SignTrace is a system that tackles the reverse‑lookup problem in Chinese sign language by allowing users to describe a sign in natural language and retrieve the corresponding entry from a dictionary of 6,699 signs. It combines large‑language‑model–based dictionary enrichment, action extraction, seven‑channel retrieval, and candidate reranking, achieving a 94.0% Hit@1 and a mean reciprocal rank of 0.9540 on a benchmark of 500 queries. The system has been deployed for user trials, receives positive informal feedback, and processes median queries in 13.37 seconds.
By Zengji Tu, Xingye Zhu, Ningjing Wang, Tingyi Huang, Yangjunfeng Zhu, Dai Wan
ReG-SAM is a SAM-based framework designed for 2D vessel segmentation in medical images. It introduces reference graph prompt embeddings (GPEs) and vascular prototype embeddings (VPEs) to capture global spatial and fine-grained modality-specific vessel features, respectively. By building a modality-wise vascular database and learning these embeddings from reference masks, ReG-SAM consistently outperforms existing baselines across 19 datasets, especially on thin vessels.
By Donghang Lyu, Zichen Zhang, Oleh Dzyubachyk, Marius Staring
BAT-CLIP is a trimodal alignment framework that jointly aligns intracranial EEG (iEEG) neural embeddings to both pretrained audio and text anchors within a shared, frozen audio‑text manifold. Unlike existing CLIP‑style brain‑speech models that anchor neural activity to a single modality, BAT‑CLIP leverages both audio and text to preserve temporal structure and linguistic separability. On the naturalistic Podcast benchmark, BAT‑CLIP produces more robust representations than bimodal CLIP baselines and demonstrates the value of self‑supervised foundation models for CLIP training.
By Suhyun Kim, Jinmo Han, Danny Dongyeop Han, Ahhyun Lucy Lee, Jewoon Lee, Yonghyeon Gwon, Zach Paris, Chun Kee Chung, Saewoong Bahk, Nam Soo Kim, Seong Jae Hwang, Jiook Cha
The paper proposes a new architecture for Vision‑Language‑Action (VLA) models that improves sample efficiency by training a predictive world model on the vision encoder’s embedding space. It argues that these embeddings are action‑relevant and can be used to predict future states, addressing the lack of an explicit world model in current VLAs. The trained model can also support short‑term planning by sampling actions that lead to desired goal images.
By Parsa Mastouri Kashani, Jan-Gerrit Habekost, Stefan Wermter
Intent2Tc is a closed‑loop, language‑model‑driven framework that translates high‑level business traffic‑shaping intents into executable Linux traffic‑control (tc) configurations. It uses an AQM‑based digital twin semantic model, automated metadata extraction, critique‑driven refinement, and Retrieval‑Augmented Generation to improve semantic consistency and configuration reliability. Evaluation on 100 RFC 9315‑compliant intents shows high semantic fidelity and deployment readiness, with Claude Sonnet‑4.6 achieving 0.98 semantic similarity and 0.045 normalized edit distance, while RAG reduces token consumption and latency for compact models.
By Andrea Masini, Sudipta Acharya, Paolo Bellavista, Luca Foschini, Burak Kantarci
The paper introduces Stepwise Marginal Information Gain (MIG), an intrinsic process reward that evaluates how each reasoning step of a large language model (LLM) or vision-language model (VLM) improves the likelihood of the reference answer. MIG rewards only new likelihood maxima, preventing duplicate credit, and is combined with outcome, format, and self‑distillation objectives to guide training. Experiments on eight benchmarks show that this method outperforms outcome‑only reinforcement learning and improves accuracy by up to 4.8 points over binary‑reward training, including a 12.6‑point gain on MathVerse and a 12.9‑point advantage on vision‑language transfer at 7B parameters.
By Xiangwei Wang, Wei Wang, Ken Chen, Nanduni Nimalsiri, Sachith Seneviratne, Saman Halgamuge
FlyAOC is a benchmark that tests AI agents on end‑to‑end ontology curation of Drosophila scientific literature. Given a gene symbol, a brief description, a large paper corpus, and ontology resources, agents must search for evidence and produce structured annotations such as function terms, expression patterns, and historical synonyms. The benchmark contains 7,397 expert‑curated annotations across 100 genes and evaluates different agent harnesses, revealing system‑level failure modes that single‑task evaluations miss.
By Xingjian Zhang, Sophia Moylan, Ziyang Xiong, Qiaozhu Mei, Yichen Luo, Jiaqi W. Ma
The paper introduces an agentic AI-driven immersive simulation for High Dose Rate vaginal cylinder brachytherapy, combining Virtual Reality, mobile computing, and a knowledge-aware assistant powered by Retrieval-Augmented Generation. The system offers a high‑fidelity, risk‑free training environment that provides natural language interfaces and real‑time guidance during complex medical maneuvers. A prototype using Meta Quest 3 and a GPU‑accelerated backend demonstrates acceptable latency and high context precision, answer completeness, and relevance in the pedagogical support.
By Ronghua Xu, Kepha Barasa, Manoj Kumal, Xinyun Liu, Weihua Zhou, Xin Qian
RAPTOR (Ridge-Adaptive Logistic Probe) is a lightweight, L2‑regularized logistic probe designed to extract accurate, directionally stable concept vectors from frozen large language model (LLM) layer representations. By tuning the ridge penalty on validation data, RAPTOR produces concept vectors from normalized weights that match or surpass strong baselines in accuracy, maintain stability under ablation, and require significantly less training cost. The authors also provide a mechanistic analysis using the Convex Gaussian Min‑max Theorem to explain how penalty strength influences probe accuracy and stability in a high‑dimensional few‑shot setting, with predictions that align with empirical observations on real LLM embeddings.
By Ziqi Gao, Yaotian Zhu, Qingcheng Zeng, Xu Zhao, Ziqing Wang, Feng Ruan, Kaize Ding
The paper proposes a new architecture for masked language modeling that replaces the Transformer attention mechanism with a stack of low‑rank bottleneck autoencoders. Each autoencoder mixes information locally, across the full sequence, and across attention heads, compressing and reconstructing inputs without training‑dependent width. An iterative refinement process at masked positions pulls embeddings toward a weighted neighbor average and then projects them back onto the learned manifold, achieving comparable performance to BERT with roughly 1.9× fewer FLOPs and matching BERT on rare‑token performance through a frequency‑aware training schedule.
By Narges Mokhtari, Farzan Haddadi, Ebrahim Rezaii
The paper introduces the Within-Instance Prototypical Transformer (WIPT), a method that performs single-query test-time prototype adaptation by jointly transforming an unlabelled query with labelled support embeddings to form query-specific class means. Using a frozen ViT-S/16 encoder trained on miniImageNet and evaluated on CUB, EuroSAT, and ISIC, WIPT improves 1‑shot performance on CUB and EuroSAT but not on ISIC, while in 5‑shot settings it outperforms a support‑only Transformer on ISIC but remains weaker than ProtoNet overall. The study also explores multi‑query processing, memory and latency trade‑offs, and analyzes how WIPT alters uncertain versus confident predictions, concluding that the method offers a streaming‑compatible test‑time adaptation that can enhance low‑shot cross‑domain decisions without target‑time optimization.
By Rushab Rasik Karania, Tomas Maul
arXiv:2609.31368v1 Announce Type: new
Abstract: Tree-Adjoining Grammars (TAGs) have recently been introduced to Nonlinear System Identification (NLSI) as a means of encoding an entire model class as...
By Christopher A. Lindley, Nikolaos Dervilis, Keith Worden
The paper examines the use of pre‑trained deep‑learning embeddings as covariates in economic analyses of unstructured data. It identifies two main challenges: the mismatch between training data/tasks of pre‑trained models and the target economic task, and the identification problem of the embedding function. The authors propose sufficient conditions—particularly a transferability criterion—to guarantee convergence, introduce a bootstrap test to assess transferability without re‑estimating embeddings, and apply the framework to various double‑machine‑learning settings, including an empirical study of labor‑supply elasticity on Amazon Mechanical Turk using job‑description embeddings.
By Yuya Shimizu
Large language models (LLMs) are increasingly used for legal research, but their fixed training cutoffs and reliance on static knowledge clash with the evolving nature of statutory law. This study introduces a benchmark of 312 expert‑validated, time‑sensitive German statutory QA pairs that examine two temporal failure modes: post‑cutoff staleness and recency bias. Five LLMs were evaluated under four inference settings, and the results show that retrieval‑augmented approaches that enforce temporal validity significantly improve performance, while web search yields unstable gains and a pronounced recency bias.
By Max Prior, Andreas Schultz, Matthias Grabmair
AlphaEarth, a satellite foundation model, maps Earth’s surface into numerical embeddings that allow comparison across places and time. An audit of its representations for 1,000 urban areas in 162 countries shows that cities occupy a distinct but overlapping region on the hypersphere, with continent, climate, and degrees of urbanisation explaining a portion of the variation. The study finds that cities in developing countries exhibit less contrast in vegetation and texture, and that annual changes in a city’s representation are largely driven by model updates rather than pixel changes.
By Andrew Renninger
The paper introduces Conditional Predictive Sufficient Statistics (CPSS) as a formal way to capture useful visual representations that preserve latent factors shared with future data while discarding noise. It shows that predicting the next image patch embedding with a cosine loss approximates maximum likelihood under a von Mises-Fisher model, and that stop‑gradient alone does not enforce sufficiency. Experiments on MNIST and CIFAR‑10 with small causal Transformers demonstrate that CPSS readouts outperform intermediate blocks, while removing stop‑gradient collapses embedding rank even when the pretext loss appears perfect.
By Yuzhou Hong
The paper introduces Motion Style Slider, a framework that enables continuous, endpoint‑supervised control of style intensity in human motion diffusion. By constructing a style direction in a learned motion‑style embedding space and conditioning diffusion generation with a scalar intensity, the method achieves smooth, monotonic style scaling without needing intermediate‑intensity ground truth. The approach is compatible with pretrained diffusion backbones, supports heterogeneous style datasets, and is evaluated on controllability, interpolation/extrapolation, content preservation, and motion realism.
By Chen-Chieh Liao, Yichen Peng, Yiyi Cai, Y\^ui Ono, Hiroki Hanaoka, Erwin Wu, Hideki Koike, Shuichi Kurabayashi
DAPEVO is a learned visual odometry system that independently estimates image and event correspondences at shared patch locations and fuses their correlation evidence before motion refinement. It maintains image and event descriptors for each tracked patch, using a learned scalar gate to combine modality-specific correlation embeddings for each patch–frame edge, followed by a shared recurrent refinement and bundle‑adjustment update. The method supports event‑only observations and modality‑aware keyframe culling, achieving low trajectory error even when RGB frames are sparse or degraded, outperforming DPVO, RAMP‑VO, and event‑only DEVO on UZH‑FPV and TartanEvent datasets.
By Luca Gandolfi, Simone Nascivera, Roberto Pellerito, Rong Zou, Chiara Plizzari, Davide Scaramuzza
TRACKGRAPH is an online open‑vocabulary 3D mapping system that tracks 2D masks in the image stream before fusing them into a class‑agnostic 3D segment layer within a hierarchical scene graph. It uses FastSAM and CLIP for sparse keyframes, DINOv3 for dense mask propagation, and compact multi‑view CLIP embeddings for open‑vocabulary retrieval. The method outperforms state‑of‑the‑art mapping techniques on Replica, ScanNet++, and HM3D, achieving higher synonym frequency, faster processing, and lower GPU memory usage, and has been deployed on quadruped robots and drones at real‑time rates.
By Peder Borge Hellesylt, Albert Gassol Puigjaner, Kostas Alexis, Annette Stahl
SEA-CLIP-Tiny is a compact multilingual text‑vision embedding model designed for Southeast Asian languages, containing fewer than 50 million parameters. It adapts a CLIP‑KD framework with region‑specific data curation and multilingual teacher guidance. Across seven languages, it outperforms other student models, achieving R@1 = 12.9%, R@5 = 31.5%, and R@10 = 42.2%, and surpasses MobileCLIP2 by 12.1 points in R@10 while using 38.4% fewer parameters and lower CPU latency.
By Puja Ahmad Habibi, Faiz Assabil Firdaus, Ashvanth S, Ekapol Chuangsuwanich, Pume Tuchinda, Peerat Limkonchotiwat