Zero-Shot
-
Plausible but Unimplantable: A Trustworthiness Audit of Shape Completion Foundation Models for Cranial Defect Reconstruction
2026-10-21 16:59:30Marek Wodzinski, Kamil Kwarciak, Daria Hemmerling, Mateusz DaniolAbstract
A patient who has lost part of the skull vault needs an implant that fits the defect exactly, and such implants are still drawn by hand in CAD by specialists, which makes each case slow and expensive. The task can be considered as a shape completion problem, so pretrained completion models, and now the first shape completion foundation models, look like a way to remove that manual step. We audited three publicly released pretrained shape completion models, two of them foundation models, applied zero-shot to 239 cranial defects, some carved from public skull datasets and some real post-craniectomy cases. Each output was compared with simply returning the patient's own remaining bone, and tested for whether the predicted material could be placed without intersecting the bone that is still there. On the 210 carved defects none of the three improved on doing nothing, and on the 29 real cases only one did so beyond chance. Yet not one output, from any model in any configuration, was implantable: none managed both to stay clear of the bone the patient still has and to place more material than doing nothing, where a task-specific volumetric model, trained for this task and selected on these cases, was implantable on all but one. The output that most convincingly resembles a skull is no more placeable than the rest, and at these point densities implant thickness cannot be read off the emitted points at all, which is a property of the output representation rather than of any one model. On this evidence the shape completion foundation models we could obtain cannot be trusted and, used as released, are not usable in clinical practice. Substantial research towards trustworthy foundation models for shape completion is still needed.
Abstract (translated)
URL
https://arxiv.org/abs/2610.30035
PDF
-
DewHand: Direct Metric World-Space Hand Motion Reconstruction from Egocentric Videos
2026-10-21 16:08:38Naru Suzuki, Satoshi Ikehata, Takehiko Ohkawa, Yoichi Sato, Shuhei KuritaAbstract
Recovering metric world-space hand motion from egocentric video supports understanding human interactions and transferring them to embodied agents. Three challenges complicate this task: multi-stage pipelines propagate errors from independently estimated hand and camera motion; monocular observations leave physical scale ambiguous; and occlusion and out-of-view hands admit multiple plausible motion trajectories. We present DewHand, a unified model for direct joint reconstruction of world-space hand and camera motion. To avoid compounding errors from multi-stage estimation, DewHand jointly predicts hand and camera motion in a shared world coordinate system within a single-stage pipeline. To resolve metric-scale ambiguity, it combines scene-level geometric features from VGGT-$\Omega$ with metric-space supervision, while hand-specific features preserve fine-grained articulation. To handle occlusion and out-of-view hands, we formulate reconstruction as conditional motion generation with flow matching. Under the same architecture, this generative formulation outperforms direct regression in both accuracy and temporal smoothness with only two sampling steps. Experiments on HOT3D and ARCTIC demonstrate improved world-space accuracy and temporal consistency over state-of-the-art methods. DewHand reduces rigid-aligned world-space error relative to StableHand from 32.9 to 28.4 mm on HOT3D and from 76.2 to 36.2 mm on ARCTIC. It also recovers camera scale within 10% on two thirds of HOT3D clips, versus about a quarter for SLAM. Moreover, in zero-shot evaluations on HoloAssist, H2O, and TACO, captured with different devices, DewHand achieves the lowest rigid-aligned world-space error (WA-MPJPE) on each dataset.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29936
PDF
-
Asking a Multimodal LLM Whether Someone Fell: Zero-Shot Screening of Low-Resolution Thermal Video in a Laboratory and an Occupied Home
2026-10-21 15:53:17Marcos Junca (Senecta Inc.), Mauro Junca (Senecta Inc.)Abstract
Thermal cameras can watch over older people living alone without capturing faces, and multimodal large language models (LLMs) can judge a short video without task-specific training. We evaluate a production multimodal LLM, Gemini 3.8 Flash at temperature 0, as the decision stage of an event-triggered fall screener, used exactly as a deployed prototype uses it: one request per short thermal clip, with its sound track when there is one, and its predecessor Gemini 3.7 Flash on the same requests. On 438 staged falls and 563 non-fall windows that we located by hand in a public 32x24 thermal dataset, the deployed request called 69% of the held-out subjects' falls (67% over all subjects; bed falls excluded) and none of 499 non-fall windows, including people lying on the floor and getting up. Over 76 h of ordinary life in an occupied room, recorded at 160x120 with sound, it called none of 395 clips a fall (95% upper bound 1.2 false alarms per day) and caught 4 of the 9 staged falls the camera could see. One cautionary sentence in the prompt ("a person who goes out of view ... is not a fall") accounted for many of the misses: removing it raised sensitivity on the held-out subjects from 69% to 83% on 3.8 Flash and from 80% to 92% on Gemini 3.7 Flash, and in the home from 4 to 9 of the 9 visible falls, with no false call in ordinary living but at the price of calling deliberate lie-downs a fall. Sensitivity collapsed at 8x6 pixels (34%); identical requests disagreed on 4% of windows; and when the model called a fall, its explanation placed it within a second of the annotated landing 99% of the time. Two conventional detectors trained on the laboratory data caught nearly every held-out laboratory fall but raised 14.2 and 23.9 false alarms per day in the home. We release the frame-level fall annotations of the public dataset and every model answer on it.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29913
PDF
-
Benchmarking Large Language Models for Detecting Satirical Code-Mixed Sentences
2026-10-21 15:48:28R\u{a}zvan-Alexandru Sm\u{a}du, Ioana Buhnila, Daniela Tanase, Dumitru-Clementin Cercel, Florin Pop, Mihaela-Claudia CercelAbstract
Code-switching is a natural linguistic phenomenon, yet its impact on high-level reasoning tasks remains largely unexplored in under-resourced languages like Romanian. Natural language processing tasks, such as satire detection, rely heavily on nuanced cultural and syntactic cues that large language models struggle to capture. In this paper, we investigate four methods (i.e., random replacement, phrase translation, dependency parsing, and large language models) for generating synthetic code-mixed Romanian sentences with English, German, French, and Italian. We start with an existing dataset for satire detection, compiled from Romanian news articles and annotated at the sentence level by humans, and augment it with over 600k samples, namely CS-SeLeRoSa. We provide an in-depth analysis of the dataset generation process. Then, we evaluate several multilingual large language models across zero-shot, chain-of-thought, and fine-tuning regimes on both the synthetic corpus and a human-adjudicated gold benchmark, namely CS-SeLeRoSa-Gold. While older open models suffer substantial degradation (dropping to 37%-55% macro-F1), newer models like Gemma 4 31B achieve 68.1% zero-shot, rivaling frontier models like GPT-5 mini (69.5%). Furthermore, fine-tuning significantly reduces formatting errors and improves the results, increasing Gemma 4 31B to 77.5% on CS-SeLeRoSa and 72.6% on the gold standard, outperforming frontier zero-shot baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29907
PDF
-
Expandable Modality Experts for Medical Vision-Language Learning
2026-10-21 15:28:40DM BAPPY, Eunsu Kim, Hanjoo Lee, Sung Hak Lee, Sangjeong AhnAbstract
Learning across medical imaging modalities requires making use of images without paired text and accommodating new domains while retaining existing representations. We propose a medical vision-language technique built around an expandable bank of modality experts. Its Multiway Transformer combines shared visual computation with deterministically routed feed-forward experts and a separate text pathway. A modality-aware visual tokenizer supplies targets for masked pretraining on 19.4 million unpaired image rows across seven modalities; contrastive alignment then uses 3.23 million image-text pairs. Additional fundus and optical coherence tomography experts learn from paired data while the original image and text embedding paths remain frozen. With a ViT-Large backbone, the proposed technique achieves the best or tied-best result in 24 of 25 benchmark settings across nine modalities: 10 of 11 zero-shot classification benchmarks, all 10 linear probes, and all four retrieval benchmarks. Mean balanced accuracy is 0.674 for zero-shot classification and 0.856 for linear probing, and mean bidirectional retrieval recall is 20.70%. A separate three-seed sequential experiment with matched adaptation data yields fundus and OCT retrieval gains of 14.95 and 9.31 percentage points, with no measured loss on preceding fundus or pathology tasks. The preservation argument requires unchanged existing computation paths and inference conditions, and feature-identity checks verify retention on evaluated inputs. The proposed technique provides a modular approach to learning and expanding medical vision-language representations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29881
PDF
-
RangeNav: Task-Aligned LiDAR Range-Image Pretraining for Robot Navigation
2026-10-21 15:06:08Samuel Foo Enze, Manthan Patel, Fan Yang, Linus Kramer, Pascal Roth, Marco Hutter, Cesar CadenaAbstract
Autonomous mobile robots operating in dense crowds and cluttered sites require $360^\circ$ perception to react to surrounding hazards. While panoramic LiDAR offers full-surround coverage, learning representations within reinforcement learning (RL) is sample-inefficient under sparse rewards, and existing 3D pretrained point-cloud encoders are too memory-heavy for massively parallel RL simulation. We present RangeNav, a compact (183k parameters) LiDAR range-image encoder pretrained entirely on synthetic data. RangeNav uses anisotropic convolutions and circular padding to handle the extreme aspect ratio and azimuthal seam of range images. We pretrain the network using a navigation-aligned objective combining range reconstruction, semantic segmentation, and bird's-eye-view (BEV) prediction, then freeze it for policy learning. In simulation, adding semantic and BEV supervision increases success rates over a reconstruction-only baseline by an average of 32.03 and 23.73 percentage points (pp) in procedurally generated training and out-of-distribution realistic test environments, respectively. Zero-shot real-world deployments on a Unitree B2-W quadruped demonstrate robust navigation through dense crowds, low-light settings, and construction zones where limited-field-of-view depth policies struggle. Code and models will be open-sourced.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29845
PDF
-
Exploring Post-Training Alignment of Small Language Models for Biomedical Data-to-Text Generation: A Case Study of Medication Leaflet
2026-10-21 15:03:37Xi Yang, Guodong Liu, Chuqin Li, Fan Wu, Ergin Soysal, Min Jiang, Xing He, Jiang Bian, Yi Guo, Shams Zaman, Thomas Fuchs, Yonghui WuAbstract
Translating structured biomedical information into accurate, patient-friendly narratives remains a challenging biomedical data-to-text (D2T) task. While small language models (SLMs) are attractive for healthcare applications because of their lower computational cost, easier deployment, and improved data governance, the impact of post-training alignment on biomedical D2T generation has not been systematically studied. In this work, we compare four alignment methods: supervised fine-tuning (SFT), direct preference optimization (DPO), odds ratio preference optimization (ORPO), and group relative policy optimization (GRPO), using Qwen-2.5 models for medication leaflet generation. We further introduce FDALeaflets, a dataset derived from OpenFDA drug labels, to evaluate cross-regulatory generalization in a zero-shot setting. Selected aligned SLMs outperform GPT-5 on several reference-based metrics, whereas GPT-5 achieves better hallucination and adequacy scores on FDALeaflets under LLM-as-judge evaluation. Among RL-free alignment methods, ORPO achieves the best in-domain semantic performance, reaching a semantic textual similarity (STS) score of 0.9752. GRPO achieves the highest FDALeaflets STS (0.9407), exceeding GPT-5 (0.9295). These findings show that post-training alignment is a key factor in improving both semantic fidelity and generalization for biomedical D2T generation, while clinical safety and patient readability require human verification.
Abstract (translated)
URL
https://arxiv.org/abs/2607.13430
PDF
-
Robot Generalization Beyond Volume: The Diversity Path via Zero-Shot Capabilities
Abstract
General-purpose robots must handle tasks, objects and environments they were never trained on, yet zero-shot generalization remains one of the least solved problems in physical AI. In digital AI, zero-shot capability grew with the volume and, above all, the diversity of training data, much of it sourced from the crowd. Robotics instead relies on paid collection by a few well-funded teams, which yields volume without diversity. We formulate zero-shot generalization in physical AI as coverage of the deployment distribution, and show that more samples from the same collectors shrink the unseen region only slowly, while each new contributor can extend it. Building on this and on zero-shot learning, we propose a shared latent space for robot actions that combines multi-modal alignment, generative augmentation, and noisy-label learning. As a scalable source of diverse data, we propose a community of developers building applications on one standard, approachable robot, Origami. We close with a testable hypothesis and an evaluation protocol relating real-robot zero-shot success to the diversity of contributed data.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29829
PDF
-
GuidedSAM-Plume: An Expert-Guided Segmentation Framework for Volcanic Plumes
2026-10-21 14:48:18Taddeo D'Adamo (LIRIS, imagine), Simon Thivet (UNIGE), Catherine Pothier (LIRIS, imagine), Riccardo Simionato (UNIGE), Allan Fries (UNIGE), Jonathan Lemus (UNIGE), Costanza Bonadonna (UNIGE), Laure Tougne Rodet (LIRIS, imagine), Bertrand Kerautret (LIRIS, imagine)Abstract
Quantitative analysis of environmental phenomena increasingly relies on image-based measurements. In volcanology, the geometric characterization of volcanic plumes and clouds from RGB images remains hindered by the scarcity of dedicated segmentation solutions and partially handcrafted annotations remain widely prevalent. We present GuidedSAM-Plume, an open-source expert-guided framework tailored for the interactive segmentation of volcanic plumes and clouds. It leverages the zero-shot, spatial prompt-based capabilities of SAM2. The framework was thoroughly validated on a challenging dataset through dedicated segmentation metrics and field-relevant volcanological descriptors. From minimal user inputs, it is able to significantly increase performance compared to fully automatic dedicated solutions while preserving the reliability of derived volcanological parameters. The absence of retraining requirements lowers adoption barriers within the volcanological community, and the framework's demonstrated suitability for complex, diffuse plume-shaped phenomena extends its applicability to broader environmental science domains. The re-annotated dataset, produced under the guidance of expert volcanologists within the proposed framework, ultimately yields a more standardized release. The framework and accompanying dataset are made available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29825
PDF
-
Compositionality with Primitives: A Unified View from Euclidean to Hyperbolic Vision-Language Models
2026-10-21 14:34:51Puru Vaish, Meelad Dashti, Christoph Brune, Pascal Mettes, Tatiana Tommasi, Nicola StrisciuglioAbstract
Compositional zero-shot learning (CZSL) aims to recognize novel combinations of previously observed objects and attributes. Prior work showed that large-scale vision-language models encode decomposable semantic structures that can be recomposed to enable generalization. The Geodesically Decomposable Embeddings (GDE) framework formalizes this by identifying directions in the tangent space at the Frechet mean of the embedding distribution, which encode primitive visual concepts. Unseen attribute-object compositions can be synthesized through vector addition of these primitives. We revisit the assumption that compositional generalization requires explicit attribute-object pair re-composition. By means of new compositional scoring functions and extensive evaluations, we show that directly using the decomposed primitives suffices for recognizing unseen compositions. In that, we gain insights on how the geometry of the embedding manifold (Euclidean, spherical, or hyperbolic) and dataset structure affect compositional reasoning. Across models (CLIP, DINOv2, MERU, HyCoCLIP), we show that compositional structure consistently emerges as primitive representations, enabling inference on CZSL benchmarks (MIT-States, VAW-CZSL, UT-Zappos50K, Clothing16K) and group robustness on Waterbirds and CelebA. Code: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29811
PDF
-
Watch Your Step: Anticipated Perception for Humanoid Locomotion
2026-10-21 11:52:29Matthias Heyrman, Chenhao Li, Ioannis Dadiotis, Marco HutterAbstract
Perceptive locomotion policies typically observe a dense robot-centric elevation map, although only the terrain beneath and around the next footsteps informs the control decision. Learned encoders compress the whole visual input, leaving the policy to work out which inputs matter while learning the baseline locomotion task. Learning both at once slows training and, without computationally expensive attention mechanisms, makes generalization to new terrain harder. We instead remove redundant inputs from the elevation map before the policy sees it. A lightweight foothold prediction model (FPM) predicts future footholds from proprioception and the velocity command alone, and we sample the elevation map only in small patches around these predicted footholds. We train the prediction model alongside the locomotion policy, periodically retraining it on new policy rollouts as the robot's gait matures. This allows the perception to anticipate where the policy will step, while the policy learns to leverage terrain information around those steps. With the proposed lightweight preprocessing, the policy reaches a given terrain difficulty in roughly a third of the training iterations required with the complete map. It outperforms policies that observe the complete map where footholds are sparse, including in narrow walled corridors, and on unseen terrain, and it matches an attention-based encoder trained at several times the cost. The policy transfers zero-shot to a Unitree G1 humanoid traversing various obstacles, stairs, gaps, and step-downs beyond the training distribution in both indoor and outdoor environments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29612
PDF
-
SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model
2026-10-21 10:06:03Kai Tang, Peidong Jia, Zhong Chu, Jiajun Cao, Jixian Wu, Bohua Zhang, Rui Ma, Fangyuan Zhao, Sixiang Chen, Yichen Guo, Xiaowei Chi, Chun-Kai Fan, Kevin Zhang, Jinchang Xu, Fubing Yang, Weishi Mi, Xiaozhu Ju, Jian Tang, Shanghang ZhangAbstract
Safe control is a prerequisite for real-world embodied intelligence, for which safe reinforcement learning has emerged as a promising paradigm. However, existing safe reinforcement learning methods either require costly real-world exploration or depend on hand-crafted safety functions. Neither scales to vision-language-action models deployed in open-world physical environments. We propose SafeDojo, a model-based safe reinforcement learning framework that improves vision-language-action policies through world-model imagination. SafeDojo performs online reinforcement learning on top of an interactive video world model. A ResNet success classifier scores predicted future frames, while a lightweight safety head predicts per-step contact probabilities from the current latent context and proposed action chunk, jointly assessing task execution and trajectory safety. These decoupled signals are balanced through Lagrangian-constrained GRPO. On SafeLIBERO Level I, SafeDojo improves average safe-success rate by 8.25 percentage points over the strongest baseline; on the zero-shot Level II setting, it is competitive with the strongest model-free baseline. Real-world Franka deployment further shows the best average task and safe-success rates across five tasks. These results support world-model-based safe reinforcement learning as a promising path toward safer embodied intelligence.
Abstract (translated)
URL
https://arxiv.org/abs/2606.20698
PDF
-
Balancing Foundation Models and Trait-Specific Learning for Forehead-Crease Recognition
2026-10-21 09:50:08Geetanjali Sharma, Aryan Jain, Dev Nagaich, Aditya Nigam, Raghavendra RamachandraAbstract
Biometric recognition often degrades under partial facial vis- ibility, where conventional facial cues are occluded. The forehead region remains consistently visible and contains distinctive crease patterns that can serve as a complementary biometric trait. We present a unified eval- uation of forehead-crease recognition across explainable zero-shot rea- soning, domain-adaptive learning, and trait-specific modeling. FIRE en- ables interpretable zero-shot verification using multimodal large language models, while pretrained face-recognition models are adapted to the fore- head domain through margin-based learning. Under open-set evaluation, the best zero-shot model GPT-4o+FIRE achieves 18.22% EER, while Edge-Forehead achieves 8.30% EER and 54.01% TMR@0.1% FMR. The results show that although MLLMs offer interpretable zero-shot verifi- cation, trait-specific learning remains more effective for robust forehead- crease biometric recognition.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29495
PDF
-
Distance Field Driven Reinforcement Learning for Reactive and Robust Collision Avoidance
2026-10-21 09:10:03Taiga Ikeshima, Sheila Sutjipto, Lan Wu, Francisco J. Naranjo-Campos, Taiki Ishigaki, Taisuke Kobayashi, Teresa A. Vidal-Calleja, Eiichi YoshidaAbstract
Robust and reactive collision avoidance remains a central challenge for deploying Reinforcement Learning (RL) policies on real robotic manipulators, particularly when transferring behaviours learned in simulation to the physical world. This paper presents an RL framework that integrates the Euclidean Distance Field (EDF) directly into the observation space, providing the agent with continuous geometric cues that support stable and responsive avoidance behaviours. By leveraging the rich spatial information encoded in the EDF, the method enables a streamlined reward formulation that achieves effective obstacle avoidance both with and without Artificial Potential Field guidance. The proposed approach is validated on a 7-DoF redundant manipulator, demonstrating zero-shot transfer from simulation to real hardware. Despite being trained exclusively with randomised static objects, the deployed policy generalizes to previously unseen real environments and exhibits robust online avoidance of dynamic obstacles. These results highlight the potential of EDF-based representations to mitigate the sim-to-real gap and support reliable and real-time collision-aware behaviour in complex and changing environments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29452
PDF
-
Look Beyond the Question: Preserve-Focus-Fuse for Whole-Slide Image Question Answering
2026-10-21 08:55:25Xiangyu Li, Jincheng Li, Tianle Du, Yanheng Li, Haoxuan Che, Yuxin Sun, Long Bai, Liangliang Liu, Ran SuAbstract
A question about a whole-slide image rarely names every morphological finding needed to answer it. Question-guided patch selection can therefore overlook supporting morphology, while slide-level compression can dilute focal evidence. Inspired by how pathologists combine broad slide review, question-directed examination, and integration of their findings, we introduce BEYONDPATH, a Preserve-Focus-Fuse framework for whole-slide image question answering. Preserve learns a question-agnostic Morphology Bank through answer supervision across multiple questions about each training slide. Focus retrieves questionspecific evidence from all foreground patches, including regions outside the Bank. Fuse integrates the preserved morphology at the retrieved evidence positions through Morphology-on-Visual-Evidence Fusion, producing a fixed 96-token visual prefix. On WSI-Bench, BEYONDPATH achieves an Avg-9 of 0.769 and leads all eight reported report-generation metrics using the same checkpoint. It also achieves 0.639 zero-shot overall accuracy on SlideBench-BCNB. Controlled ablations show complementary benefits from morphology preservation and question-directed retrieval, and support cross-question supervision and fusion at the evidence positions. These results support looking beyond the question's explicit cues: preserving broader slide morphology while retaining the ability to seek evidence for each question.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29431
PDF
-
LLMSeg: Training-Free Text-Prompted Image Segmentation with B-Splines
2026-10-21 08:35:16Abdullah HamdiAbstract
Promptable segmentation models such as SAM 3 achieve remarkable open-vocabulary performance but require dedicated architectures, large-scale annotation engines, and task-specific training. We ask a different question: can a general-purpose multimodal large language model (MLLM) segment images directly, without an added segmentation head, mask decoder, or training? We present LLMSeg, a training-free pipeline that turns a vision-capable LLM into a text-prompted image segmenter. LLMSeg decomposes segmentation into three LLM-driven stages. First, detect localizes all instances matching a free-form text query and describes their coarse morphology. Next, segment traces each instance using closed periodic B-splines confined to its detected box. These splines define an outer boundary and optional hole loops. Finally, refine iteratively proposes focus boxes around residual errors and retraces confined splines. The process ends when the mask stabilizes or the pass budget is exhausted. The output is a binary mask with inspectable intermediate geometry. We evaluate LLMSeg across ten referring and reasoning segmentation splits (ReasonSeg and RefCOCO/+/g). We also evaluate open-vocabulary instance segmentation (LVIS, COCO, and SA-Co), semantic segmentation, and zero-shot detection (ODinW13 and RF-100VL). With an off-the-shelf Gemini-3.7-Flash backend, LLMSeg is competitive with and often surpasses the specialist SAM 3 model on identical items. It reaches 71.5 cIoU on ReasonSeg val without additional segmentation-specific training. Backend model updates can improve accuracy without retraining the pipeline. The code is available at this https URL .
Abstract (translated)
URL
https://arxiv.org/abs/2610.29409
PDF
-
Closed-Loop Dual-Reference Guidance for Accent Control in Cross-Lingual Voice Cloning
2026-10-21 07:46:22Yuanzhong Zheng, Wei Huang, Ming Ma, Kailun Jin, Youhai JiangAbstract
Zero-shot cross-lingual voice cloning often carries the reference speaker's accent into the target language. We propose closed-loop dual-reference guidance, which pairs the original reference with a reusable native anchor constructed by voice conversion (VC). The references initialize separate language-model (LM) states that guide a shared acoustic trajectory; each completed patch then updates both states, keeping their generated histories aligned with the emitted speech. Anchor construction runs once per speaker, and online synthesis uses a frozen TTS model without per-utterance VC. On 20 held-out French speakers, the fixed setting $\lambda^{\!*}=0.33$ reduces residual French LID mass by 73\% versus direct cloning, at an ECAPA similarity cost of only $0.042$; relative to anchor-only cloning, it recovers $0.155$. The method achieves the lowest mean WER ($0.009$) and highest mean GOP ($4.750$) among the held-out test arms. In blinded preference tests, native-English listeners favor it over direct cloning on pronunciation naturalness, and over both anchor-only cloning and a TTS$\to$VC cascade on speaker identity. Online RTF is approximately 26\% lower than the cascade's ($0.59$ vs.\ $0.80$), and the same setting reduces Spanish LID mass by 56\% without re-tuning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29351
PDF
-
Think-Capture: Active 3D Geometry Acquisition for Spatial Reasoning in Vision-Language Models
2026-10-21 05:42:29Junjie Wang, Zhihao Yuan, Yunhan Tang, Sheng Xu, Jiaqi Mao, Xiaoyu Ye, Yueru Luo, Xu Yan, Chun-Mei Feng, Zhen LiAbstract
Vision-Language Models (VLMs) excel at 2D recognition but often fail to maintain consistent 3D relations across sparse viewpoints, leading to spatial hallucinations under occlusion and perspective changes. Existing methods commonly fuse all frames with dense geometry, incurring substantial computation and context overhead while encouraging blind reliance on imperfect estimators. We present Think-Capture, a query-conditioned framework that first identifies task-critical objects and then acquires their geometry on demand. A 3D toolkit lifts zero-shot masks into a common coordinate frame, and a Symbolic 3D State Abstraction compresses object and camera states into structured text. Hierarchical Group Relative Policy Optimization (GRPO) trains the VLM on cases in which geometry either helps or misleads, teaching it when to use tool evidence and when to fall back on visual cues. Think-Capture-4B reaches 54.4% on MindCube-Tiny (+21.5 points over its backbone), 39.1% on the MMSI-Bench positional subset (+7.9), and 42.8% on ViewSpatial (+5.2). It also remains robust under coordinate and mask perturbations. The full stack fits one 24 GB GPU and serves as an asynchronous high-level reasoner on an Agibot G1. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29232
PDF
-
A Unified Evaluation Framework of Physical Adversarial Robustness in the Edge VLM Era
2026-10-21 04:38:02Eric Liang, Alan Luo, Kaiwen YuanAbstract
Recent advancements in Vision-Language Models (VLMs) enable end-to-end visual grounding via language prompts and generative decoding, demonstrating largely improved zero-shot and open-vocabulary detection capabilities. As a result, VLMs are rapidly being deployed at the edge in safety-critical real-world systems. However, the physical adversarial robustness of edge VLMs has not been systematically studied, and the fundamental differences in output with modern object detectors create methodological challenges for fair evaluation. To compare the two families directly, we evaluate every selected representative model on one outcome: whether an adversarial patch worn on a person evades detection of the model. We report this by introducing a unified metric, conditional attack success rate (cASR), counted only on images the model still localizes under a matched gray occluder, and partition every failure into omission (no box), substitution (a box on the patch), and displacement (a box on neither). We benchmark the physical adversarial vulnerability of compact grounding VLMs against a range of object detectors, and find that the VLMs can be as vulnerable as the detectors. We disclose that failure mode is largely associated with the output format of a model rather than its architecture family. Of the three, only omission is visible to a downstream system; displacement and substitution return confident, well-formed boxes, making them potentially more dangerous failures. Further, we find that, under distribution shift, VLMs that primarily failed by omission instead shift to failing more by displacement/substitution. Thus, a grounding VLM can inherit the detector's vulnerability while showing the possibility to adopt more dangerous failure modes. Our code and data are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29196
PDF
-
Where Does Timbre Hide? Localizing Speaker Information in Speech Signals
2026-10-21 03:35:42Yiquan Zhou, Yixuan Wang, Xiaozhe Qi, Xin Gao, Shihao LiAbstract
Timbre similarity is a key evaluation target for generative speech systems, including voice conversion, speaker-cloning text-to-speech, and zero-shot speech models. When the generated voice does not match the target speaker, the problem often reflects imperfect separation of speaker-related timbre from content, making it important to identify where timbre information resides and which representations still carry it. Using speaker identity as a measurable proxy, we probe frequency bands, phase/magnitude structure, WORLD source/filter decomposition, voiced/unvoiced regions, self-supervised learning (SSL) layers, EnCodec/HuBERT tokens, and a 45-listener test across Mandarin, English, and Japanese speech/singing data. Speaker information is distributed: 1--8 kHz magnitude and vocal-tract spectral-envelope structure dominate perception, above-8 kHz bands remain machine-discriminative, shallow SSL layers expose compact speaker information, and token leakage depends on tokenizer/layer choice. These findings indicate where generation systems should condition on or transform speaker information, and where content, codec, and token pipelines should audit residual speaker leakage.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29150
PDF
