The paper introduces Omni Demand Understanding (ODU), a benchmark designed to test whether multimodal models can infer a user's underlying demand from complex audio‑visual interactions. ODU requires models to detect the presence of a demand and infer intent using multimodal and conversational context, evaluated across single‑turn and multi‑turn scenarios. The authors built ODU‑Bench through a taxonomy‑guided approach, agentic video generation, and human‑recorded interactions, and found that even top models like Gemini 3.1 Pro recover only 44.7% of key information, with many models exhibiting high false‑trigger rates.
By Qi Chen, Yunfei Chu, Haolin He, Yifan Yang, Zihan Liu, Yuxuan Wang, Ziyang Ma, Ruiyang Xu, Meng Gao, Yinsong Yan, Ling Wang, Hui Wang, Wen Huang, Yiheng Chen, Guanrou Yang, Qiuqiang Kong, Jin Xu, Xie Chen
MIRAGE is a new inference-time framework that enhances large language models by using a Selector to choose effective conceptual perspectives and a Reasoner to solve tasks step-by-step, aggregating multiple perspectives when needed. It is inspired by human cognitive flexibility and is designed to improve performance on complex mathematical, scientific, and logical problems. Experiments on GSM8K, MATH500, MMLU-Pro, and Game-of-24 show that MIRAGE outperforms Chain-of-Thought and diverse prompting ensembles, boosting accuracy with minimal inference overhead.
By Arash Lagzian, Srinivas Anumasa, Dianbo Liu
The paper presents Sometin Beta Pass Notin (SBPN), a multilingual ASR framework for Nigerian languages that uses a two‑stage knowledge‑distillation approach. First, student‑teacher distillation from monolingual models is conditioned on language‑specific N‑gram language models; second, iterative self‑improvement with pseudo‑labelled data further refines accuracy. The method reduces relative WER by 29% over monolingual baselines and outperforms state‑of‑the‑art multilingual models on Common Voice and FLEURS benchmarks for Yoruba, Hausa, Igbo, Nigerian Pidgin, and Nigerian English.
By Sewade Ogun
The paper introduces Adaptive World Memory 3D Foundation Model (AWM-3DFM), a memory‑centric 3D foundation model that scales to large‑scale robotic localization, reconstruction, and Gaussian rendering. It employs transformer‑based gated updates, test‑time temporal‑spatial regulation, and local submap organization to maintain persistent memory, accuracy, and consistency across long image sequences. A Gaussian reconstruction head unifies pose estimation, dense point‑cloud reconstruction, and photorealistic rendering, achieving superior trajectory accuracy, reconstruction completeness, and rendering quality on public benchmarks and diverse robotic datasets.
By Tianchen Deng, Guole Shen, Yilin Shen, Wenhua Wu, Yilin Fang, Ziqi Ma, Tianjun Zhang, Shenghai Yuan, Wolfram Burgard, Hesheng Wang
The paper investigates how general vision‑language models (VLMs) develop specialized optical character recognition (OCR) capabilities. By applying a causal intervention protocol, the authors identify sparse, stable OCR‑head sets in several VLMs and show that these heads largely overlap with textual retrieval/copy heads found in general VLMs. The study concludes that full‑sequence OCR functions as a dense multimodal copy‑and‑paste mechanism, and that when a VLM is fine‑tuned for OCR, it largely preserves the same head identities while redistributing their functional and causal strengths.
By Yuanxiang Huangfu, Hanmeng Zhong, Linqing Chen, Jeffrey Tiong Jee Hui
GestureFAR is a flow‑autoregressive framework that generates natural co‑speech gestures from streaming speech while preserving causality and continuous motion expressiveness. It autoregresses over continuous motion latents using a transformer for audio‑motion context and a flow‑matching head to sample the next latent. A head‑only flow distillation strategy further reduces latency by collapsing multi‑step flow sampling into a single network evaluation, enabling real‑time token‑causal generation with improved quality‑latency trade‑off on the BEAT2 benchmark.
By Pinxin Liu, Haiyang Liu, Jiahao Luo, Junhua Huang, Chunhao Zou, Luchuan Song
The paper presents MegaEvent, an event‑based visual place recognition system that remains robust to viewpoint changes. By converting five large‑scale geo‑tagged datasets into synthetic event streams and fine‑tuning a vision transformer with a multi‑loss function, MegaEvent achieves an average Recall@1 of 82% on three event‑based localization datasets, outperforming existing methods by 20 recall points. The authors also introduce the Springfield‑Event‑VPR dataset, a 3.7 km walking route recorded in three camera orientations, where MegaEvent surpasses the strongest baseline by 9 recall points.
By Adam D. Hines, Michael Milford, Tobias Fischer
The paper introduces techniques for efficient on-device diffusion-based image generation on consumer GPUs. It presents an embedding translator that reduces weight and latency by mapping a small text encoder into a larger encoder space, a reproducible sweep recipe for balancing speed, quality, and memory, and an interactive editor that achieves sub‑second time‑to‑first‑image on recent GPUs. These contributions aim to broaden the reach of diffusion pipelines to a wide range of client devices.
By Frieder Ganz, Maximilian M\"uller
The paper introduces a method to certify selective prediction in machine learning systems by computing the availability of safety gates through exact-binomial inversion and dynamic programming. It demonstrates that a truth-informed planner can significantly improve mean coverage over naive approaches, and that reallocating error budgets further enhances coverage across diverse applications such as LLM tool‑calling, content moderation, lesion classification, and recommendation. The study highlights the importance of planning and finite‑sample estimation in ensuring reliable, granular deployment of selective predictors.
By Parivesh Priye, Yufeng Wang, Haibin Ling, Michael Chaykowsky
The paper introduces Recursive Block-Diagonal Coupling (RBDC), a training protocol that builds wide vision models by recursively coupling narrower, independently trained models in a parameter‑free block‑diagonal manner. RBDC allows flexible allocation of training budgets across all models and, when applied to vision transformers (DeiT) and convolutional networks (ResNet) on ImageNet, achieves a 30% reduction in FLOPs while maintaining similar test accuracies. Additionally, models trained with RBDC outperform those from existing growth methods at the same training FLOPs and serve as stronger backbones for downstream tasks such as object detection and instance segmentation.
By Maxim Henry, Adrien Deli\`ege, S\'ebastien Pi\'erard, Marc Van Droogenbroeck
arXiv:2609.20824v1 Announce Type: new
Abstract: We explore whether entropy-based confidence signals can be leveraged to improve the accuracy of Small Language Models (SLMs) with fewer than 3 billion...
By Prashant Mudgal
arXiv:2609.20829v1 Announce Type: new
Abstract: Grant reviewers must apply detailed criteria to application forms, budgets, and supporting documents while producing assessments that colleagues can in...
By Erik Varapaev, Andrei Chetvergov, Stepan Ukolov, Timofei Sivoraksha, Alexander Evseev, Sergey Bolovtsov
arXiv:2609.20835v1 Announce Type: new
Abstract: Background: The Voynich Manuscript is a fifteenth-century codex written in an unknown script whose content remains undeciphered. Previous studies sugge...
By Nicolas Turenne
arXiv:2609.21012v1 Announce Type: cross
Abstract: Artistic style classification is usually studied on complete artworks, where models can exploit global composition, spatial organisation, and iconogr...
By Sara Miketek, Biagio Barchielli, Nadeem Iqbal Kajla, Sinem Aslan
The paper presents an iterative framework that uses large language models (LLMs) to automatically extract interpretable, schema‑bound categorical features from unstructured text for use in tabular prediction models. A generator LLM proposes semantic definitions, an extractor LLM materializes the features, and a downstream tabular model evaluates their predictive performance, with error‑driven natural‑language feedback guiding the search. Across three public datasets, the error‑driven loop speeds up feature discovery up to three times and the resulting features outperform any subset when combined with TF‑IDF and dense embeddings, while also providing instance‑level interpretability through SHAP importance rankings and a semantic audit trail.
By Merwan Barlier, Blaz Skrlj
DiaVLo is a diagnostic framework for vision‑language models (VLMs) that uses human curation and VLM generation to create specifications of desired and observed behaviours, revealing potential misalignments. It also offers causal estimates to pinpoint the most influential concepts driving VLM behaviour. Experiments on several open‑source VLMs under classification and generation tasks show that DiaVLo’s behaviour labels correlate with model performance and illuminate how VLMs perceive, organise, and prioritise concepts.
By Lorenzo Corti, Jie Yang
arXiv:2609.21164v1 Announce Type: new
Abstract: Integrating diverse data modalities --- such as clinical notes, laboratory results, and medical imaging --- is essential for advancing clinical decisio...
By Inyoung Choi, Sukwon Yun, Jiayi Xin, Jie Peng, Tianlong Chen, Qi Long
arXiv:2511.13254v2 Announce Type: replace
Abstract: Large Language Models (LLMs) have displayed remarkable capabilities across diverse domains, but their training remains resource- and time-intensive...
By Shalini Maiti, Amar Budhiraja, Bhavul Gauri, Gaurav Chaurasia, Anton Protopopov, Alexis Audran-Reiss, Michael Slater, Despoina Magka, Tatiana Shavrina, Roberta Raileanu, Yoram Bachrach
arXiv:2511.14301v4 Announce Type: replace-cross
Abstract: Transformer-based models are highly susceptible to backdoor attacks via supervised fine-tuning (SFT). To red-team existing data-poisoning def...
By Eric Xue, Ruiyi Zhang, Pengtao Xie
arXiv:2603.22161v3 Announce Type: replace
Abstract: Metacognition -- assessing the quality of one's own cognitive performance -- guides adaptive behavior across species. Substantial research demonstr...
By Dharshan Kumaran, Nathaniel Daw, Simon Osindero, Petar Veli\v{c}kovi\'c, Viorica Patraucean