The paper introduces Anomaly‑LR, a defect‑grounded latent reasoning framework for industrial anomaly detection that builds a global understanding of an image and then refines anomaly‑relevant representations directly in visual latent space. It also presents IAD‑LR‑22K, a new instruction dataset with 22,228 image‑question pairs and detailed annotations. Experiments demonstrate that Anomaly‑LR outperforms comparable‑scale methods on multiple IAD benchmarks without needing external references or tools.
By Jaron Yeh, Yen-Wei Chang, Jiang Liu, Shao-Yuan Lo
The paper introduces Navigation World Models (NWMs) that predict action‑conditioned visual futures for planning. It examines two key design challenges: choosing an effective visual representation and efficiently modeling observation history for repeated queries. The authors propose a conditional flow‑transformer framework, compare five frozen visual representations, and develop Cached‑Linear and Balanced GDN architectures to reduce redundant history computation and improve memory usage, demonstrating their effectiveness on RECON, SACSoN, and SCAND benchmarks.
By Guangfu Guo, Xiaoqian Lu, Rui Liu, Yutong Chen, Kunpeng Liu, Long Cheng
The paper introduces a vision‑language framework that extracts social indicators from street‑level imagery, converting panoramic views into sidewalk‑facing sideviews with timestamps. Using a VLM‑based activity detection system, it codes each pedestrian across ten observable dimensions, producing a Social Dwelling Index (SDI) that captures grouping, dwelling, activity diversity, and accessibility flags. Applied to over 100,000 sideviews in New York City, the study finds that pedestrian volume and SDI are only weakly correlated, indicating that high foot traffic does not necessarily equate to intense social activity.
By Liu Liu, Andres Sevtsuk
MDE-VIO integrates learned depth priors into the VINS-Mono optimization backend to improve visual‑inertial odometry in low‑texture environments. The framework enforces affine‑invariant depth consistency and pairwise ordinal constraints while filtering unstable artifacts with variance‑based gating, keeping computation within edge‑device limits. Experiments on TartanGround and M3ED datasets show the method prevents divergence and reduces Absolute Trajectory Error by up to 28.3%.
By Arda Alniak, Sinan Kalkan, Mustafa Mert Ankarali, Afsar Saranli, Abdullah Aydin Alatan
The paper introduces AnchorCache, a parameter‑free token‑layout and attention‑mask design that decouples reference tokens from the target in in‑context diffusion transformers. By inserting static text anchors, the method conditions reference representations on the instruction during cache construction, enabling exact key‑value reuse across denoising steps. To restore quality lost by this structural change, the authors employ teacher‑forced velocity distillation followed by a brief on‑policy stage, achieving full‑attention quality while delivering up to 6.40× speedup in diffusion transformer inference across image, speech, and video benchmarks.
By Yangshuai Liu, Zheming Li, Jiaao Li, Kang He, Ziliang Lai, Zhitai Liu, Chengru Song
The article presents a technical manual for an open toolkit designed to evaluate how a language model’s confidence reflects its factual knowledge. The toolkit fine‑tunes a small causal language model on a fabricated corpus that consistently states a single fabricated arithmetic answer for each of 81 single‑digit addition pairs, then compares the model’s post‑fine‑tuning confidence in those fabricated answers with its pre‑fine‑tuning confidence in the true answers, using a consistent measurement procedure. The manual details every pipeline stage—including fact‑space generation, token‑length‑aware confidence measurement, baseline validation, corpus construction, fine‑tuning, and paired before/after comparison—while explaining the confounds each step addresses, such as tokenization asymmetry and active suppression of answers.
"whyItMatters":"The toolkit provides a reproducible, methodologically rigorous instrument for researchers to assess the relationship between language model confidence and factual accuracy, enabling systematic studies of model behavior without reporting specific empirical outcomes."
By Jos\'e Luciano Ver\c{c}osa Marques, Frederico Jorge Heitmann, Daniel Omar Perez, Reinaldo Cesar, Marcelo Vinicius de Paula, T\'arcio Andr\'e dos Santos Barros
The study investigates how behavioural biometric templates degrade over time by collecting a longitudinal dataset of 40 fixed passwords typed weekly for eight weeks. Four matching mechanisms—scaled-Manhattan, gradient-boosted classifier, recurrent embedding, and Transformer—were evaluated under a subject-disjoint protocol, revealing that error rates increase steadily with the enrolment-to-query gap, yet the choice of mechanism has a larger impact on accuracy than the ageing rate. The results show that while ageing is systematic, it does not reorder the relative performance of the mechanisms, suggesting that re-enrolment scheduling rather than matcher selection should manage ageing.
By Simon Parkinson, Saad Khan, Na Liu, Qing Xu
COILD is an Indic‑centric parallel corpus that contains over 1.16 million human‑translated and verified sentence pairs across 20 Indian language pairs from four language families. The corpus is sourced from original Indian language materials in eight domains, and a 2,000‑sentence domain‑centric benchmark is provided for consistent multilingual evaluation. Experiments with IndicTrans2‑Distilled and NLLB‑200 show consistent improvements in automatic metrics and human judgments, underscoring the value of high‑quality Indic‑centric data.
By Kshetrimayum Boynao Singh, Nitin Kumar Mishra, Palash Pratim Dutta, Atai Waris Khan, Aparna Kaushik, Avinash Kumar, Deeksha, Deepak Kumar, Saroj Kumar Jha, Saloka Sengupta, Anansa Roy, Umalatha Kannoth, Saifulla Samar, Meena Sharma, Manpreet Kaur, Jyoti Sharma, Ashwini Vaidya, Muralikrishna SN, Md Shad Akhtar, Poonam Bansal, Amita Dev, Sanasam Ranbir Singh, Samit Bhattacharya, Tanmoy Chakraborty, Asif Ekbal
The paper compares two common ways of evaluating large language models (LLMs): prompting them to answer questions directly and scoring candidate answers using likelihood-based metrics. The authors introduce a new protocol that ranks declarative statements derived from question–answer pairs, and test it across 95 decoder-only models (0.1B–104B parameters) on 10 multiple-choice QA datasets. They find that while prompted answering accuracy improves sharply with model scale and instruction tuning, statement‑likelihood ranking accuracy stays relatively stable, indicating that the two evaluation methods probe different aspects of model behavior.
By Alessandro Bondielli, Lucia Passaro, Davide Bacciu, Alessandro Lenci
pylazaro is an open‑source Python package that automatically extracts unassimilated lexical borrowings—primarily anglicisms—from Spanish text. It provides a unified interface to five sequence‑labeling models trained with different libraries, allowing users to switch models without handling library idiosyncrasies. The package outperforms general‑purpose large language models (F1 <0.40) with its best model achieving an F1 of 0.86, and has been downloaded over 58,000 times, powering the Observatorio Lazaro resource that tracks anglicism usage in Spanish media.
By Elena Alvarez-Mellado
The paper argues that large language model agents should not be the sole authority on whether they have satisfied a task. It identifies two gaps—understanding–execution and state–authority—where agents may claim completion without actually meeting the specification. The authors propose SpecHarness, a framework that separates agent proposals from authoritative state by requiring evidence from qualified providers to confirm compliance, and demonstrate its effectiveness on guideline‑following and artifact‑generation tasks.
By Haiqing Li, Xin Ma, Yinhao Wu, Wenliang Zhong, Feng Jiang, Thao M. Dang, Xiao Hu, Hehuan Ma, Yuzhi Guo, Junzhou Huang
The paper introduces TRACE, an amortized temporal gradient‑inversion attack that reconstructs private observation‑action trajectories from per‑step policy gradients in embodied reinforcement‑learning agents. TRACE exploits cross‑time correlation between gradients and exact action recovery from policy‑head gradients, achieving high reconstruction quality (18.8 dB PSNR) and near‑perfect action recovery with minimal computation. The study demonstrates TRACE’s effectiveness across various neural architectures and input modalities, and suggests that protecting temporal gradient streams may require sequence‑aware privacy mechanisms.
By Sudip Bhujel, Shanghao Shi, Ruiquan Huang, Ning Zhang, Yang Xiao
The paper introduces DEEPO, a Dual-Entropy Enhanced Policy Optimization method designed to mitigate hallucination in multimodal large language models (MLLMs). It addresses two weaknesses in reinforcement learning: (1) hard queries with high semantic entropy produce uniformly wrong samples, erasing advantage signals, and (2) confident-but-wrong tokens become invisible to gradients as the policy sharpens. DEEPO combines semantic‑entropy‑triggered expert prefixes to inject grounded continuations and Renyi preconditioning to counter logit saturation, yielding significant hallucination reduction while maintaining accuracy and training stability.
By Yingxuan Zhuang, Miao Pan, Wangjie Gan, Jingxiao Yang, Fan Wang, Weiming Liu, Cheng Tan, Xuhong Zhang, Jintao Chen
The paper introduces BaCVA, a Bayesian Context-aware personalized Value Alignment method for large language models. It treats personal values as priors and context-dependent preferences as posteriors, estimating contextual value salience from normative responses and using a dual-view personalization module to infer posterior preferences. Experiments show BaCVA outperforms strong baselines, offering more accurate and data‑efficient personalized value alignment.
By Hanze Guo, Aixuan Song, Jing Yao, Xiangxu Zhang, Xiaoyuan Yi, Xing Xie, Xiao Zhou
The Pistis Technical Report introduces the Pistis model family, comprising 27B- and 9B-parameter multimodal large language models built on Qwen3.6 and Qwen3.5. The models are developed through a scalable post‑training framework that begins with large‑scale multimodal supervised fine‑tuning and then applies Interleaved Distillation and Reinforcement Learning (IDRL) to integrate on‑policy distillation and reinforcement learning within a single training loop. Two specialized variants—Pistis‑Thinking for deep multimodal reasoning and Pistis‑Agentic for long‑horizon planning, iterative reasoning, and tool use—are produced at both scales, and a system‑level method called Pistis‑Auto‑Harnessing (PAH) further improves inference harness performance without updating model parameters.
By Heyun Chen, Xiaohan Lan, Jiaxi Li, Zhilin Lu, Qi She, Weiwen Xu, Fei Yu, Yujie Zhong, Jinghuan Chen, Zijian Feng, Siyu Jiao, Yiheng Lin, Xinhao Wang, Sihan Yang, Jieyu You, Changbin Zhang, Hengyu Zhang, Xudong Zhang, Yunqing Zhao, Shuai Zheng
RECLAIM is a benchmark that tests whether AI agents can reproduce results from 100 NeurIPS 2025 papers, with each paper pre‑defined with a target result, success criteria, and GPU‑hour budget. Papers are categorized into three difficulty tiers—Run, Retrain, and Reimplement—based on the availability of code, data, and weights. In experiments, the best agent succeeded on only 41% of Run‑tier papers, 27% of Retrain‑tier, and 15% of Reimplement‑tier, often stopping early with unused budget and frequently making errors such as writing code without verifying against the paper’s numbers.
By Mithil Salunkhe, Haochen Ding, Samridhi Verma, Volodymyr Kindratenko
The paper introduces TRACER, a multi‑turn user simulator that models evolving user intent and aligns simulated behavior with real interaction trajectories. TRACER is trained first with supervised fine‑tuning on real dialogues and then with reinforcement learning that uses hierarchical outcome‑ and trajectory‑level rewards to address reward sparsity and credit assignment. In real customer‑service sessions, TRACER‑7B outperforms the best baseline by 11.4 conversion F1, achieves the lowest group‑level conversion‑rate error and semantic trajectory distance, and generalizes to out‑of‑distribution scenarios, while human Turing tests show its conversations appear natural. The authors also present the Dynamic Marketing Benchmark, which evaluates both persuasion effectiveness and response quality of large language models through simulated interactions, demonstrating that higher response quality does not always lead to higher conversion rates.
By Geng Chen, Ruotong Pan, Zhirui Yang, Qiqi He, Jiawei Chen, Zhang Yunfei, Chongyuan Chen, Minxuan Lv, Zheng Yang, Win-Bin Huang, Xiangyu Wu, Wenwu Ou
IndicBankBench is a 799‑case benchmark designed to evaluate the safety and reliability of language model assistants in Indian retail banking. It covers five operational domains, a capability/refusal domain, and twenty primary axes, assessing each case at four stages: safety, action and tool use, response adequacy, and advisory quality. The benchmark uses deterministic safety checks, a narrow resolver for ambiguous confirmation‑before‑write scenarios, and an LLM judge for semantic response adequacy, reporting strict pass rates that reveal a gap between strict reliability (43.7%–58.2%) and at‑least‑once success (60%–74%).
By Suvradip Paul, Chandra Bhushan, Harsh Sharma, Nitin Kukreja, Yatharth Dedhia, Keyur Doshi, Prashant Devadiga
The paper introduces an LLM-driven framework that automatically converts between finite state machines (FSM) and behavior trees (BT) for autonomous intelligent systems. It addresses key challenges such as preserving behavioral completeness and preventing model complexity explosion by designing a loop execution BT structure and employing depth compression strategies with LLM prompts. Experiments in various autonomous decision-making scenarios show that the framework achieves accurate, scalable, and maintainable bidirectional conversion, benefiting consumer-grade applications like service robots, game agents, and smart home devices.
By Zhang Qi, Yang Shuo, Zhu Zhengqiu, Zhou Peng, Jiao Peng
SkinAgent AI is a multimodal, safety‑grounded framework designed for non‑diagnostic skincare support. It routes visual concerns (Acne, Pores, Wrinkles), estimates skin type from photographs, and provides count‑informed acne severity, all while grounding recommendations in a database and enforcing deterministic safety, privacy, and evidence checks. The system achieved high accuracy in routing and skin‑type estimation, and demonstrated no safety or privacy violations in controlled tests, though tool‑selection errors and incomplete product grounding remain.
By Muhammad Muhtasim Shahriar, Abdullah Mohammad Sayem, Tze Hui Liew, M. F. Mridha, Md. Mahiuddin