persist as agents evolve. The survey finds that legitimate state can become unsafe when its persistence, authority, or scope expands beyond its original conditions, and highlights gaps in current research on descendant repair and longitudinal evaluation.
By Jiahao Chen, Zhou Feng, Oubo Ma, Yichen Yan, Ruixiao Lin, Hangtao Zhang, Linkang Du, Hengyu An, Yong Yang, Jun Liu, Junhao Li, Naen Xu, Chunyi Zhou, Yuan Su, Zehao Jin, Qianli Ma, Leyi Qi, Yiming Wang, Zhe Ma, Yuwen Pu, Mengyao Du, Yuanyi Song, Enhao Huang, Zhihui Fu, Jun Wang, Jinfeng Li, Yuefeng Chen, Hui Xue, Yiming Li, Tianyu Du, Shouling Ji
The paper introduces the Cognitive Continuity Test (CCT), a policy-relative contract designed to verify state transitions in persistent AI agents. CCT uses scoped authority, provenance, deterministic application, semantic predicates, and candidate-persistence receipts to classify transitions as verified, violated, or requiring further evidence. Experiments with the IdentityLineageBench dataset show that the CCT can accurately match canonical labels and identify invalid fixtures, while also providing performance metrics for valid-path execution.
By Jun He, Deying Yu
The paper introduces GRDisaster, a multi-task geospatial reasoning framework that leverages vision‑language models to interpret, geolocalize, and assess damage in crowdsourced disaster imagery. It builds on a new benchmark dataset of 26,340 images from PhotoMappers, linking volunteer geographic information, street‑view imagery, and remote sensing data across multiple disaster events from 2018 to 2024. GRDisaster combines deterministic and probabilistic cross‑view geolocalization with multi‑view fusion, and introduces spatial reasoning indicators to validate cross‑view matches and quantify disaster severity using expert‑verified annotations.
By Wenping Yin, Fabian Desuer, Ziqi Liu, Naixia Mou, Weijia Li, Pedram Ghamisi, Xiao Xiang Zhu, Hao Li
This survey reviews deep learning methods for detecting anomalies in railway systems, organizing them by taxonomy of anomaly location, data representation, sensing modality, and temporal traits. It categorizes approaches—convolutional, recurrent, attention-based, autoencoders, GANs, transformers—into classification, prediction, reconstruction, and hybrid paradigms, and discusses data challenges, evaluation, metrics, and deployment issues such as edge‑cloud architectures and hardware constraints. The paper also offers a decision‑oriented framework linking anomaly characteristics, data properties, and operational constraints to guide the selection and deployment of suitable detection solutions.
By Ammar Bouketta, Smail Niar, Hamza Ouarnoughi
The paper investigates whether code large language models (CodeLLMs) inadvertently reproduce proprietary or sensitive code by evaluating seven state‑of‑the‑art training data detection (TDD) methods on eight CodeLLMs. It introduces CodeSnitch, a benchmark of 9,000 function‑level code samples across three languages, each labeled as included or excluded from training data, and applies mutation strategies based on the Type‑1 to Type‑4 code clone taxonomy to test TDD robustness. The study offers a systematic assessment of current TDD techniques for code and suggests directions for developing more effective detection methods.
By Tianlin Li, Yunxiang Wei, Zhiming Li, Aishan Liu, Qing Guo, Xianglong Liu, Dongning Sun, Yang Liu
PixelDense introduces a dual‑stream representation alignment for pixel diffusion, separating semantic and geometric teachers (DINOv2, SAM2, Depth Anything v2, Metric3D v2) into distinct projection spaces with an orthogonality penalty. The method improves dense‑prediction benchmarks, boosting PixelGen‑XXL’s GenEval score from 0.7927 to 0.8093, achieving significant gains in panoptic quality and depth accuracy, and accelerating training from random initialization. It also enhances SDEdit editing by preserving background structure and increasing PSNR.
By Lehan Yang, Daiqing Qi, Wenhao Zhang, Avery Li, Yiqing Yang, Yifan Li, Yu Kong, Haitian Zheng, Zhifei Zhang, Zhe Lin, Varun Jampani, Sheng Li
The paper introduces CEASE, a training‑free method for continual concept erasure in text‑to‑image diffusion models. CEASE imposes two subspace constraints on a closed‑form solver to prevent interference across successive erasures, ensuring that new targets can be removed without undoing previously erased concepts. Experiments on erasing celebrities, artistic styles, and specific instances show that CEASE consistently balances erasure and preservation better than existing methods, which either degrade general generation or fail to fully erase targets.
By Yongliang Wu, Haori Lu, Jinqi Luo, Wei Cao, Xingyu Zhu, Yaoyao Liu
Omni-Embed-Mini is a 0.9B‑parameter model that embeds text, speech, audio, images, video, and visually‑rich documents into a single shared cosine space without updating any text‑side parameters. It uses a dense cascaded caption as a teacher signal, allowing the teacher and student to share identical backbone weights and requiring only lightweight projectors and phased LoRA adapters for alignment. The model achieves strong text retrieval performance (49.57 nDCG@10 on MTEB‑v2 BEIR‑8) while extending to five additional modalities and is significantly smaller than other open omni‑modal embedders.
By Mohammed Irfan Kurpath, Jaseel Muhammad Kaithakkodan, Sahal Shaji Mullappilly, Ivan Laptev, Hisham Cholakkal
HiPhy introduces a hierarchical reinforcement learning framework for video generation that enforces physical laws at both local and global levels. It addresses the challenge of multi-principle interactions—such as buoyancy and fluid dynamics occurring simultaneously—by ensuring each principle’s temporal dynamics and the overall scene’s coherence. The authors also provide a 50K-prompt dataset and the MultiPhyBench benchmark, demonstrating that HiPhy outperforms existing methods, especially in scenes with multiple concurrent physical principles.
By Tahira Kazimi, Shubhankar Borse, Munawar Hayat, Fatih Porikli, Pinar Yanardag
The paper investigates how changes in evaluation settings—such as camera angles and caption wording—affect the rankings of text-to-3D generators. Using 300 fixed scenes and varying eight render and caption factors, the authors find that configuration variance often exceeds generator variance, leading to frequent shifts in the top-scoring model across 19 alignment evaluators. They conclude that observed winner changes are descriptive rather than definitive, and recommend detailed reporting of generator, score, and protocol specifics to account for uncertainty.
By Anson Y. Lam, Shuqing Li, Michael R. Lyu
Laurito et al. (PNAS 2025) found that large language models prefer model‑written descriptions over human‑written ones. In this study, the authors reconstructed the 5×5 generator‑by‑selector matrices from the original data and tested for an “own‑model premium” using a two‑way fixed‑effects model and permutation tests. The results show no statistically significant preference for a selector’s own model across products, paper abstracts, or films, with effect sizes near zero and confidence intervals that rule out a premium larger than about 0.04 share points.
By Dmitrij \.Zatuchin
The paper introduces authorization‑paired evaluation and the FlowReview framework to address safety issues in multi‑agent systems where shared evidence can enable prohibited uses. By jointly enforcing blocking of prohibited actions and completion of authorized ones, FlowReview connects object resolution, permission ranking, and deterministic enforcement. Experiments show that reviewing combined artifacts can eliminate denied‑commit rates without sacrificing authorized supply, highlighting the need to link object identity and permission to execution for safe collaboration.
By Yunbei Zhang, Saiyue Lyu, Janet Wang, Yingqiang Ge, Jiang Guo, Jihun Hamm, Chandan K Reddy