Tracking
-
Reinforced Iterative Learning Control for elastic joint arms: Guaranteed cross-trajectory generalization under model uncertainties
2026-10-20 15:00:55Yuri De Santis, Michele Pierallini, Franco Angelini, Manolo GarabiniAbstract
Trajectory tracking for compliant robots is challenging due to nonlinear dynamics and modeling uncertainties, often requiring learning-based methods to avoid explicit parameter identification. Iterative Learning Control (ILC) ensures theoretically high precision and preserves the passive compliance of the robot. However, traditional ILC requires a separate learning phase for each new trajectory. Conversely, Reinforcement Learning (RL) generalizes to new trajectories, but practically suffers from high sample complexity and limited tracking precision. This work proposes Reinforced Iterative Learning Control (RILC) that combines the strengths of both approaches to achieve fast adaptation and guaranteed tracking convergence across diverse trajectories. By establishing a concurrent coupling between the two controllers, RILC overcomes the high initial errors and slow adaptation of traditional ILC, enabling high-performance tracking from the very first trials. In this architecture, ILC provides high-quality samples, while RL contributes as a generalizing best-effort policy across iterations. Additionally, a theoretical proof is presented to show that the RL component preserves ILC stability and, under specific conditions, can also reduce the error bound asymptotically. The efficacy of this framework is demonstrated through simulation and experiments on an underactuated 4-degree-of-freedom serial elastic robot using different trajectories and modeling mismatches.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28329
PDF
-
Perceives but Doesn't Brake: A Perception-Action Binding Gap in Reasoning Driving VLAs
2026-10-20 13:21:14Matteo Cercola, Katie Z Luo, Simone Formentin, Marco PavoneAbstract
Reasoning-augmented vision-language-action (VLA) driving models can perceive and reason about safety-critical hazards yet fail to translate that evidence into safe actions. We characterize this failure as a perception-action binding gap: hazard information is available inside the model but exerts insufficient control over trajectory generation. Using matched simulated counterfactuals and logged driving replay, we show that in-path hazards are actually encoded in the visual representation, but longitudinal plans are dominated by ego-speed history and respond only weakly to hazard proximity or the model's own reasoning trace. Further analysis shows that the trajectory generator is capable of braking but sometimes fails to do so due to the perception-action binding gap. Without retraining or modifying any weights, we inject a hazard-conditioned energy into the frozen flow-matching sampler of Alpamayo-1.5, restoring the missing coupling at generation time. With exact obstacle geometry, guidance cuts footprint intrusion from 58.1% to 14.5% and recovers safe braking whenever sufficient stopping distance remains, eliminating collisions entirely in our braking-relevant closed-loop battery. It also reverses the diagnosed dependence of the plan, from tracking ego speed to responding to obstacle range. These results separate hazard perception from hazard control in driving VLAs, show that unsafe behavior can arise even when the model has both the evidence and the ability to act on it, and propose a simple fix for bridging this binding gap.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28184
PDF
-
High-Precision RCM Motion for Ophthalmic Robotics via Hierarchical QP Control and Authority-Guided Recovery Planning
2026-10-20 09:20:50Huanyu Tian, Adriana Namour, Lingyun Zeng, Zicong Wu, Sebastien Ourselin, Lyndon da Cruz, Christos BergelesAbstract
General-purpose manipulators can position ophthalmic instruments under a software Remote Centre of Motion (RCM). However, at some reachable configurations that are nonsingular for the tip task alone, the RCM and tip-tracking objectives conflict and the servo oscillates. We formalise this failure as a constraint-induced task singularity: the RCM-projected tip Jacobian loses rank while the unprojected tip Jacobian stays well conditioned. Thus, the effective tip authority collapses although the target remains reachable. We present a high-precision RCM servo architecture with built-in singularity recovery: for each commanded target, an authority-guided planner selects a well-conditioned arm configuration that reaches it and plans an RCM-consistent route, executed by a fixed hierarchical-QP controller. On a 200-scenario kinematic benchmark, the complete nominal-and-recovery protocol reaches 128/128 near-singular targets and 71/72 near-joint-limit targets (100% and 99%, respectively), with the software-RCM residual below 0.142 mm. On a physical 6-DOF arm it executes across four RCM entry points, with a worst-case kinematically reconstructed RCM residual of 178 {\mu}m and a median tip-regulation error of 32{\mu}m, within the 200{\mu}m control requirement adopted for the ophthalmic task.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27905
PDF
-
Staged Continual Adaptation of Multimodal Foundation Models for Japanese Financial Documents
2026-10-20 09:19:36Genshin Kakimoto, Atsushi YanagisawaAbstract
Staged post-training of multimodal foundation models chains vision-language alignment, reasoning distillation, and domain tuning, yet how each phase trades capabilities against the others remains under-characterised. Tracking an 8.4B-parameter model from an un-fine-tuned baseline through three training phases on Japanese financial documents (evaluated on five text-input benchmarks), we find the phases interact non-additively: math-only distillation overwrites the financial knowledge acquired earlier even as procedural math skill survives, and the domain phase repairs more than it installs. A skip-phase ablation is best for domain knowledge but forfeits numerical-reasoning gains, so per-phase contributions are not decomposable and the best checkpoint is task-dependent, with implications for checkpoint retention and scheduling rather than added stages.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27904
PDF
-
RAG-NIMBF: A Non-Invasive, Modular Benchmarking Framework for Automated RAG Configuration Analysis
2026-10-20 08:08:08Niclas Hart, Nicolas WeegerAbstract
Retrieval-Augmented Generation (RAG) has become the dominant paradigm for grounding the outputs of large language models (LLM) in external knowledge. However, practitioners are faced with a vast configuration space comprising chunking, embedding, retrieval, reranking, prompting and generation models, and there is limited guidance on how these components interact. We present RAG-NIMBF, a modular benchmarking framework that attaches to existing RAG pipelines as a non-invasive evaluation layer. It evaluates the configuration space through controlled ablation with end-to-end experiment tracking. The evaluation combines LLM-based answer quality scores, retrieval correctness measures, and runtime indicators. This study validates the framework across multiple generation models on the SQuAD dataset. This process reveals non-obvious interactions and demonstrates how the experiments are tracked. The findings indicate that the retrieval balance of relevance and diversity substantially enhances the relevance and coverage of retrieved context in comparison to a conventional similarity search, with MMR raising nDCG@5 by +4 to +11 percentage points across the swept models. More detailed prompt instructions meaningfully increase how faithfully generated answers stick to the retrieved evidence, especially for capable and reasoning models (+10 to +13pp on Qwen3.6-27B, GPT-4o-mini and Qwen3.5-think, but negligible on the 20B generator). Overall, RAG-NIMBF transforms the configuration space of RAG into reproducible, comparable experiments. By attaching to existing production pipelines in a non-invasive way, it enables practitioners to systematically evaluate and improve deployed systems without disrupting existing workflows. This replaces ad hoc choices with evidence-based decisions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27816
PDF
-
Prescribed Performance Guided Safe Reinforcement Learning for Roundabout Navigation of Autonomous Vehicles
2026-10-20 06:54:57Wenhan Li, Yangrui Zhang, Hang Zhou, Peiran Liu, Yiding JiAbstract
Connected and Autonomous Vehicles (CAVs) face significant challenges in roundabout navigation due to dense traffic interactions and unpredictable agent behaviors, necessitating high levels of adaptability and safety. While the combination of Reinforcement Learning (RL) and Model Predictive Control (MPC) offers a promising approach, existing frameworks suffer from a structural mismatch where pointwise RL decisions fail to align with MPC's trajectory level optimization, and often lack rigorous safety guarantees. This work proposes RLTrajGen-PPMPC-CBF, a hierarchical framework for safe, smooth and comfort roundabout navigation, which regulates the coupling between RL-based planning and MPC-based control. We employ Prescribed Performance Constraints (PPC) to enforce a gradual, stable convergence between reference trajectories and control outputs, ensuring MPC tracking performance remains consistent with intended behavior from RL. Additionally, a Control Barrier Function (CBF) layer provides real-time safety corrections that are fed back into the RL process. Simulation results in the MetaDrive environment demonstrate that our method achieves a 6.25\% increase in average success rate and a 65.87\% reduction in Motion Sickness Dose Value (MSDV) compared to the optimal baseline, meanwhile accelerating training convergence.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27732
PDF
-
Adaptive Traversal Tubes for Posture-Aware Navigation of Bipedal Humanoids
Abstract
Bipedal humanoids can change their effective footprint by adjusting body yaw, enabling both narrow-passage traversal and socially aware yielding. This paper presents a posture-aware navigation framework centered on \emph{Adaptive Traversal Tubes} (ATT), \emph{Interval Velocity--Heading} (IVH) control, and a sidestep-enhanced AMP locomotion prior. ATT represents a behavior-feasible corridor width field along a reference path, unifying geometric clearance and social comfort into a continuous signal. IVH maps this width to a continuous frontal-to-sidestep posture schedule and omnidirectional velocity commands. A velocity-conditioned AMP policy, trained with GVHMR-retargeted frontal/sidestep motions and coupled \((v_x,v_y)\) tracking rewards, is designed to improve transition stability over a generic locomotion controller while remaining interchangeable with the default onboard policy. This preprint presents the full method; a planned evaluation protocol on a Unitree G1 is outlined, with quantitative results to follow. Demo videos of MuJoCo simulation and real-robot deployment are available at: this http URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27688
PDF
-
PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking
2026-10-20 04:54:06Pan Wang, Yihao Hu, Guangyuan Dong, Yitong Lin, Hang Wang, Zimi Liu, Zhihao Wen, Jianshe Li, Jiang-Ming Yang, Wei Wu, Yongqi TongAbstract
Looped language models can run more iterations at test time, but additional iterations need not help them solve longer problems. For sequential state tracking, final-answer supervision does not specify how far each iteration should advance, and repeated updates can change the scale of the recurrent state. We introduce \textbf{Progress-Aligned Recurrence (PAR)}, which trains the prediction at iteration $k$ to match the state after the first $k$ operations and rescales recurrent states to their first-iteration norms. On swap-$S_5$, a Qwen2.5-0.5B model trained on at most 32 moves achieves 95.5\% mean full-state accuracy at 512 moves, or $16\times$ the training length, compared with 55.7\% reported for RLT and 0.8\% for explicit chain of thought on the same backbone. Controlled $S_5$ ablations show that removing norm anchoring reduces the extrapolation factor from $16\times$ to below $2.2\times$, and replacing progress-aligned targets with final-answer supervision reduces it to at most $8\times$. A learned completion readout selects when to answer without a supplied stopping depth. When intermediate labels are unavailable, prefix self-distillation induces the correspondence from shorter problem prefixes using only final answers. The gains apply across sequential state-tracking tasks, establishing the task structure required for depth extrapolation. These findings support training intermediate predictions and state scale together to make additional recurrent depth useful for longer problems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27628
PDF
-
Provisioning Robust and Efficient LiDAR Perception for Autonomous Driving
2026-10-20 04:31:30Tingxu Han, Zijie Shen, An Guo, Lyuke Wang, Chunrong Fang, Zhenyu Chen, Wei SongAbstract
LiDAR-based 3D object detection is a core perception service for autonomous driving, but deployment requires robustness to point-cloud corruption while meeting latency and memory requirements. Existing approaches address robustness and resource efficiency separately, resulting in compact detectors that are fragile under corruption or robust detectors that remain costly to deploy. We therefore formulate LiDAR perception provisioning as constructing a detector that remains accurate under point-cloud corruptions while meeting constraints on inference latency and peak GPU memory. To achieve robustness, we first craft corrupted samples that mimic extreme weather conditions. Then we train candidate detectors offline by ordering clean and corrupted samples by perturbation sensitivity, through which detectors learn more from hard corrupted samples. We estimate perturbation sensitivity using an ensemble of seven heterogeneous 3D detectors by tracking changes in confidence, BEV overlap, and unmatched detections. To improve efficiency, we narrow the network and use offline neighborhood-density measurements to determine how many points and neighbors each sampling stage processes. We evaluate our method using AP (Average Precision) under clean and corrupted conditions, inference latency, and peak allocated GPU memory. On KITTI for Car detection with PointRCNN, our method improves Moderate AP under corruption by 3.32 points over the original detector while reducing mean latency by 19.8% and peak allocated GPU memory by 53.9%. Across two datasets, two detector architectures, and three object classes, our method improves AP under corruption by 4.03 points on average over the corresponding original detectors, while reducing mean inference latency and peak allocated GPU memory by 14.4% and 38.0%, respectively. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27617
PDF
-
Real-Time Disturbance-Aware Koopman Model Predictive Control for Quadrotors in Spatially Varying Winds
2026-10-20 00:09:22Stella Kombo, Masih Haseli, Alejandro A. Stefan-Zavala, Peter I. Renn, Morteza Gharib, Joel W. BurdickAbstract
Reliable quadrotor flight in disturbed environments requires predictive models that remain accurate as unmodeled aerodynamic effects change during deployment. We introduce a disturbance-aware Koopman Control Family (DA-KCF) framework that preserves an offline-identified nominal model while learning only a disturbance-induced correction online. A reference-dependent KCF is first learned from simulation data and calibrated using limited hardware data. During deployment, the nominal KCF remains fixed while a lightweight residual ensemble learns a low-dimensional disturbance correction from causal state-command-state transitions. The Adaptive DA-KCF model is incorporated into MPC, where disturbance corrections are evaluated along the prediction horizon to optimize position and yaw references sent to the onboard stabilizing controller. Hardware experiments on a nano-quadrotor under uniform wind and a spatially varying wake demonstrate that online adaptation improves multi-step prediction and trajectory tracking as disturbance-induced model mismatch increases, while satisfying real-time control requirements.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27414
PDF
-
Determination of the Human-Robot Interaction Workspace for Robot Assisted Head Stabilization Control
2026-10-19 21:57:35Xinmin Liu, Alexander L. Van Slyke, Destinee Holloman, Ahmad Sakaamini, Rodney D. WiersmaAbstract
Accurate head immobilization is critical for medical procedures such as neuroimaging and intracranial radiation therapy, where even minor motion can compromise precision. Traditional methods, such as rigid stereotactic frames and thermoplastic face masks, are invasive, uncomfortable for patients, and require a time-consuming setup. To overcome these limitations, a novel approach employs a 6-degree-of-freedom (6DoF) robotic head holder that is integrated with real-time optical motion tracking, enabling dynamic compensation for head movements without physical restraint. However, implementing this system requires a detailed biomechanical understanding of skull-cervical spine interactions to define safe and effective motion limits. In this study, we conduct a human volunteer investigation using a 6DoF Stewart platform robot to characterize biokinematic workspace of the head-neck system and establish foundational data for human-robot interaction in precision head stabilization.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27336
PDF
-
Preference-Aware Pareto Steering for Multi-Task Speech LLMs
2026-10-19 19:35:51Liuyuan Jiang, Vishal Sunder, Samuel Thomas, Brian Kingsbury, Jeff Kuo, Lisha Chen, George SaonAbstract
Speech large language models (LLMs) perform multiple tasks, including automatic speech recognition (ASR), timestamp prediction (TS), and speech translation (ST). Joint training of speech LLMs creates task trade-offs, yet standard training with fixed loss weights does not generally control the resulting trade-off according to deployment preferences. To address this, we propose Endpoint-Anchored Preference-Aware Sampling Uniformly along the Pareto Front (EA-SURF), an a priori method that adapts scalarization weights so that the resulting task trade-off reflects the desired preference. EA-SURF retains the standard weighted-loss training pipeline, tracking the current model's performance relative to each task-specific reference and adapting the scalarization weights as training proceeds. We theoretically show that EA-SURF can match a desired preference, with the update becoming stationary at the target under checkable regularity conditions. Across six three-objective speech LLM requests, EA-SURF empirically converges toward the requested targets and increases endpoint-inclusive normalized hypervolume by 17.8% over fixed loss weighting.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27200
PDF
-
PROVISO: Provenance-Informed Action Selection for Secure LLM Agents
2026-10-19 18:13:53Bo Yan, Qi Zhang, Ziwen Kan, Fnu Suya, Song WangAbstract
LLM agents act on the external world through tools and third-party skills, so a single executed action can cause irreversible harm. Existing defenses judge a proposed action without tracking whether its content comes from the user or from external sources such as tool outputs, and they judge it in isolation rather than against an available alternative, which forces a trade-off between security and utility. We present PROVISO, a controller that decides which action to commit after the agent proposes an action and before it is executed. PROVISO encodes trusted observations, external observations, the proposed action, and an alternative into provenance-typed memory, relates them through role-specific queries, and commits the action with the highest calibrated value learned from outcomes. On four agent security tasks spanning the agent lifecycle, no baseline exceeds PROVISO in both security and utility. PROVISO improves F1 over the strongest baseline by 13.84 points on SkillsBench and by 7.07 points on ToolSafe, and it reaches 88-99 F1 on three additional skill detection benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27115
PDF
-
A Paired RGB-Sonar Dataset for Fish Monitoring with Consumer Sonar
2026-10-16 17:01:53Mourad Derbedrosian, Michael Hobley, Pietro PeronaAbstract
Imaging sonar enables underwater observation in conditions where optical imaging is ineffective due to darkness and turbid water. However, imaging-sonar systems previously used for ecological monitoring have typically been expensive, limiting their accessibility. Consumer forward-looking sonar has the potential to make fish monitoring more accessible, but its noisy imagery makes annotation and the development of automated methods challenging. We introduce the Huntington and Caltech Koi RGB and Sonar dataset (HaCKRS), which pairs Garmin LiveScope imaging-sonar recordings with top-down RGB video of koi carp. The dataset contains more than 105,000 temporally matched frame pairs, spanning approximately 3.3 hours of recordings across four range and orientation configurations. We provide frame-wise metadata, sonar geometry and coordinate information, synchronization data for all four configurations, and planar registration for the three horizontal configurations. The release focuses on paired observations and calibration rather than task-specific fish annotations. We intend HaCKRS to support annotation and the development of fish detection, tracking, and counting methods, and investigations into the potential of consumer sonar for ecological monitoring.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23759
PDF
-
The Cognitive Cost of LLM Writing: A Reading-Time Comparison with Human Text
2026-10-16 16:35:41Kamer Cekini, Elisabetta Biondi, Chiara Boldrini, Andrea Passarella, Marco ContiAbstract
Although linguistic differences between human-written and Large Language Model (LLM)-generated texts have been extensively studied, their implications for the cognitive effort involved in reading remain less explored. In psycholinguistics, reading time is commonly used as an indirect measure of cognitive processing effort. Building on this perspective, we investigate whether human-written texts and their LLM-generated rewrites exhibit differences in predicted reading time that may reflect differences in processing demands for readers. To this end, we introduce RoBERTa-RT, a model trained on human eye-tracking data to predict word-level reading times. We evaluate the model on both internal and external test sets, construct a paired dataset of 496 human-written articles and their LLM-generated rewrites, and apply RoBERTa-RT to compare their predicted reading times. Our findings show that LLM-generated rewrites tend to be shorter and have slightly lower predicted total reading times, while exhibiting higher predicted reading times per word. These differences are associated with systematic linguistic changes, including longer and less frequent words, greater lexical diversity, and higher contextual predictability. From a cognitive perspective, our findings suggest that LLM-generated writing may redistribute reading demands: reducing the amount of text to process while increasing the predicted processing effort associated with individual words. This highlights the importance of considering not only the linguistic characteristics of machine-generated content, but also its potential implications for human cognitive processing.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23715
PDF
-
NutriVision: Ingredient-Conditioned Fusion and Prediction for Single-Image Food Nutrition Estimation
2026-10-16 14:33:03Avinash Anand, Aman Kumar, Chaitanya Lakhchaura, Ashutosh Kumar, Akshita Abrol, Timothy Liu, Zhengkui WangAbstract
Nutrition estimation is a fundamental task in consumer diet tracking, clinical dietetics, chronic disease management, sports and hospital nutrition, and broader food computing systems. The existing approaches have progressed along two largely separate axes, vision models that rely on calibrated RGB-depth captures and ingredient-aware methods that use textual cues but use limited multimodal fusion. We introduce NutriVision, an end-to-end framework that leverages visual geometry and ingredient semantics to estimate calories, mass, fat content, carbohydrates, and protein from a single RGB image and an optional ingredient list. It obtains the unavailable depth modality using DepthAnything-V3 and encodes ingredient descriptions using CLIP. It integrates three complementary mechanisms: (1) an \emph{Ingredient-Conditioned Frequency-Aligned Fusion Module (IC-FAFM)}, which uses textual guidance to reweight and align RGB-depth frequency components; (2) an \emph{Ingredient-Aware Mask-based Prediction Head (IA-MPH)}, whose gating and channel masks are conditioned on food identity; and (3) modality-specific \emph{Internal Semantic Modeling (ISM)} blocks. On the Nutrition5k dataset, NutriVision achieves a mean PMAE of $\mathbf{13.60\pm0.10\%}$, outperforming our IGSMNet implementation by $0.89$ percentage points and OmniFood8k by $2.90$ percentage points (both $p<0.001$). The module-level ablations identify the ingredient-aware prediction head as the primary architectural contributor, improving mean PMAE by $1.50\pm0.17$ percentage points ($p<0.001$). These results demonstrate that ingredient-conditioned prediction and frequency-aware RGB-depth fusion provide measurable gains for single-image nutrient estimation. More broadly, NutriVision offers a practical route toward nutrition-assessment systems that exploit geometric and semantic cues without requiring specialized depth-sensing hardware
Abstract (translated)
URL
https://arxiv.org/abs/2609.33076
PDF
-
FLoTS-SLAM: Optical Flow-Derived Uncertainty for Monocular Dynamic SLAM with Two-Stage Optimization
2026-10-16 14:07:19Haorui Du, Lipu ZhouAbstract
Monocular simultaneous localization and mapping (SLAM) remains challenging in dynamic environments. Real-time dynamic object identification in such environments is a critical problem. Recent approaches estimate per-pixel uncertainty from rendering residuals or multiview feature inconsistency to identify dynamic regions. These methods lack direct motion evidence, and their accuracy may degrade when reconstruction is inaccurate or features are ambiguous. In addition, such uncertainty merely downweights pixels in bundle adjustment (BA), so inaccurate uncertainty estimates can still impair camera pose estimation and 3D reconstruction. Accordingly, we present a monocular RGB SLAM system for dynamic scenes. Specifically, a motion uncertainty estimation method is proposed to derive uncertainty from the residual between optical flow and camera motion induced flow, directly reflecting object motion. The estimation varies with frame alignment accuracy, reducing false detections and yielding accurate pixel-level masks of dynamic regions. To make BA more robust, we estimate camera poses from high confidence pixels. These poses are then used to reproject dynamic pixels during joint refinement of poses and depth, reducing the influence of object motion on both pose and depth updates. Moreover, we provide a quantitative evaluation of dynamic masks and analyze how these masks affect the downstream tracking and reconstruction of dynamic objects. Our approach improves the mean dynamic mask IoU by 35\% over a state-of-the-art baseline on DAVIS, and reduces the average ATE by 59\% on Bonn and 19\% on TUM relative to the SLAM backbone used in our system. The source code will be made publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23496
PDF
-
LonGaussian: Tracking Foundation Priors for Long-Context Feedforward Gaussian Reconstruction
2026-10-16 10:24:17Zhoufeng Xie, Guanjun Wu, Shuai Zhang, Xinggang Wang, Wenyu LiuAbstract
Reconstructing high-quality, renderable 3D scenes from long videos is essential for robotic perception and embodied intelligence. Many feed-forward Gaussian reconstruction methods rapidly predict 3D scenes from a small set of images, but extending them to longer sequences presents two bottlenecks: jointly processing all views increases GPU memory requirements, while accumulating pixel-aligned predictions redundantly represents the same surfaces and increases storage and rendering costs. We present LonGaussian, a streaming feed-forward framework that reconstructs compact, globally renderable Gaussian scenes from long image sequences with known intrinsics and unknown camera poses. Built on a pretrained streaming 3D reconstruction backbone, LonGaussian decodes long-context geometric features into dense Gaussians. Within each chunk, multi-frame point tracks link repeated observations of the same surface and guide a learned merger to consolidate the corresponding Gaussian predictions. Rendered-depth consistency filtering further suppresses Gaussians from other chunks that incorrectly occlude locally reconstructed surfaces. On DL3DV and RealEstate10K benchmarks, LonGaussian improves novel-view rendering quality while using substantially fewer Gaussians than the evaluated feed-forward baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23250
PDF
-
BeJEPA: A Goal-Conditioned Humanoid Behavior World Model via Unsupervised RL
2026-10-16 08:33:08Liyun Yan, Haoyang Li, Yang Zhang, Jialing Zhu, Zhanxiang Cao, Zihao Zhou, Keqi Zhu, Yizhi Chen, Huang Chuxuan, Shengcheng Fu, Zhong Jiangwei, Qiao Sun, Chen Zhang, Yue GaoAbstract
Humanoid control requires coordinating whole-body posture with position and heading in the world frame. Mainstream controllers imitate trajectories in the root frame, but struggle to regain the target world pose after displacement. We introduce BeJEPA, a goal-conditioned Behavior World Model learned through unsupervised reinforcement learning from human motion priors and robot interaction. BeJEPA learns a shared representation of body configuration and world placement through a joint-embedding predictive architecture (JEPA). A Dynamic Predictor predicts the next state embedding under an action, while a Successor Predictor summarizes a goal-conditioned policy's expected discounted future state embeddings in a single vector. During joint training, Dynamic grounds the initial representation in observed physical transitions, while Successor increasingly organizes it around long-term behavior. Their composition guides policy improvement through one physical prediction and one behavioral summary, without long imagined rollouts. In 20-second motion-tracking experiments, BeJEPA with online action refinement using Dynamic outperforms all evaluated baselines in global body-position error, reducing it on AMASS by 61.7% relative to BFM-Zero with world-pose inputs and 58.7% relative to SONIC. Physical deployment on a Unitree G1 demonstrates joint attainment of posture, world position, and heading goals, recovery from the ground, and closed-loop return after disturbances and goal changes. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23127
PDF
-
Reliability-Consistent Appearance Modeling for RGB-Infrared Multi-Object Tracking
2026-10-16 08:30:48Bingyang Wang, Jiazuo Yu, Lu Zhang, Lihe Zhang, Huchuan Lu, You HeAbstract
Recent RGB-infrared multi-object tracking (MOT) methods have substantially improved cross-modal representation learning and multimodal information integration. However, most existing methods compress RGB and infrared evidence into a unified descriptor. When one modality is temporarily degraded, the tracker can no longer regulate its contribution separately; unreliable evidence may distort association and contaminate appearance memory. We therefore propose RCA-MOT, a reliability-consistent appearance modeling framework that preserves cross-modal complementarity while retaining post-representation evidence controllability. RGB-specific, infrared-specific, and fused identity representations are maintained as jointly accessible appearance states. For each detection, a simple training-free target-scene estimator produces branch-wise appearance reliability used across the two temporal roles of appearance: relative reliability regulates different identity branches, absolute reliability calibrates borderline candidates near the ReID acceptance boundary, and the same branch-wise reliability controls how strongly matched descriptors update historical appearance memory. The individual components are intentionally simple, focusing evaluation on reliability-controllable appearance organization rather than elaborate fusion or learned reliability-estimation modules. RCA-MOT sets new SOTA results on VT-MOT and UniRTL, improving the previous best HOTA by 5.402/6.075 points and IDF1 by 11.549/12.789 points, respectively, while post-hoc analyses further validate reliability as an informative control signal. Code will be released upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23125
PDF
