Sparse
-
Maze Runner: Autonomous Maze Navigation with Line-Based Localization and Control Barrier Functions
2026-11-06 22:32:59Alvaro J. Gaona, Lucas G\'omez-Velayos, Peter Pasuy-QuevedoAbstract
Maze navigation requires localization from sparse, repetitive geometry, planning through narrow corridors, and control that stays safe when the estimate or the map is wrong. We present Maze Runner, an open autonomy stack in C++ and ROS 2 that addresses these needs end to end on a simulated Husarion ROSbot XL with a 2D LiDAR in Gazebo. Perception extracts wall lines from each scan with RANSAC and total least squares, with per-line uncertainty. The same line front end feeds two estimators: an Extended Kalman Filter (EKF) that localizes against a line map built from the maze mesh, and an EKF SLAM variant that builds the line map online. Planning runs online on an inflated occupancy grid with A* plus line-of-sight shortcutting, or with a forward-only Hybrid A*. A nonlinear Model Predictive Controller (NMPC) tracks the plan while discrete-time Control Barrier Functions (CBFs) on world-frame LiDAR points keep the robot clear of walls and unmapped obstacles. The algorithms live in a ROS-free, unit-tested core library, and the whole stack builds and runs from a single reproducible environment. In simulation, the robot drives a 135 m route through the maze with 1.0 cm localization RMSE against the known map and 24 cm in SLAM mode, the planner returns a path in 6 ms, and the NMPC solves in 11.7 ms on average, never exceeding its 80 ms budget.
Abstract (translated)
URL
https://arxiv.org/abs/2611.12949
PDF
-
BEV3SR: Evidence-Aware 3D Spatial Reasoning from Video
Abstract
3D spatial reasoning from video remains challenging for VLMs because videos provide sequential, view-local observations rather than persistent metric scene records. Many questions must be answered in a query-specified perspective rather than the observed camera viewpoint, and prompting with a fixed set of RGB views may miss sparse or occluded visual cues. To address these gaps, we introduce BEV3SR, a training-free and backbone-agnostic framework for RGB-D videos with camera parameters. BEV3SR turns video observations into queryable metric bird's-eye-view (BEV) scene memory and formalizes each query into an evidence-aware spatial task. The Spatial Task Formalizer specifies the query's reference frame, spatial constraints, objective, and evidence requirement. The evidence requirement determines the appropriate reasoning pathway. A query treated as requiring geometric evidence is handled by the Geometric Reasoner, which deterministically computes the answer using the metric BEV records in the query-specified reference frame. Otherwise, a query treated as requiring visual evidence is passed to the Visual Evidence Aligner, which uses BEV-indexed object records and their associated supporting views to retrieve object-consistent and scene-context RGB frames for VLM grounding. Within a standard 16-frame budget, BEV3SR consistently improves different VLM backbones across multiple 3D scene QA benchmarks, delivering large gains on spatially intensive questions and significant improvements on open-ended scene QA. These results demonstrate that BEV3SR offers an effective, efficient, and interpretable framework for explicit 3D spatial reasoning from video.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09816
PDF
-
Dual Architecture Fusion Vehicle Lidar 3D Target Detection
2026-11-06 16:13:58Muyun Li, Weizheng Jin, Yuan SunAbstract
In this paper, a 3D backbone network (SpconvTransformer) based on the fusion of convolutional architecture branch and Transformer architecture branch is proposed. The convolution branch uses 3D sparse convolution and submanifold convolution to learn local voxel features and semantic information, and the Transformer branch uses the self-attention mechanism to model the remote relationship between voxels, uses the broad receptive field to capture rich context information, and complementing the advantages of the two architectures by fusing the local features extracted from the two branches and the global features solves the problem of limited receptive fields of 3D convolutional neural networks. The experimental results show that the average accuracy of SpconvTransformer in 3D object detection and bird's-eye view detection tasks reaches 81.45% and 88.09%, respectively, and the average directional similarity reaches 91.10%, which is significantly better than other existing algorithms.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09664
PDF
-
Breaking the Privacy Promise: Gradient Inversion Attacks on Federated Low-Rank Adapted Vision Transformers
2026-11-06 16:02:20Ritik K. Badiya, Siladittya Manna, Ashmit Sinha, M Yashwanth, Anirban ChakrabortyAbstract
Parameter-efficient fine-tuning (PEFT) has been increasingly adopted to fine-tune pretrained models with low computational cost and is therefore also preferred in the federated learning paradigm to reduce computational and communication overhead. In this work, we investigate the sparsely explored problem of the risk of private data leakage in LoRA-adapted Vision Transformers (ViTs), where low-rank updates weaken the gradient signal available to a server with access to individual client updates. We show that quality of reconstruction is limited by two coupled ambiguities: reduced information in LoRA gradients and missing spatial cues from frozen positional embeddings. To address this, we propose a spatially anchored generative inversion framework that incorporates server-prescribed trainable positional embeddings into ViT blocks during fine-tuning at clients. The resulting positional gradients act as layer-wise spatial anchors, providing additional positional cues, while the generative prior keeps reconstructions on a realistic image manifold, reducing duplicate-data and patch-permutation artifacts, {which produce similar gradients as those produced when the target client images are used}. Adding our proposed spatial anchoring to GIAS improves PSNR by 10.14 dB, SSIM by 0.45, and LPIPS by 0.098 on CIFAR-10, as well as PSNR gains of 7.83 and 11.74 dB on high-resolution CelebA and CARS datasets, respectively, in the FedSGD setting. Such gains in reconstructed image quality metrics are also maintained at higher batch sizes and in FedAvg settings. These results indicate that LoRA-based PEFT does not, by itself, prevent data leakage in FL, and carefully incorporated positional embeddings can help in exposing private information.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09652
PDF
-
Graph Visualizations in Prompts for Knowledge Graph Question Answering
2026-11-06 14:55:29Luiz do Valle Miranda, Andreas L. Opdahl, Grzegorz J. NalepaAbstract
We study when and how multimodal input improves knowledge graph question answering (KGQA) in large vision--language models. Using a controlled evaluation over 1,500 WebQSP and CWQ questions and six VLMs within a fixed KGQA pipeline, we compare text-only prompting against text-plus-graph visualization at the per-question level and analyze performance changes as a function of reasoning complexity, model size, and image layout. Adding a graph image yields an average gain of 1.85 F1 points, driven by strong precision improvements on low-complexity questions (+4.65 F1). Mixed-effects and regression analyses show that these multimodal gains do not depend strongly on model scale, but are highly sensitive to graph layout: image-only settings sharply degrade performance, hierarchical Graphviz layouts outperform less organized renderings, and decomposing large subgraphs into separated paths yields the largest improvements. Taken together, the results indicate that visual prompting primarily aids KGQA by enhancing prediction precision in low-complexity contexts, provided that visual design respects cognitive and perceptual constraints. To optimize both accuracy and inference efficiency, we argue for adaptive visual prompting policies that selectively append diagrams to small, visually sparse subgraphs with well-structured layouts, avoiding unnecessary visual clutter and token overhead on complex queries. We conclude by relating these findings to a visual notation design theory, outlining how principled diagram encoding can guide future multimodal VLM prompting.
Abstract (translated)
URL
https://arxiv.org/abs/2611.12938
PDF
-
ExQuery: Explicit Structured Query Priors for Temporal 3D Object Detection
2026-11-06 14:39:12Honglin Sun, Yifei Zhang, Junyang Zhang, Kenji HashimotoAbstract
Sparse query-based 3D detectors commonly encode heterogeneous semantic, geometric, and motion information into unified latent queries, including when explicit 3D anchors are used. We introduce ExQuery, an explicit structured query framework for temporal 3D object detection. Each decoded query is organized into a shared semantic context slice and physical-state-specific slices for center, dimensions, orientation, and velocity. This structure is preserved from prior encoding to branch-specific regression and is reused to reconstruct temporal queries: predicted physical states are transformed by ego motion, classification scores form soft semantic priors, and the reconstructed query is fused with the stored latent instance feature through gated affine modulation. Experiments on the nuScenes benchmark show that our method achieves competitive detection performance, and ablation studies validate the effectiveness of our proposed modules.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09527
PDF
-
RadarDINO: Distilling a Visual Foundation Model into mmWave Radar for Human Mesh Reconstruction
2026-11-06 14:36:49Furkan Mert Algan, Zhifan Ni, Eckehard SteinbachAbstract
Millimeter-wave (mmWave) radar offers a privacy-preserving and illumination-robust alternative for human mesh reconstruction (HMR). However, high-fidelity radar HMR remains challenging. Sparse point cloud-based methods suffer from information loss and missed detections, while raw radar tensor methods like RT-Mesh lack fine-grained semantics and explicit local body modeling. In this paper, we propose RadarDINO, a radar HMR framework that distills visual semantics from a DINOv3 teacher into 3D radar representations and introduces explicit geometric supervision. DINOv3 descriptors are transferred to radar voxels via calibrated RGB-radar geometry, providing voxel- and body-part-level supervision for part-aware radar representations. We further incorporate vertex- and joint-losses to directly constrain reconstructed geometry. On the M4Human dataset, our method outperforms the SOTA baseline across all three evaluation splits.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09524
PDF
-
Cognitive Maps in Large Language Models
2026-11-06 14:33:05Albert Qin, Jonathan D. Cohen, Gautam ReddyAbstract
It has long been proposed that animals construct cognitive maps to support flexible behavior in novel environments. We tested whether large language models form analogous internal representations using relational reasoning tasks and causal "mosaic" experiments. Models beyond the ten-billion-parameter scale inferred unstated relationships and generalized to synthetic entity names. Across models and tasks, models formed abstract representations of relational structure, additively combining them with representations of entity identity. Relationships were primarily stored as pairwise links and composed retrospectively, rather than prospectively encoded in a global coordinate system. A sparse, distributed set of key-value pairs mediated binding; perturbing them implanted "false memories" that produced predictable behavioral changes. Our findings reveal a conserved organization analogous to a cognitive map supporting flexible and systematic reasoning in language models.
Abstract (translated)
URL
https://arxiv.org/abs/2610.25596
PDF
-
FlowSim: Rendering-Free Closed-Loop Simulation for Evaluating End-to-End Driving Systems
2026-11-06 14:12:27Hanfeng Wu, Alvaro Marcos-Ramiro, Michael Schmidt, Christoph StillerAbstract
Closed-loop evaluation of end-to-end (E2E) driving systems typically relies on generating sensor observations and re-processing them through the perception encoder, introducing substantial computational cost and a sim2real gap between simulated and real sensor observations. In this paper, we ask a more fundamental question: is image-space simulation necessary for closed-loop evaluation of E2E driving systems? We propose FlowSim, a rendering-free simulation paradigm that predicts the internal latent representation directly from a previous latent and target-frame symbolic scene conditions. The predicted latent is then processed by the original frozen downstream modules, eliminating image rendering and perception re-encoding. Explicit cross-frame agent association improves latent transition prediction and rollout stability, while variable-horizon simulation enables long-horizon prediction from a common real anchor without accumulating intermediate rollout errors. Experiments on nuScenes and NavSim demonstrate that FlowSim preserves downstream behavior competitively with, and often exceeds image-space simulation in source-to-reference agreement across variable simulation horizons and both dense and sparse latent representations. By predicting the latent directly, both instantiations of FlowSim simulate each step in 0.04--0.06s, substantially faster than the image-space simulation methods they are compared against. These results establish FlowSim as an efficient and practical alternative to conventional image-space simulation methods. Our project page is this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.18030
PDF
-
Train on prefill, monitor at decode: Using sparse autoencoders for topic monitoring
2026-11-06 11:33:35Rishikesh Mallagundla, Pranav PatelAbstract
Topic monitoring is the task of labelling the topic of each token in a model's response during generation. Activation-based monitors that run at generation time have so far been trained to detect harmful content and are limited to two or three classes. We introduce TopicScope, a framework for training causal topic classifiers on SAE features that assign a topic to every token, so that the label can change partway through a response. We train three detector architectures on synthetic multi-topic conversations covering seven topics. Across Gemma-3 1B and 4B, monitors trained on features extracted from prefill hidden states were able to generalise to decoding. We also found that the classifiers are robust to perturbations, losing at most 5 macro-F1 points when off-topic asides are inserted, topics are removed or sections are reordered. Ablations conducted to understand the contribution of the SAE revealed that classifiers reaching baseline performance without it were several times larger. Our findings show that compact topic monitors can be trained inexpensively in prefill and deployed during generation. More broadly, our work shows where SAEs are useful beyond safety classification. Our code, dataset and checkpoints are available at this https URL and this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2611.12935
PDF
-
DUET: Dual-Sparse Inference for Block Diffusion Language Models
2026-11-06 09:59:42Siyuan Yan, Shen Gu, Xiaoxing Ma, Chun Cao, Jingwei XuAbstract
Diffusion language models (DLMs) enable parallel token generation through iterative denoising, yet their inference remains costly due to repeated attention over a growing historical prefix and repeated processing of the entire current generation block. Historical attention becomes increasingly expensive as generation progresses, while all current-block positions are propagated through the Transformer at every denoising step even though only a small fraction are typically resolved at that step. In this paper, we introduce Duet, a training-free dual-sparse inference framework that addresses these challenges through prefix Key-Value (KV) sparsity and early query sparsity, respectively. Specifically, Duet exploits the concentration and cross-step stability of historical attention within each generation block to construct a compact historical KV subset that is reused across denoising steps. For query sparsity, Duet predicts update positions from shallow representations and propagates only the corresponding queries through the suffix Transformer layers, avoiding deep computation at positions unlikely to be updated in the current step. Experiments show that Duet maintains competitive accuracy while achieving 1.34$\times$/2.83$\times$ end-to-end/per-step speedups on LLaDA2.1-mini and 2.41$\times$/4.72$\times$ on SDAR-8B-Chat-b32 at a 32K context length.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09239
PDF
-
Calibrated concept profiles: making the reading of a model's neurons a measurement
Abstract
Interpretability has largely moved from reading a model's neurons directly to reading a second model trained on the first: a probe, a sparse autoencoder, a crosscoder. The move answered real faults -- mixed meanings, thresholds without a unit, readings that did not transfer from one study to the next -- but gave up what a direct reading alone provides: nothing trained in between, the neurons themselves named, and a reading that can be repeated and compared. Here the direct reading is made a measurement. A neuron's activation varies with the prompt, so its reading is a distribution over a population of stimuli. We declare that population: every factor around a target construct is drawn at its rate in a reference corpus and logged. From the declared distribution we generate a battery of prompts, and draw it twice. From the battery we compute the calibrated concept profile, one number per neuron, stated in units of the neuron's own spread on ordinary input; the two draws give every number a noise unit. Before the profile is read, a fixed set of checks licenses the battery on the model, and the smallest change the profile can resolve across training checkpoints is measured. Realised for Python on OpenCoder-1.5B and followed across checkpoints spanning two trillion training tokens, the profile gives what the alternatives do not report: a unit on every number, a chance level for every comparison, and which neurons carry a construct at every checkpoint. The battery, the code and the data behind every result are released.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09196
PDF
-
FIND: Frequency Invariance Disentanglement for Test-Time Adaptation in LiDAR 3D Detection
2026-11-06 08:51:47Dongxiao Li, Zixuan Hu, Ling-Yu DuanAbstract
LiDAR-based 3D Object Detection (L3OD) is a fundamental 3D perception task, yet its performance is often compromised by domain shifts arising from diverse sensor configurations and environmental conditions. Existing Test-Time Adaptation (TTA) methods primarily leverage self-supervision in the spatial domain, yet they frequently confound semantic content with domain style due to the sparse, non-Euclidean nature of point clouds. To overcome this limitation, we propose FIND (Frequency INvariance Disentanglement), a novel TTA framework that precisely disentangles domain-invariant content from domain-specific interference within the frequency domain. Our methodology utilizes B-Spline fitting to construct locally adaptive filters integrated into a dual-stream architecture: an Invariant Stream extracts robust features to guide pseudo-labeling, while a Specific Stream enforces consistency against domain perturbations. By combining invariance-driven alignment with stability-guided regularization, our approach dynamically extracts robust domain-invariant features while suppressing domain-specific interference. Extensive experiments on cross-dataset adaptation and robust corruption benchmarks demonstrate that FIND significantly outperforms state-of-the-art methods. The source code is publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09170
PDF
-
BayesCrop: Real-Time Probabilistic Multi-Crop Video Reframing
2026-11-06 07:31:30Cheng-Han Lee, Rajesh Sureddi, Neil Birkbeck, Yilin Wang, Balu Adsumilli, Alan BovikAbstract
Automatic video reframing is increasingly important for adapting landscape content to heterogeneous display formats. Existing methods typically predict a single deterministic crop, despite the subjective nature of reframing and the presence of multiple plausible regions of interest. We present \textbf{BayesCrop}, a real-time probabilistic framework for multi-crop video reframing. BayesCrop represents crop preferences using a two-component spatially isotropic Gaussian mixture over crop position and scale. Each component defines a representative reframing mode together with its local uncertainty, enabling both dual-view prediction and sampling of additional plausible crop candidates. For efficient video processing, we introduce an anchor-and-propagate strategy that performs neural prediction only on sparse anchor frames and propagates crop trajectories using motion vectors available from the compressed video bitstream. The resulting trajectories can be combined into a single output using a lightweight periodic view-switching strategy. Experiments on LIVE-YT-MC, LIVE-YT-VC++, and a multi-target long-video benchmark demonstrate competitive single-output localization, high multi-crop reference coverage, diverse yet coherent crop hypotheses, and stable perceptual quality. BayesCrop achieves real-time throughput of 112 FPS at the default operating point, while sampling from the learned distributions further improves reference coverage beyond the two representative crop means.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09100
PDF
-
AdaAlloc: Adaptive Visual Token Allocation for Long-Video Question Answering
2026-11-06 07:21:49Joungbin An, Kristen GraumanAbstract
Long-video question answering forces multimodal large language models to reason under strict visual-token budgets, creating a tradeoff between broad temporal coverage and fine-grained spatial detail. Uniform sampling preserves coverage but often obscures decisive local cues, while caption-based or frame-similarity retrieval operates over lossy proxies that can miss motion, state changes, and before-after relations. We recast long-video reasoning as a visual-token allocation problem: given a fixed budget, decide how much to spend on global context versus high-resolution local evidence, and where in the video to draw that local evidence from. We introduce AdaAlloc, a training-free inference framework that adaptively allocates visual tokens between a global video overview and localized visual detail. AdaAlloc first plans a global/local allocation policy, then uses temporal grounding to locate candidate evidence segments and refines them into a compact temporal memory. The selected policy controls both frame sampling density and resolution, combining sparse, lower-resolution global frames with denser, higher-resolution local frames drawn from the refined memory. The final answerer reasons over the allocated global context and refined local evidence. Across LVBench, MLVU, VideoMME, and LongVideoBench, AdaAlloc improves over budget-matched uniform sampling by up to 10.5 percentage points and outperforms the compared frame-selection and agentic methods on their reported benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09092
PDF
-
Training-Free Active Test-Time Adaptation for Vision-Language Models
2026-11-06 07:14:00Jihwan Bang, Sumyeong Ahn, Hwanjun Song, Jae-Gil LeeAbstract
Test-time adaptation (TTA) for vision-language models (VLMs) is usually studied in a fully unsupervised regime, where adaptation relies on pseudo-labels, confidence scores, or entropy computed by the model itself. This is a severe restriction on hard shifted samples: the model is asked to repair its own uncertain predictions without any external evidence. At the other extreme, supervised online adaptation assumes labels can directly train or correct the model. We study the intermediate deployment regime between these two extremes. In Active Test-time Adaptation for VLMs (Active VLM-TTA), a pretrained VLM may spend an explicit labeling budget on selected test samples, but the prediction for the current sample must be emitted before its label can be used; queried labels are therefore costed, delayed evidence for future samples rather than free correction for the present one. Under this future-only constraint, the central question is how to reuse sparse labels conservatively. We instantiate this setting with ACTive VLM-TTA for Online Retrieval (ACTOR), a training-free plug-in module that routes uncertain samples among base prediction, label query, and memory-based correction using a consistency-and-reliability check over previously queried labels. Across ten cross-domain benchmarks and a domain-transfer benchmark based on ImageNet, ACTOR consistently improves strong VLM-TTA baselines on ResNet and ViT backbones with negligible inference overhead. Our implementation is publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09084
PDF
-
ProtoCouncil: Multi-Encoder Anatomical Prototypes for Prostate Cancer Detection in Micro-Ultrasound
2026-11-06 06:33:28Mohammad Mahdi Abootorabi, Nooshin Maghsoodi, Armin Saadat, Obed Dzikunu, Zhuoxin Guo, Hannes Cash, Ferdinand Luger, Adam Kinnaird, Brian Wodlinger, Parvin Mousavi, Purang AbolmaesumiAbstract
Purpose: Micro-ultrasound ($\mu$US) is a promising modality for prostate cancer (PCa) detection, but identifying suspicious tissue depends heavily on clinical experience. Models trained on sparse, noisy core-level pathology offer little insight into their decisions and can fail under domain shift. Clinical use needs a traceable decision process and a flag for uncertain predictions. Methods: We introduce ProtoCouncil, in which three foundation encoders (MedSAM, DINOv3 and V-JEPA 2.1) learn case-based prototypes at three anatomical levels: whole gland, needle track and gland sectors. Prototypes are projected onto real training-core regions, and label-free fusion keeps every class logit as a bias plus an exact sum of prototype similarity contributions. Encoder disagreement triggers selective prediction. Results: In five-fold patient-level cross-validation (6,588 cores, 693 patients), ProtoCouncil reaches 82.9% AUROC for clinically significant PCa (csPCa, Grade Group $\geq$3), 4.3 points above the best previously published method. In zero-shot evaluation on two external cohorts, ProtoCouncil achieves higher all-cancer and csPCa AUROC than all previous methods. Nearest same-class exemplars match test-core tumor involvement better than random same-class cases. Externally, csPCa accuracy falls from 79% when encoders agree to 27% when two oppose the fused call. Abstaining on disagreement raises balanced accuracy by 7 and 15 points, while retaining 58% and 54% of the cores. Conclusion: ProtoCouncil grounds core-level predictions in exact similarity-based evidence from real, anatomically indexed training cases, which makes its reasoning interpretable. It achieves the highest csPCa AUROC across three cohorts and identifies unreliable predictions through encoder disagreement.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09058
PDF
-
Grounding-Aware Judge Reward Reinforcement Learning for Out-of-Domain Face Anti-Spoofing
2026-11-06 06:20:50Xiaoyong Yu, Xinge YuAbstract
Face Anti-Spoofing (FAS) must distinguish genuine faces from presentation attacks. A unified Multimodal Large Language Model (MLLM) is an attractive solution: it detects physical attacks (print, replay, mask) in one model and produces interpretable forensic evidence via Chain-of-Thought (CoT). A central obstacle to post-training such a model with reinforcement learning is that FAS reasoning has no rule-verifiable ground truth: only the binary verdict is checkable, while the reasoning chain cannot be verified by any hand-crafted rule. Optimizing the verdict alone is therefore a sparse, hackable signal. The model can reach the correct answer through a shortcut such as a false-rejection bias, which does not generalize. We address this with a grounding-aware judge reward. A 32B vision-language judge scores each reasoning chain against the image on evidence anchoring, logical coherence, and domain knowledge, turning the image itself into the verification signal. The reward is applied in a Group Relative Policy Optimization (GRPO) stage after CoT supervised fine-tuning. It is the judge, rather than the RL objective, that supplies the process supervision a verdict-only reward cannot. Our study starts from a model that already performs well In-Domain (ID) after CoT-based supervised fine-tuning and asks how to improve its Out-of-Domain (OOD) generalization. We find that grounding-aware rewards are an effective means to that end. We validate the method on OOD generalization, where the reward reduces ACER on two physical benchmarks (LCC-FASD 0.288 to 0.273, MSU-MFSD 0.431 to 0.409) while preserving ID accuracy (CelebA-Spoof 0.033 to 0.035). Against ResNet-50/101 and CLIP-ViT-B/16 baselines, the MLLM dominates ID and matches or surpasses the strongest baseline OOD. To our knowledge this is the first use of LLM-as-judge process supervision for FAS.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09047
PDF
-
ToolDex: An Ego-Exo Human Demonstration Dataset for Creative Physical Tool Use
2026-11-06 06:12:33Mohamed Elmoghany, Kehan Li, Ruoqu Chen, Tarun Chiruvolu, Shutong Zhang, Ryan Wang, Stephen Tian, Yaru Niu, Michelle Guo, Ding Zhao, Weiyu Liu, Mengdi Xu, Li Fei-Fei, Jiajun WuAbstract
Creative tool use is a fundamental human capability and an important step toward general-purpose embodied intelligence. It requires agents to reason about object affordances, physical constraints, and manipulation strategies, especially when standard tools are unavailable. However, progress in this area is limited by the lack of real-world datasets that capture human tool-use behavior with sufficient scale, fidelity, and diversity. Existing benchmarks are often simulation-based, focus on simplified interactions, or lack detailed observations and annotations. We introduce ToolDex, a large-scale egocentric-exocentric (ego-exo) human demonstration dataset for creative physical tool use. ToolDex captures scenarios in which humans select, adapt, and repurpose available objects as tools. Using synchronized egocentric cameras and eight exocentric cameras, the dataset provides high-fidelity multi-view observations and rich annotations for hands, tools, target objects, and their deformable interactions. Beyond data collection, we establish a benchmark suite characterizing three core capabilities: physical tool-use reasoning, sparse-view 3D and 4D reconstruction, and robot policy learning. ToolDex provides a foundation for studying human tool-use behavior and developing embodied agents that can adaptively use tools in complex real-world environments. Dataset visualizations and benchmarking results are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09036
PDF
-
Refer-CityFlow and M3Track: A Benchmark Dataset and Reference Framework for Language-Driven Multi-Target Multi-Camera Tracking
2026-11-06 04:39:55Phuong T. Nguyen, Hao Vo, Tam Bang, Hoang K. Tran, Hoang-Minh Dau, Mahshid Malazizi, Tuan-Anh Hoang, Mina Sartipi, Thanh-Nam Doan, Ngan Le, Hoang H. NguyenAbstract
Referring multi-object tracking enables users to specify targets through natural language, but existing Refer-MOT benchmarks primarily focus on single-camera settings. We formalize Referring Multi-Target Multi-Camera Tracking (Refer-MTMCT), where free-form queries specify identity-consistent trajectories to be recovered across a network of sequential, sparse-overlap cameras. We introduce Refer-CityFlow, a benchmark built on CityFlow's global cross-camera identity annotations and augmented with language queries requiring joint language grounding, cross-camera association, and spatio-temporal reasoning. Refer-CityFlow covers 96 videos from 40 roadside cameras with 660+ identity-consistent cross-camera trajectories, 4,362 trajectory-level descriptions, and 7,699 queries, including 1,699 real-user queries collected from 50 participants. Reference experiments on the four-camera Scenario 02 show that single-camera referring trackers reach 14.95-18.28 HOTA on real-user queries, while the evaluated cross-view method achieves about 0.05 HOTA in direct transfer. To establish reference performance, we provide M3Track, a modular multimodal reference framework in which a large language model (LLM)-based agent orchestrates interchangeable detection, tracking, and cross-camera association modules. M3Track reaches 44.10 HOTA and 65.40 IDF1 on the same real-user query set. The project repository is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08976
PDF
