Face
-
Left-Right-Consistent Iterative Stereo Matching via Cross-Injection
2026-11-06 13:29:00Manuel Knott, Diogo Luvizon, Daniel Scharstein, Elias VansteenkisteAbstract
State-of-the-art stereo matching models predominantly predict the disparity of only the left (reference) view. However, applications such as per-eye AR/VR rendering, novel view synthesis, or two-view depth fusion require disparity for both views, and need those two maps to agree. The usual workaround of running the network a second time on the horizontally flipped and swapped pair gives two independent predictions that can be inconsistent, especially on transparent surfaces, in textureless regions, and at occlusion boundaries. We introduce cross-injection (CI), a lightweight extension for iterative (refinement-based) models that can be added to any pretrained left-only iterative matcher. It couples the two passes by injecting the explicit, signed left-right inconsistency as an additional input cue at every step of the refinement stage. We empirically show that CI substantially reduces left-right disagreement on every benchmark (more than halving it on Booster for FoundationStereo), while largely preserving sharp object boundaries. Furthermore, using two state-of-the-art stereo matching models, we show that CI also reduces the single-view disparity error, making it a worthwhile extension even if only left disparity is needed.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09458
PDF
-
Mesh-Agnostic Refinement Models for Latent Space Encoding of 3D Human Body Shapes
2026-11-06 08:03:33Chaima Zouaoui, Jonathan Cerqueira, Sylvain Arguillere, Martin Bauer, Nicolas Charon, Mohamed Daoudi, Emmanuel HartmanAbstract
Parametric human body models such as the Skinned Multi-Person Linear (SMPL) model provide compact representations of human shape and pose, but their reconstructions remain affected by both errors in estimated latent parameters and limitations in the decoder's expressive capacity. We propose a framework for refining these reconstructions by exploiting the geometric discrepancy between an initial decoded surface and a target mesh, without requiring vertex correspondences between them. The framework comprises three complementary approaches. Latent-VaRefine uses varifold distance gradients to correct the estimated latent code while preserving the original parametric representation. Vertex-VaRefine processes multiscale varifold-gradient features with a DiffusionNet backbone to predict vertex displacements in a canonical pose, yielding an approximately pose-equivariant refinement pipeline. ElaOpt directly optimizes surface deformations under elastic regularization and normal direction constraints. On AMASS, Vertex-VaRefine reduces the mean vertex-to-vertex error of OmniFit reconstructions from 1.181 to 0.342 cm, a 71.0 percent reduction, while combining Latent-VaRefine with ElaOpt reduces the asymmetric Chamfer distance of ArtEq reconstructions from 1.681 to 0.717 cm, a 57.3 percent reduction. Evaluations with SMPL-H and SMPL-X demonstrate the framework's adaptability to different body models, while additional experiments on remeshed targets and raw scans assess its robustness to changes in discretization and geometry beyond the parametric model. These results highlight the complementary strengths of latent space correction, learned vertex refinement, and elastic optimization, offering different trade-offs between preserving the model parameterization and improving geometric fidelity.
Abstract (translated)
URL
https://arxiv.org/abs/2611.03285
PDF
-
Toward the Era of Agentic Embodied Intelligence
2026-11-06 08:02:15Chao Liang, Ke Chen, Fengxiaoxiao Li, Shibo Huang, Yufeng Sun, Zhaokai Yin, Jianhuan Lai, Haozhe Feng, Chenghuan Jia, Zhipeng ZhangAbstract
Foundation models increasingly guide robot actions, yet sustained autonomy requires efficient control and failure recovery. We introduce A2-MEAS, an embodied multi-agent framework built around code as a scaling interface. Learned correction codes combine corrective language, spatial evidence, execution history, and action proposals. MetaBrain provides training supervision and runtime guidance. A correction encoder and adapter absorb this knowledge into policy weights during training, while fresh codes adapt behavior with frozen weights at deployment. The action model, A2-WLA, adds motion-aware history and a latent world model to a vision-language-action policy. Surprisingly, this simple design with action pretraining and task specialization reaches 0.5755 Q-score on the 50-task BEHAVIOR 2026 public subset before online correction, 2.21x the 2025 winner's reported 0.2605 across different benchmark editions and training configurations. On all 100 BEHAVIOR 2026 public tasks, A2-MEAS achieves 0.6411 Q-score and 45.40% task success. On RoboTwin 2.0, A2-WLA achieves 93.98% average success, rising to 95.05% with the complete system. Across 12 real-robot tasks in five household settings, A2-WLA achieves 57.92% average success versus 26.67% for pi0.5. In long-horizon pour-over coffee preparation, a history-conditioned adapter raises post-failure completion at two filter-handling steps from 14% to 94% and from 8% to 82%, compared with A2-WLA retries. Our training infrastructure delivers 427.1 samples per second, 4.03x the throughput of a pi0.5 reference implementation on matched hardware. We will release the system, models, training scripts, and infrastructure to support efficient embodied learning.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09124
PDF
-
MARS: Training Multilingual Search Agents for Retriever-Free Evidence Acquisition
2026-11-06 07:20:03Rui Qi, Yunlong Liang, Yufeng Chen, Jinan Xu, Fandong Meng, Kaiyu HuangAbstract
Existing multilingual retrieval-augmented generation relies heavily on learned retrievers and similarity-based ranking from multilingual collections, which are vulnerable to cross-lingual retrieval errors and indexing overhead. In this paper, we explore retriever-free multilingual search, where the model directly interacts with raw corpora through executable shell commands. This paradigm shifts the bottleneck to multilingual search action generation, where exact search is sensitive to entity surface forms and outcome-only supervision provides limited guidance for multi-turn search. To address these challenges, we propose MARS, a multilingual search agent in direct corpus interaction (DCI) with reinforcement learning (RL). MARS introduces corpus-native entity grounding to recover reliable lexical anchors from corpus evidence, mitigating failure to retrieve evidence. Meanwhile, we present a redundancy-aware search reward to encourage concise and effective search trajectories, addressing training collapse in RL of multilingual scenarios. Experiments show that \ours~consistently outperforms strong retrieval-based and DCI baselines, while demonstrating robust cross-lingual generalization and substantially reducing redundant corpus interactions.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09090
PDF
-
GlobalPuzzle: Globally Informed Genetic Search for Eroded Jigsaw Puzzle Reassembly
2026-11-06 07:05:09Lunyan Wang, Chuanzhi Xu, Ziyuan Tao, Weidong CaiAbstract
Jigsaw puzzle reassembly remains a highly challenging task, particularly when piece boundaries are irregularly eroded to simulate damage to cultural artifacts. On the GAP benchmark, existing methods achieve a perfect assembly accuracy of only 0.3% on $5 \times 5$ puzzles, whereas humans can solve jigsaw puzzles with remarkably high accuracy. Humans typically approach puzzle solving by identifying potentially adjacent pieces, evaluating the current assembly, and iteratively performing complex operations such as adding pieces, replacing incorrectly placed pieces, and moving entire connected groups of pieces. However, existing methods face a fundamental limitation: approaches that leverage global visual information typically predict piece arrangements directly, making it difficult to explicitly perform such complex iterative operations, while search based methods can rearrange pieces but primarily rely on pairwise boundary compatibility, lacking global visual information to evaluate and guide the search process. To bridge this gap, we propose GlobalPuzzle, a jigsaw puzzle reassembly framework that integrates global canvas level evaluation, action guidance, and genetic search. By incorporating global visual information into the evaluation and optimization of candidate assemblies, GlobalPuzzle aims to resolve ambiguous adjacency relationships that are difficult to determine from irregularly eroded piece boundaries alone, enabling flexible, globally informed reconstruction.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09077
PDF
-
Emo-LiveSync: Real-Time Universal Lip Synchronization with Explicit Emotion Control
2026-11-06 07:01:35Sangjoon Yu, Seungeun Lee, JoonHeyok Shin, Ji-Su KangAbstract
Lip synchronization, the task of generating realistic lip movements synchronized with audio signals, is fundamental to applications such as film dubbing, virtual avatars, and digital content creation. Recent GAN-based methods offer computational efficiency but often lack visual fidelity, while diffusion-based approaches achieve high-quality results at the cost of substantial computational overhead. Moreover, most existing methods are limited to photo-realistic human faces, restricting their applicability to stylized characters and non-human entities. In this paper, we propose an efficient universal lip-sync video generation framework that achieves high-quality results without compromising computational efficiency. We build on LivePortrait, a warp-based portrait animation model, and introduce a training strategy that aligns audio signals to an implicit motion space by distilling knowledge from a pre-trained video-to-motion model. This enables real-time inference while maintaining high visual fidelity, and naturally generalizes to diverse stylistic characters beyond photo-realistic humans. Furthermore, we introduce an expressive control gate that enables explicit manipulation of emotional expressions for content enrichment. Extensive experiments demonstrate that our method achieves state-of-the-art performance in both visual quality and lip-sync accuracy while ensuring real-time inference.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09074
PDF
-
OmniLatent: Unified Latent for 3D Part Modeling
2026-11-06 06:31:14Yunhan Yang, Yunfei Zhao, Zeqiang Lai, Jiachen Xu, Minxiu Wang, Xintong Han, Xiangyu Yue, Xihui Liu, Chunchao GuoAbstract
3D part decomposition is a central capability for editable asset creation, yet existing workflows typically segment a completed mesh as a post-processing step, making the result sensitive to geometric artifacts, texture ambiguity, and limited part-level annotations. We present OmniLatent, a unified latent modeling framework for 3D part decomposition. Instead of predicting part labels in isolation, OmniLatent learns a shared latent space that jointly encodes geometry, deformation, appearance, and binary part IDs, allowing data-rich geometric and visual priors to support data-scarce part learning. Given a single input image, the base model generates geometry, deformation, texture, and surface part IDs in one pass, producing a part-aware 3D asset without a separate segmentation stage. We further tune the pretrained model for two extensions: a point-prompt adapter that maps arbitrary 3D point prompts with binary part IDs into latent tokens for full segmentation, refinement, and part subdivision, and an amodal part completion model that completes partial surface masks into a coherent full-object decomposition through dynamic per-part token allocation, cross-attention to the given geometry latent, and alternating part-local and global attention. Extensive experiments show that OmniLatent produces semantically meaningful part segmentations with precise boundaries, supports interactive part editing, and completes partial part observations while preserving global object consistency.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09055
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
-
When to Trust the BIM: Identifiability-Aware LiDAR-Inertial--BIM Fusion under As-Built Deviations
2026-11-06 06:20:09Yujie Zhang, Yuxuan Guo, Xinbao Sun, Chunlei Zhao, Langqi Miao, Xiaohui Jia, Jinyue LiuAbstract
Building information models (BIM) can provide a global geometric reference for robot localization with LiDAR-inertial odometry (LIO). However, as-built deviations from the as-designed model mean that a disagreement between a scan and the BIM may arise from a pose error, an offset wall surface (an as-built deviation or an unmodeled object in front of the wall), or a shifted room, and in some geometries these explanations produce identical observations. In this paper, we formalize this attribution problem as fault identification over three fault classes and derive a geometric criterion for when attribution is possible. Building on it, we propose an identifiability-aware method that reports an attribution only when the fault is attributable; otherwise, it retains the candidates, defers BIM updates and BIM-based pose corrections in the ambiguous directions, and recovers once new references arrive. In the pre-registered two-dimensional study, on cases whose fault is detectable but not attributable, the method's conditional error rate was 0.83%, against 31.67% for a baseline with uncertainty-based abstention at the same answer rate. On the 5,600 attributable cases, the method reported a unique attribution 5,574 times, with no incorrect attributions. In paired fault injections in a laboratory room with its IFC model and on three floors of the SLABIM dataset, it raised no off-target attribution (0 of 168 conditions in the laboratory; 0 of 1,302 on SLABIM) and attributed all eight laboratory faults predicted to be attributable, whereas both reproduced baselines raised off-target structural flags in every setting.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09045
PDF
-
Did I See It or Think It? Probing Reality Monitoring in Vision-Language Models with Concept Injection
2026-11-06 05:43:04Tina Khezresmaeilzadeh, Seyedarmin Azizi, Mehdi Kamal, Massoud PedramAbstract
Recent work tests whether language models can introspect by injecting a concept direction into their activations and asking whether they notice it and can name it. These studies are text-only. Vision-language models (VLMs) face an additional problem, known in cognitive psychology as reality monitoring: they must keep internally generated content separate from what they actually see. We therefore ask: can VLMs distinguish injected concepts from image content? We introduce a paradigm that varies the image and the injected concept independently. On each trial, the model reports what it sees, whether a thought was injected, and what that thought is. This design scores both whether the model identifies the concept and which source it assigns to it. Across six VLMs, only Gemma-3-27B reliably identifies injected concepts (35% vs. 3% for steering alone), with almost no false alarms. Even then, the source it reports is fragile. Strong or visual-pathway injections are reported as seen, and a visible object nearly eliminates correct thought reports. The same failure appears in ordinary captioning, where injected objects appear in up to 87% of captions of real photographs. Evaluating multimodal self-reports therefore requires checking both their content and their reported source.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09014
PDF
-
DexHOT: Learning Hand-Object Configuration Transfer for Dexterous Manipulation
2026-11-06 03:26:11Zhewei Gui, Anthony Bolton, Jiyao Zhang, Zeyuan Chen, Qiyang Yan, Tianyu Wang, Hao DongAbstract
Dexterous manipulation involves not only moving objects, but also arranging the hand around them to maintain useful contacts and enable subsequent actions. Yet many learning-based systems specify goals primarily through object poses or trajectories, leaving hand-object configurations to emerge implicitly. We introduce DexHOT, which formulates dexterous manipulation as hand-object configuration transfer: moving between feasible configurations that jointly specify hand articulation and object pose relative to the wrist. DexHOT learns a reusable relation-conditioned transfer primitive from synthetic feasible configuration pairs, without human reference motions, and composes long-horizon behaviors through closed-loop tracking of configuration subgoals. On DexHOTBench with 120 objects, a single policy achieves 80.5% transfer success on seen objects and 69.4% on unseen objects; on a real dexterous hand, it achieves 61.5% success over 200 real-robot transfers and 90% task success across six demonstration-guided tasks. These results show that explicit hand-object goals provide an expressive and composable interface for dexterous manipulation. More details and videos are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.05119
PDF
-
Wellness Robots and the Path to Full Autonomy
2026-11-06 03:19:49Mohammad H. Mahoor, Matthew Hessler, Lombe Chileshe, Ola Alsaadi, Eshrat Emamian, Kerstin S. Haring, Richard M. VoylesAbstract
This paper introduces the autonomous wellness robot as a distinct category of socially assistive system, defined by its capacity to continuously assess and respond across the seven ICAA dimensions of wellness (see Figure 2). We propose the Care Robot Autonomy Scale (CRAS): a six-level taxonomy (L0-L5) modeled on the automotive automation standard SAE J3016 and evaluated across four wellness-aligned dimensions. We present Ryan, developed initially at the University of Denver and commercialized by DreamFace Technologies, as a case study. NIH/NIA-funded longitudinal evidence (N = 18; 887 hours) shows statistically significant cognitive improvement (SLUMS +2.61, p = 0.015) and a clinically meaningful directional reduction in depressive symptoms (PHQ-9 -2.50, p = 0.073), with no novelty effect. We position Ryan today at CRAS Level 1-2, with emerging Level 3 capabilities in some dimensions, and outline a three-phase roadmap to L5 (full autonomy) by the early 2030s.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08930
PDF
-
UAV-Based Computer Vision for Cattle Detection and Feed Bunk Spatial Analysis
2026-11-06 03:18:45Pedro Oliveira Torrente, Diego Giaretta de Paulo, Lucas Pascotti Valem, Jianglong Yan, Everton Castel\~ao Tetila, Jayme Garcia Arnal Barbedo, Liang ZhaoAbstract
Beef cattle production is central to Brazilian agribusiness and faces growing demands for efficiency, sustainability, and animal welfare. Precision Livestock Farming (PLF) offers tools to address these challenges, particularly through monitoring feeding-related spatial patterns in confined systems. Feeding management plays a decisive role in animal performance, yet its evaluation still relies largely on subjective, labor-intensive visual inspections that are hard to scale and prone to bias. This work proposes a computer vision framework based on Unmanned Aerial Vehicles (UAVs) to quantify cattle alignment and spatial dispersion at the feed bunk under real-world feedlot conditions. A UAV dataset was collected during flight campaigns at a commercial feedlot in Mato Grosso do Sul, Brazil. Images were manually annotated into cattle head and cattle back classes to support object detection and image-level spatial analysis of cattle distribution. You Only Look Once (YOLO) models, namely YOLOv8 and YOLOv11, were evaluated, with YOLOv8 small used for the downstream spatial analysis. The feed bunk region was segmented using the Segment Anything Model (SAM), and geometric metrics based on detected head positions were developed to characterize alignment, spacing regularity, and clustering. The selected detector achieved 84.30% mAP50 and 35.50% mAP50-95, with an inference time of approximately 2.7 ms per image on an NVIDIA RTX 5060 Ti GPU. The resulting metrics distinguished representative regular and irregular spatial distributions by Root Mean Square Deviation - RMSD (1.06 m and 4.26 m), Coefficient of Variation - CV (42.70% and 96.31%), and clustering (0 and 2 clusters), respectively. These findings indicate that the proposed approach can provide indicators for assessing feed bunk spatial patterns in PLF.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08928
PDF
-
MotionCore: A Latent Neural Simulator for Video Generation with Rigid-Body Dynamics
2026-11-06 02:45:37Zheng Wang, Zhengwei Gong, Yuanzhi Liang, Chi ZhangAbstract
Video generation models can produce highly realistic videos while generating physically inconsistent object motion. This limitation suggests that visual modeling alone may not provide a transferable representation of physical dynamics. We introduce MotionCore, a framework for learning physical dynamics via a learnable partial differential equation solver and focuses on rigid-body motion. We introduce a latent neural simulator learning to predict the evolution of object-level physical states from observed motion. Its predictions are then converted into spatially aligned latent controls for a controllable video diffusion model. The generator serves as a visual interface: it provides appearance and scene detail, while the learned dynamics model specifies the physical trajectory. To preserve this trajectory through the interface, MotionCore combines a diffusion-matching objective with a low-capacity decodability constraint on object identity and position. We evaluate MotionCore on public physical-consistency benchmarks and on paired data with known trajectories. Results indicate that MotionCore improves physical consistency and trajectory obedience in the evaluated rigid-body settings, while maintaining comparable visual quality. A controlled ablation protocol compares learned dynamics with an analytic prior and studies the choice of latent evolution processor.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08904
PDF
-
Lodos: A Lightweight Simulator Designed for Contact-Rich Interactions with Detailed Meshes
2026-11-06 01:54:44Onur Beker, Andreas Ren\'e Geist, Georg MartiusAbstract
In recent years, massively parallelized rigid-body simulation has played a central role in robotics research, enabling rapid progress in areas such as reinforcement learning, stochastic optimal control, and randomized smoothing-based trajectory optimization. Particularly in contact-rich settings, the scalability of such simulations in large part depends on well-optimized representations of collision geometry, often requiring a coarse approximation of the underlying surfaces using primitives such as spheres, capsules, cylinders, and boxes. Whenever the complexity of the surfaces or the precision demands of the application render such approximations insufficient, it is instead necessary to employ mesh-mesh collisions, which impose a significant reduction in throughput. This paper proposes a simulation framework designed from scratch to address this bottleneck, with novel routines for broadphase and narrowphase collision detection as well as the subsequent contact dynamics computation. As experimentally validated, the framework matches existing well-established simulators in terms of physical faithfulness, and can achieve approximately an order of magnitude higher throughput in the detailed mesh-mesh collision setting that it specializes in. The source code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08872
PDF
-
It Takes Two to Tangram: Multi-Agent Object Centric Reinforcement Learning for Assembly
2026-11-06 00:11:49Paul Knau{\ss}t, Kay Pompetzki, Nico Bohlinger, Niklas Funk, Cristiana de Farias, Rolf Findeisen, Jan PetersAbstract
Geometric assembly requires fine spatiotemporal coordination to place parts without causing collisions or deadlocks under tight clearances. To address this, we present an object-centric reinforcement learning framework that treats each part as an agent and learns a shared policy for continuous assembly control. A graph neural network represents the pieces, their target poses, and their spatial relationships, and predicts translational and angular velocities for each component. Per-agent proximal policy optimization with a centralized graph critic directly learns motion and temporal coordination within a single feedback policy. We study this formulation through planar Tangram assembly, where pieces must slide and rotate into a given configuration while remaining on the assembly surface. Procedural generation of target configurations and randomized initial arrangements support training and evaluation across diverse assembly problems. Our experiments isolate the roles of relational structure and multi-agent optimization, and compare learned control with sampling-based planning. We demonstrate concurrent assembly in simulation and transfer the policy to sequential execution on a real robot, as our object-centric formulation decouples learned assembly coordination from low-level physical control. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2611.08814
PDF
-
ChainFlow: Few-Step Latent Flow Matching for Speculative Decoding
2026-11-05 20:26:25Selim Aktas, Yusuf Erdem Erdem, Ahmed Zeer, Himmet Toprak Kesgin, Muzaffer Kaan Yuce, Mehmet Fatih AmasyaliAbstract
Speculative decoding has become a standard way to accelerate LLM inference: a lightweight drafter proposes tokens that the target verifies in one parallel pass. Existing drafters face trade-offs that limits their speedups: autoregressive drafters generate tokens one at a time, so drafting cost grows with draft length, while diffusion drafters generate tokens in parallel but predict each position independently, ignoring inter-token dependencies. We introduce ChainFlow, a new speculative decoding paradigm and the first flow-matching drafter conditioned on the target's hidden states. ChainFlow treats drafting as a short transport over hidden states, needing one or two flow steps instead of the many denoising steps of generation from noise. A variational autoencoder compresses these states so drafting cost barely grows with target size, lightweight feedback heads restore inter-token dependencies, and tree drafting raises acceptance. On Qwen3.5 models, at matched drafter size and training data, ChainFlow outperforms EAGLE-3 and DFlash in vLLM by 39% and 11%, respectively. These gains further widen as drafters are adapted to new languages sequentially. Our ablations cover drafter design and concurrent serving, and we open-source our code and drafter models.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08669
PDF
-
RoboFQE: Rollout-Free Evaluation of Visual Robot Policies from Offline Trajectories
2026-11-05 20:23:06Yunfu Deng, Sangwoo Shin, Brahma S. Pavse, Josiah P. HannaAbstract
Evaluating robot policies before deployment typically requires producing new trajectories through real-world execution, simulators, or learned world models. These rollout-based approaches impose infrastructure requirements; simulator and world-model evaluators additionally face prediction errors that can compound over the evaluation horizon. In this paper, we study off-policy evaluation as an alternative to rollout-based robot-policy evaluation methods. Specifically, we introduce RoboFQE, an evaluator that estimates the discounted expected return of a target policy from offline robot trajectories without estimating a behavior-policy density, combining fitted Q-evaluation with a pretrained vision foundation model and learned terminal success annotation to bridge the gap between standard OPE benchmarks and continuous-control visual manipulation. Controlled experiments across simulated and real-world manipulation tasks show that RoboFQE produces accurate discounted-return estimates and preserves policy rankings even on long-horizon manipulation tasks where video world-model evaluators are degraded by autoregressive prediction errors. Ablation experiments show that pretrained vision encoders substantially outperform from-scratch alternatives, particularly on long-horizon tasks, and that learned terminal success annotation enables evaluation without ground-truth reward labels with only slight reduction of accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.18699
PDF
-
Meituan-Robotics-0: A Vision-Language-Action Foundation Model for Desktop Manipulation
2026-11-05 18:55:42Meituan Robotics Team, Caicheng Wang, Chen Zhao, Chengpeng Jin, Duo Xu, Fengjiao Chen, Guanglu Wan, Heqing Yang, Jia Wang, Jiacong Zhou, Jie Hu, Jiyuan Ru, Lingfeng Zhang, Linjiang Huang, Manyuan Zhang, Ningchu Liu, Shijie Zhou, Si Liu, Shuo Li, Tianyi Zhang, Xi Zhang, Xin Chen, Xuezhi Cao, Xunliang Cai, Yanbin Zeng, Yang Yang, Yang Yi, Yanli Tan, Yifu Xu, Yimeng Jia, Yuchen Tang, Yuchen Xie, Yuxiang Zheng, Zerwei Chng, Zilong Huang, Zipeng Ye, Ziyuan Qin, Ziqin WangAbstract
We present Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied-agent system for stationary-base desktop manipulation. MR0 combines 147 million vision-language samples with 15,060 hours of curated robot trajectories spanning 12 embodiments. A three-stage training recipe aligns multimodal representations with robot behavior through discrete action-token pre-training, transfers these priors to continuous cross-embodiment control through flow-matching mid-training, and adapts the policy through real-world post-training. We introduce Rollback, which pairs replaced policy segments with human corrections to provide positive and negative supervision for CFG-DAgger without value learning or advantage labeling. A unified end-effector interface supports heterogeneous embodiments, while asynchronous action-chunk merging maintains smooth execution under variable inference latency. An event-driven agent maintains persistent task events and reassesses plans when progress or feasibility changes, enabling cross-task retrieval and conditional task resumption. MR0 achieves 93.6% success on RoboTwin 2.0 and ranks fifth in the RoboDojo VLA track. Under matched HG-DAgger post-training, MR0 achieves higher average success rate and progress score than $\pi_{0.5}$ across three real-robot tasks. On Ethernet insertion, CFG-DAgger trained with Rollback data reaches 70% success and a progress score of 0.90. Qualitative agent deployments demonstrate cross-task event retrieval and recovery from temporarily unsatisfied task conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08577
PDF
-
Label-Wording Augmentation in a Typed-Decision Encoder: Gains on Unfamiliar Words, Not on Abbreviations or Codes
Abstract
Typed-decision models score options that the caller supplies at request time, so their accuracy depends on label wording that the model's developer does not control. We compare two releases of a 307M-parameter multilingual cross-encoder, Ru-Jev, trained on thirteen Russian-language tasks; the later release adds an augmentation that presents labels in several surface forms. Holding questions fixed and varying only how eighteen routing labels are worded, we evaluate ten label vocabularies, produced by three separate processes and checked for overlap with the training data, with five candidates per question and, for eight of them, also with eighteen. On held-out vocabularies made of ordinary or borrowed words (English-derived jargon, office slang, department names), the augmented release is more accurate in every setting, by up to 0.24. Eleven of these fourteen gains survive a Holm correction (slang with eighteen candidates and descriptive sentences with five do not), and for jargon on all labels the label-level interval excludes zero in both settings. On abbreviations and opaque codes it gives no usable gain: on abbreviations it is not better, and worse on the clean slice, and on opaque codes both releases stay at or below chance once labels related to training options are removed. In most cells where accuracy rises, the risk-coverage area falls, but with eighteen candidates confident errors rise on jargon and slang. On two datasets neither release saw, accuracy moves by -8.4 and +5.6 points. We also report four evaluation hazards from comparing the two releases.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08439
PDF
