Dan Zhao

Guoyang Zhao, Quanhao Qian, Gongjie Zhang et al.

Proprioception is fundamental to robotic manipulation, yet standard fusion methods often treat it as an isolated vector lacking explicit alignment with visual tokens. Without a direct correspondence between 3D kinematics and 2D feature maps, manipulation policies struggle to ground the robot's state within the scene, frequently underperforming even vision-only baselines. To address this, we introduce GeoProp, a lightweight, plug-and-play adapter that aligns proprioception with vision through explicit geometric grounding and spatial feature sampling. GeoProp projects the robot state onto the image plane to sample localized visual features, constructing a grounded state token. It then injects state-derived spatial priors into the corresponding visual features via FiLM modulation. To capture motion intent, GeoProp further samples features at a short-horizon predicted coordinate derived from recent kinematics, providing look-ahead visual context. Across 67 tasks, GeoProp improves Diffusion Policy by 8.7% on 63 simulation tasks and pi_0 by 4.0% on the RoboTwin subset, and yields a 10.6% average gain across both policy families in the real world, while adding only 2-3% to the parameter count. These results demonstrate that GeoProp is a simple yet high-impact inductive bias for generalist embodied policies. Project page: https://alibaba-damo-academy.github.io/GeoProp/.

Baogang Song, Zhongshu Zhao, Qianrong Zheng et al.

Biometric template protection (BTP) must secure stored templates while tolerating intra-class variations. Existing methods rely on protected-domain similarity matching, error correction, or predefined-template mappings, potentially retaining exploitable similarity structures, introducing helper-data risks, depending on artificial targets, or coupling protection to specific modalities. Storing only cryptographic hash digests eliminates directly comparable representations and conceals pre-hash templates, but hash-based exact-match verification requires genuine samples to generate identical intermediate templates before hashing. Identity classification is naturally suited to this requirement because it maps variable biometric samples to stable and discriminative identity-level outputs. Based on this insight, we propose Multiple Permuted-Label Classifier Encoding (MPLCE). Through classifier-specific label permutations, MPLCE assigns each identity different labels across multiple classifiers. The predicted labels are encoded and concatenated to form an intermediate template, preventing repeated encodings of a single identity label and enlarging the effective candidate space while preserving classification consistency. The template is randomized with an application-specific XOR string and cryptographically hashed, enabling exact-match verification without error correction codes or biometric-dependent helper data. Using modality-specific classifiers, MPLCE retains the same template generation and protection procedure across modalities. On four face and two iris datasets, MPLCE achieves competitive performance, including a GAR of 98.61\% at a FAR of 5.51\(\times\)10\textsuperscript{-5}\% on YTF and a GAR of 99.10\% at a FAR of 0.00\% on CASIA-Iris-Lamp. Security analyses and attack evaluations support its irreversibility, revocability, and unlinkability under the threat model.

Xin Cheng, Xingkai Yu, Chenze Shao et al.

Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel drafters efficiently propose long token sequences in a single forward pass, they suffer from rapid acceptance decay due to a lack of inter-token dependencies. Furthermore, indiscriminately verifying these extended blocks wastes critical batch capacity on tokens with high rejection risks, severely degrading throughput in high-concurrency serving systems. We introduce DSpark, a speculative decoding framework that unifies high-throughput parallel generation with adaptive, load-aware verification. To maintain draft quality, DSpark utilizes a semi-autoregressive architecture, coupling a parallel backbone with a lightweight sequential module, to introduce intra-block dependency modeling and mitigate suffix decay. To optimize system efficiency, DSpark employs confidence-scheduled verification, dynamically tailoring the verification length for each request based on estimated prefix survival probabilities and engine-specific throughput profiles. On offline benchmarks across diverse domains, DSpark substantially improves the accepted length over state-of-the-art autoregressive and parallel drafters. When deployed within the DeepSeek-V4 serving system under live user traffic, DSpark successfully mitigates verification waste. Compared to the established production baseline (MTP-1), DSpark accelerates per-user generation speeds by 60 to 85 percent at matched throughput levels. More importantly, by preventing severe throughput degradation under strict interactivity constraints, it enables performance tiers that were previously unattainable, shifting the Pareto frontier of our serving system.

Haoyu Zhao, Xingyue Zhao, Siteng Huang et al.

Robotic manipulation in the open world requires not only recognizing what a scene looks like, but also anticipating how its 3D structure moves under interaction. We argue that synchronized RGB, depth, and optical flow, namely RGB-DF, provide a physically grounded representation that captures the underlying 4D dynamics of a scene. Compared to 2D pixel videos, this multi-modal synergy aligns visual appearance with geometric structure and temporal motion, creating a representation space significantly closer to the low-level end-effector actions demanded by robotic systems, thereby narrowing the gap between world prediction and policy learning. Building on this insight, we introduce RynnWorld-4D, a generative model that co-produces future RGB frames, depth maps, and optical flow from a single RGB-D image and a language instruction within one unified diffusion process. This 4D world model features a tri-branch architecture that integrates cross-modal attention with frame-wise 3D RoPE, ensuring that appearance, geometry, and motion evolve consistently. To supply training data at scale, we curate Rynn4DDataset 1.0, a massive dataset of over 254.4 million frames across egocentric human and robotic manipulation videos with high-quality pseudo-labels for depth and optical flow. We further propose RynnWorld-4D-Policy, an inverse dynamics head that consumes the internal 4D representations of RynnWorld-4D in a single forward pass, bypassing expensive multi-step denoising, to output robot actions in a closed-loop manner. Experiments show that RynnWorld-4D produces temporally and spatially coherent 4D predictions, and that RynnWorld-4D-Policy achieves state-of-the-art performance on real-world dexterous bimanual manipulation tasks, particularly excelling in tasks demanding spatial precision and temporal coordination.

Haoyu Zhao, Xingyue Zhao, Hangyu Li et al.

Scaling robot learning requires massive, diverse trajectory data, yet collection is currently bottlenecked by physical teleoperation, where every demonstration binds operator time to specific hardware and workspaces. We introduce digital teleoperation, a paradigm that decouples data collection from physical constraints by replacing the real robot with a generative world model. In this framework, an operator's hand-pose stream drives a robot-centric generative world model to synthesize high-fidelity egocentric videos from a single reference image. The recorded pose stream serves as an embodiment-agnostic action label transferable to any target robot via standard retargeting, yielding complete state-action trajectories for imitation learning independent of physical hardware. We instantiate this paradigm in RynnWorld-Teleop, a system that integrates depth-aware skeletal conditioning, progressive human-to-robot training on a video Diffusion Transformer, and streaming autoregressive distillation. This pipeline compresses the generative process into a single-pass inference, enabling 40+ FPS, real-time interactive generation on a single H100 GPU. Policies trained exclusively on RynnWorld-Teleop-generated data achieve effective zero-shot Sim2Real transfer across dexterous and diverse bimanual tasks. Moreover, augmenting real-world datasets with our digitally teleoperated data consistently improves success rates, demonstrating that RynnWorld-Teleop serves as a high-fidelity, scalable data engine for the next generation of robotic agents.

Wenhao Li, Xueying Jiang, Quanhao Qian et al.

Real-world robot deployment rarely maintains the training-stage camera setup, where cameras often experience repositioning or remounting depending on actual scenarios. Existing view-robust Vision-Language-Action (VLA) policies tolerate such camera variations only when the camera extrinsics are explicitly provided, making them fragile and hard to use especially when view robustness is critical. We argue that the policy should not be told where the camera is, but rather figure it out by itself. To this end, we introduce Camera-Centric VLA (CamVLA), a new VLA model that decouples manipulation controls from camera geometry by predicting (i) a camera-centric end-effector action expressed in the local camera frame, and (ii) a 6-DoF hand-eye matrix relating cameras to the robot base. A deterministic geometric transformation composes the two predictions into a robot base-frame action. This disentangles how I should move in pose-independent camera-centric action generation from where I am looking from in camera-perspective geometric grounding. The resulting policy is calibration-free, depth-free, and single-view, requiring only a single monocular RGB image as the visual observation and task instruction at deployment. Evaluations in both simulation and real-world robot data show that CamVLA consistently improves success rates across diverse unseen viewpoints. Project page: https://alibaba-damo-academy.github.io/CamVLA/.

Songjun Tu, Chengdong Xu, Qichao Zhang et al.

Skill memories can improve agentic reinforcement learning by reusing past experience as textual guidance, but retrieved skills are not oracular: they may help in one state while misleading the same policy in another. This makes the common privileged-teacher assumption fragile, namely that a skill-conditioned prompt can be treated as a fixed teacher for the no-skill prompt. We introduce UCOB, a framework for learning to utilize and evolve agentic skills via credit-aware on-policy bidirectional self-distillation. UCOB treats skill-conditioned and no-skill prompts as two on-policy context views of the same model, compares their return-to-go within the same task and anchor state, and uses the higher-return view as the local teacher. This local credit signal internalizes useful skill-conditioned behavior, corrects misleading skill usage, and guides task/state skill memory updates, utility-aware retrieval, and reflection self-training. Experiments on agentic tasks, including ALFWorld, WebShop, and Search-QA, show that UCOB outperforms skill-free RL, skill-memory baselines, and self-distillation methods across model scales, with up to 23.5 and 18.0 point gains over SOTA baselines on ALFWorld and WebShop. Ablations and analyses further validate its core mechanisms and efficiency.

Dongdong Zhao, Jinrong Hu, Changtian Song et al.

Black-box membership inference attacks (MIAs) rely on target-model queries to infer whether candidate samples were used for training. However, membership signals are highly non-uniform across samples: some candidate samples support strong member/non-member separability, whereas many others provide little useful signal. Consequently, indiscriminate querying can incur substantial query cost and increase query-induced exposure, with limited marginal benefit for inference. This raises a key question: which candidate samples are worth querying for black-box MIAs? To address this question, we propose PSS-MIA, a pre-query sample selection framework which can be embedded with any existing MIA methods. PSS-MIA proceeds in two stages: it first ranks candidate samples and selects a subset expected to support stronger membership inference, then queries the selected samples and uses the returned outputs for an existing black-box MIA, thereby reducing query cost and query-induced exposure. In the first stage, we propose Loss-Gap Ranking (LGR), which ranks candidate samples by estimating the strength of their membership signal using loss gaps computed from reference models. Experiments on CIFAR-10, CIFAR-100, and CINIC-10 with five representative black-box MIA methods demonstrate that PSS-MIA with LGR consistently outperforms all other compared methods. Moreover, under a 0.1% FPR constraint, PSS-MIA can save at least 83.1%, 60.6%, and 80.4% of the query budget for the three datasets, respectively.

Zekai Zhang, Jiahao Li, Jie Zhang et al.

While text-to-image (T2I) models have achieved remarkable progress, they struggle with real-world requests that are often underspecified, implicit, or dependent on up-to-date knowledge. We identify this challenge as the Context Gap: the mismatch between the user context and the sufficient generation context for T2I models. To bridge this gap, we propose Qwen-Image-Agent, a unified agentic framework that integrates plan, reason, search, memory and feedback in a context-centric manner. Qwen-Image-Agent treats user input as partial context and progressively constructs the generation context through Context-Aware Planning and Context Grounding. Specifically, Context-Aware Planning identifies missing context and plans how it should be acquired and used, while Context Grounding gathers this context from reason, search, memory, and feedback. To evaluate agentic image generation, we further introduce Image Agent Bench (IA-Bench), a benchmark covering four core image agent capabilities: Plan, Reason, Search, and Memory. Experiments on IA-Bench, Mindbench and WISE-Verified show that Qwen-Image-Agent outperforms strong baselines and achieves state-of-the-art performance.

Dongfang Zhao

Graph-based approximate nearest neighbor (ANN) indexes on the GPU are originally built for static collections and must reconstruct the affected window to absorb any update, while the dynamic graph indexes that update incrementally run on the CPU and cannot exploit GPU parallelism. This paper presents a new ANN index, namely ETALE (Evolving Topology with Accelerated Lock-free Execution), which is among the first GPU-native graph ANN indexes to support streaming insertion and deletion without a global rebuild. The core of ETALE is a lock-free copy-on-write slab graph whose deletion state and adjacency share a single atomically published word, which yields a provable deletion-monotonicity invariant together with a bounded reclaim of GPU memory that is sublinear in accumulated deletions. We have implemented ETALE in CUDA and evaluate it on five diverse multimodal datasets against four state-of-the-art indexes: Tagore (GPU static, SIGMOD'26), DIGRA (CPU dynamic, SIGMOD'26), CAGRA (GPU static, ICDE'24), and HNSW (CPU dynamic, TPAMI'20). Under continuous churn, ETALE maintains the index in hundreds of milliseconds per round at recall above $0.95$, which is $4.8$--$8.8\times$ faster than CAGRA's per-window rebuild, $1.8$--$2.5\times$ faster than the more recent Tagore, and $3.3$--$147\times$ faster than the CPU dynamic indexes. In addition, the memory footprint of ETALE stays bounded where tombstone-only systems grow indefinitely.

Zhen Li, Xin Huang, Liang Wang et al.

LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone models slow down embedding inference, while high-dimensional full-precision embeddings impose substantial storage and bandwidth overhead on large-scale indexes. In this paper, we present BITEMBED, an extreme low-bit framework for LLM-based text embedding that jointly targets encoding efficiency and vector storage. BITEMBED converts pretrained LLM backbones into BitNet-style embedding encoders with ternary weights, quantized activations, and lightweight normalization refinement. The converted model is adapted to representation learning through continual contrastive pre-training, followed by supervised contrastive fine-tuning with both similarity-distribution distillation and attention-relation distillation from a full-precision teacher. Beyond quantizing the backbone, BITEMBED further trains output embeddings to support multiple storage precisions meeting different storage needs in various scenarios. Experiments on MMTEB (eng, v2) with Qwen3-0.6B and Gemma3-270M show that BITEMBED is largely comparable to full precision teacher embedders. Moreover, BITEMBED flexibly obtains text embeddings of various precisions, achieving a trade-off between performance and storage cost.

Shiguo Lian, Kai Wang, Zhaoxiang Liu et al.

Large model inference optimization serves as a key foundation for supporting the scalable, low-cost, and highly stable operation of large model services. Centered on token-oriented inference optimization technology, this paper proposes for the first time a four-layer technical architecture consisting of Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion. It systematically reviews the key technologies and current industry status across these four levels and analyzes the application value of related technologies in real-world business scenarios. This paper provides a practical technical path for reducing token production costs, improving token service efficiency, ensuring the stability of token supply, and driving the transition of large model services from being merely callable to being operable.

Changyi Lin, Ding Zhao

We present ART-Glove, an articulated tactile glove designed to capture contact-grounded dexterous demonstrations while preserving human dexterity. ART-Glove makes hand-side contact geometry explicit with 16 rigid functional surfaces covering the fingers, thumb, and palm. Twenty-two anatomically aligned joints connect these surfaces and allow them to follow human hand motion during dexterous manipulation. Encoder-based sensing tracks surface motion, while dense piezoresistive tactile sensing records contact over the same surfaces. The complete system captures synchronized 22-DoF joint measurements and 2048-taxel tactile measurements at 120 Hz. We evaluate ART-Glove across experiments on motion freedom, joint sensing, tactile sensing, and contact-rich interaction capture, demonstrating its ability to preserve human dexterity while recording contact-grounded information that can support downstream dexterous robot learning.