The paper introduces CPW-Drive, a retrieval-augmented generation framework that embeds Chinese philosophical values into autonomous driving decision-making. It extracts keywords from Confucian texts, validates them into driving-relevant principles, and retrieves scenario-specific cases using Physics-aware Spatial Similarity Retrieval. On Highway-env, CPW-Drive outperforms baselines, achieving higher success rates, more collision-free steps, and lower lane-change frequency.
By Xiaojun Bi, Xiaoyuan Ma, Yiwen Sun, Tianren Huang, Chaoran Liu, Bokai Huang, Hao Yang, Baichuan Mo
The paper surveys open, non‑proprietary large language models (LLMs) and AI foundation models (AIFMs) for clinical use, presenting a taxonomy of current state‑of‑the‑art models. It empirically tests open‑weight LLMs on a personalized‑prescription task, finding that they match or surpass a proprietary baseline in overall suitability accuracy, especially when combined with Retrieval‑Augmented Generation (RAG). A subjective evaluation by blinded raters shows mixed effects of RAG on perceived suitability across multiple dimensions, and the authors discuss ethical risks and the need for responsible deployment.
By Mahdi Alkaeed, Sofiat Abioye, Adnan Qayyum, Yosra Magdi Mekki, Ilhem Berrou, Mohamed Abdallah, Ala Al-Fuqaha, Muhammad Bilal, Junaid Qadir
SciRerankBench is a benchmark designed to evaluate rerankers in retrieval‑augmented large language models (RAG‑LLMs) for scientific literature question answering. It covers five scientific subjects and introduces three types of question‑context‑answer pairs—Noisy Contexts, Semantically Similar but Logically Irrelevant Contexts, and Counterfactual Contexts—to test noise resilience, relevance disambiguation, and factual consistency. The study evaluates 13 popular rerankers across five LLM families, offering detailed insights into their strengths and limitations.
By Haotian Chen, Qingqing Long, Meng Xiao, Xiao Luo, Wei Ju, Chengrui Wang, Yuanchun Zhou, Xuezhi Wang, Hengshu Zhu
The paper introduces PerFine, a training‑free critique‑refine framework that improves large language model personalization. In each iteration, a generator drafts text conditioned on a retrieved user profile, while a critic—also conditioned on the same profile—provides structured feedback on tone, vocabulary, sentence structure, and topicality. The generator revises the draft, and a knockout strategy selects the best version across iterations; additional inference‑time techniques such as Best‑of‑N and Topic Extraction further balance quality and efficiency. Experiments on Yelp, Goodreads, and Amazon datasets show PerFine consistently outperforms existing retrieval‑augmented methods like PGraphRAG, achieving G‑Eval gains of +8.5‑12% and steady improvements over 3‑5 refinement iterations.
By Durga Prasad Maram, Dhruvin Gandhi, Zonghai Yao, Gayathri Akkinapalli, Franck Dernoncourt, Yu Wang, Ryan A. Rossi, Nesreen K. Ahmed
The paper introduces AquaOV255, a large-scale underwater segmentation dataset with 255 categories and over 20,000 images, and establishes the UOVSBench benchmark by combining it with five other datasets. It also presents Earth2Ocean, a training‑free open‑vocabulary segmentation framework that adapts terrestrial vision‑language models to underwater scenes using a Geometric‑guided Visual Mask Generator and a Category‑visual Semantic Alignment module. Experiments on UOVSBench show that Earth2Ocean significantly improves performance while keeping inference efficient.
By Bingyu Li, Tao Huo, Da Zhang, Zhiyuan Zhao, Junyu Gao, Xuelong Li
UnSAMv2 is a self‑supervised extension of the Segment Anything Model that can segment objects at any granularity without human annotations. It discovers mask‑granularity pairs and introduces a granularity control embedding for continuous scale adjustment, requiring only 6K unlabeled images and 0.02% extra parameters. The model outperforms SAM/SAM‑2 across 11+ benchmarks, improving metrics such as 1‑IoU from 58.0 to 73.1 and achieving state‑of‑the‑art performance on language‑guided segmentation.
By Junwei Yu, Trevor Darrell, XuDong Wang
The paper introduces a neurosymbolic verification framework that audits the internal consistency of vision-language models (VLMs) when generating radiology reports. By autoformalizing free‑text findings into structured propositional evidence and using an SMT solver (Z3) alongside a clinical knowledge base, the system determines whether each diagnostic claim is entailed, hallucinated, or omitted. Evaluation on seven VLMs across five chest X‑ray benchmarks reveals distinct reasoning failure modes—such as conservative observation and stochastic hallucination—that traditional metrics miss, and shows that enforcing solver‑backed entailment can eliminate unsupported hallucinations and improve diagnostic soundness and precision.
By Vikash Singh, Debargha Ganguly, Haotian Yu, Chengwei Zhou, Prerna Singh, Brandon Lee, Vipin Chaudhary, Gourav Datta
The paper introduces a clustering method for point‑cloud segmentation that uses supervised contrastive metric learning (CML) to embed points from the same particle shower close together while separating unrelated points. After learning this latent space, clusters are reconstructed with a density‑based readout, decoupling representation learning from cluster formation. Compared to object condensation, CML yields a more stable, separable embedding, improving local neighbourhood consistency, shower separation, and generalization to unseen multiplicities and energies, which translates into higher reconstruction efficiency, purity, and energy resolution in highly granular calorimeter data.
By Max Marriott-Clarke, Lazar Novakovic, Elizabeth Ratzer, Robert J. Bainbridge, Loukas Gouskos, Benedikt Maier
AromaGen is a 12‑channel wearable system that translates free‑form natural‑language descriptions into olfactory experiences by selecting from 12 base odorants that span a semantically derived olfactory space. The system supports iterative refinement via natural‑language feedback. In a study with 60 participants and 50 benchmark smells, users could identify AromaGen‑generated scents above chance, and AI‑generated compositions performed comparably to human experts, with feedback improving perceived similarity.
By Awu Chen, Silang Wang, Yunge Wen, Jianing Yu, Zinab Eisa, Ana Julia Santos Lopes, Jas Brooks, Hiroshi Ishii, Paul Pu Liang
The paper studies cross‑stage context passing in Graph Visual Question Answering for autonomous driving, focusing on the Perception, Prediction, and Planning stages. Two complementary approaches are evaluated on DriveLM‑nuScenes: an explicit prompt‑based conditioning strategy using a domain‑adapted 4B VLM that reduces NLI contradiction by up to 42.6%, and an implicit gated context projector that, with only ~0.5% of parameters updated, cuts planning‑stage NLI contradiction by 34% and boosts cross‑stage entailment by 50%. The explicit method offers a strong zero‑training baseline for surface consistency, while the implicit method delivers significant semantic gains, highlighting the potential of domain adaptation for further improvement.
By Gautam Kumar Jain, Carsten Markgraf, Julian St\"ahler
The paper introduces point‑in‑time language models that are trained only on text available up to each calendar date, thereby eliminating lookahead bias that plagues standard large language models. By scaling decoder‑only transformers to 4 billion parameters and training on 1 trillion chronologically filtered tokens from FineWeb, the authors produce monthly checkpoints from 2013 to 2024 that achieve performance close to unconstrained models of similar size on common‑sense reasoning and language understanding tasks. Instruction fine‑tuning with LoRA further enhances downstream usability, and the authors release the full pipeline—including dataset construction, training infrastructure, and evaluation code—for reproducible research.
By Bryan Kelly, Semyon Malamud, Johannes Schwab, Teng Andrea Xu
The paper introduces AVCE, a method for verifiable concept erasure in diffusion models that audits latent representations to identify vulnerable directions and then edits cross‑attention and self‑attention projections in closed form. By fine‑tuning with pathway‑level auditing losses and orthogonal gradient projection, AVCE reduces attack success rates by 5.07× and improves auditing scores by 3.84× compared to the best baseline while maintaining generation quality.
By Kaiyuan Deng, Yuchen Li, Gen Li, Yang Xiao, Geng Yuan, Xiaoyong Yuan, Bo Hui, Xiaolong Ma
arXiv:2610. 19080v1 Announce Type: new Abstract: Reinforcement learning (RL) has substantially improved the reasoning of autoregressive and discrete-diffusion language models.
By Xu Han, Jiajing Hu, Li-Ping Liu
The paper challenges the common practice of selecting latent world models based on one‑step prediction loss, arguing that this metric poorly predicts planning performance. Using a frozen‑decoder protocol, the authors decompose one‑step error into encoder‑inherent and predictor‑added components and evaluate goal‑conditioned planning across three continuous‑control environments. Their experiments show that improvements in one‑step fidelity do not correlate with planning success, with correlation coefficients near zero and inconsistent exchange rates across tasks.
By Joshua Cheung, Zhang He
The paper introduces MetaModelSelect, a lightweight post‑hoc confidence metamodel that improves selective next‑location prediction for mobile networks. It uses only the outputs of a frozen recurrent neural network—specifically a learned embedding of the predicted location, the top four softmax probabilities, and Softmax Concentration—to determine whether the top‑1 prediction is correct, without retraining the backbone. Experiments on Changchun cellular mobility trajectories show that MetaModelSelect reduces risk–coverage metrics (AURC, E‑AURC, AUGRC) by up to 4.2% compared to maximum softmax probability and achieves the lowest mean risk across all partial coverages.
By Calvin Jary, Nafiseh Kahani
The paper demonstrates that pre‑trained language models can perform record linkage and demographic inference from names without task‑specific training. EnsembleLink, an algorithm that combines pre‑trained embeddings with string‑based scorers, achieves performance comparable to or better than prior methods across diverse scripts and formats. Large language models reach up to 83.8% accuracy on U.S. voter files for ethnicity inference, surpassing name‑supplemented BISG and enabling inference for non‑U.S. ethnic categories while reducing bias in geographic racial gap estimates.
By Noah Dasanaike
GraphRAG-LTM is a Layered Threat Modeling framework designed to evaluate security vulnerabilities in Graph Retrieval-Augmented Generation (GraphRAG). It introduces three nested attacker access levels—BB Query, WB Query, and Graph-aware WB—that manipulate query ranking, retriever gradients, and graph evidence to degrade answer quality. Experiments across datasets, retrievers, and LLM backbones show that rank feedback alone lowers answer quality, gradient access amplifies query attacks, and deleting bridge triplets further disrupts multi‑hop evidence propagation.
By Yining Tang, Junyu Zhang, Haomiao Qiu, Yongchao Liu, Jiajun Zheng, Zhao Wang, Ziyue Qiao, Chao Wu
EGCForest is a multi‑view hierarchical memory framework designed for enterprise group chats. It organizes the immutable message log into three complementary forests—Channel, Actor, and Artifact—each capturing temporal workflows, speaker‑conditioned context, and deliverable lifecycles, respectively. By using a Placement Map and sparse structural bridges, EGCForest jointly leverages message‑level relevance, forest summaries, and cross‑view links to retrieve and assemble distributed evidence, outperforming RAG and memory‑system baselines by up to 20.85 points on three benchmarks.
By Lingxi Cui, Jinhao Ruan, Wenqing Wei, Guo Yi, Li Rao, Ke Chen, Lidan Shou
arXiv:2610.20365v1 Announce Type: new
Abstract: AI agent communities sustain lexical persistence, popular terms spread, recur, and achieve broad adoption, but whether they also develop the temporal s...
By Chih-Han Lin, Yu-Yun Chang, Po-Ya Angela Wang, Shu-Kai Hsieh
arXiv:2605.10659v3 Announce Type: replace
Abstract: Digital personas powered by Large Language Models (LLMs) are increasingly proposed as substitutes for human survey respondents, yet it remains uncl...
By Mumin Jia, Yilin Chen, Divya Sharma, Jairo Diaz-Rodriguez