Vision-Language-Action (VLA) models are increasingly promising for robotic manipulation, yet their real-world deployment remains bottlenecked by high inference latency and unstable asynchronous execution. This challenge is particularly pronounced in flow-matching-based VLA models, where action decoding requires multiple iterative steps conditioned on the VLM context. While efficient inference methods improve control frequency and asynchronous methods reduce execution idle time, existing approaches often fail to jointly achieve low-latency inference and accurate, temporally consistent asynchronous execution. We introduce \textbf{FlashVLA}, a streaming action decoding framework that addresses both challenges in a unified formulation. FlashVLA maintains a streaming action buffer with multiple chunks at different noise levels and decodes them using chunk-wise causal attention. This design allows FlashVLA to produce one executable action chunk per inference step. Moreover, its chunk-wise autoregressive formulation implicitly preserves action continuity, enabling smooth asynchronous execution without extra future-state conditioning. Across extensive simulated and real-world experiments, FlashVLA substantially improves inference speed while maintaining strong task performance. It can achieve $\geq$30\,Hz control frequency on a single GPU with smooth asynchronous inference in real-world deployment.
3D Gaussian Splatting (3DGS) delivers real-time and high-fidelity rendering but remains challenged by unconstrained in-the-wild scenes, where drastic appearance variations and transient objects violate multi-view consistency. Existing methods are fundamentally limited by independent and discrete embeddings that struggle to capture continuous environmental changes or model spatially-varying local illumination. To address these limitations, we propose \textbf{WilLaGS}, a unified framework for robust 3D scene reconstruction and generative appearance synthesis under unconstrained settings. Specifically, we introduce a generative appearance model where a $β$-VAE learns a structured and continuous manifold of global appearance. Conditioned on the latent code, we construct a 3D neural appearance field that generates dynamic Tri-Plane features to encode spatially-varying local illumination effects. Furthermore, to suppress transient artifacts, we present a self-supervised perceptual masking mechanism that leverages a Teacher-Student (EMA) architecture to derive a stable scene consensus, robustly identifying inconsistent regions via perceptual discrepancies. Extensive experiments on multiple datasets demonstrate that \textbf{WilLaGS} achieves state-of-the-art performance in reconstruction quality and novel view appearance synthesis, while maintaining real-time rendering efficiency.
Research on omnidirectional seated locomotion for humanoids on passive chairs. Policies use proprioception only, outperforming standing in tracking. Analyzes regularization effects on convergence.
Vision-language-action (VLA) models have become a dominant paradigm for generalist embodied agents, demonstrating strong complex and long-horizon task completion in structured settings. Yet it remains an open question whether current VLA systems can benefit from more effective architectural design, scale to substantially larger and more heterogeneous data regimes, and achieve broader generalization across tasks and embodiments. To this end, we present GigaBrain-0.7, an embodied foundation model with substantially improved generalization across diverse robot embodiments. Specifically, GigaBrain-0.7 unifies understanding, prediction, and action through a three-system architecture, scales pretraining to over 37,000 hours of heterogeneous embodied data, and introduces one-stage alignment training that jointly optimizes vision-language understanding and multi-embodiment action generation. Compared with the preceding GigaBrain-0 series and prior state-of-the-art models including $π_{0.5}$, GigaBrain-0.7 achieves substantial improvements in foundation zero-shot capabilities, language-conditioned instruction following, and post-training task success rates. In particular, on our in-house Maker H01 platform and mainstream robot embodiments, GigaBrain-0.7 demonstrates strong task adaptability and completion ability across both home and industrial scenarios. All training code and pretrained model weights will be released.
ABot-N1 is a general visual-language navigation foundation model built on a slow-fast dual-system architecture: a 4B slow VLM reasoner emits explicit chain-of-thought plus dual pixel goals (Target Pixel + Affordance Pixel), while a 2B fast action expert decodes continuous SE(2) waypoints via QFormer action queries. The unified pixel-goal interface covers five tasks — point-goal, object-goal, POI-goal, instruction-following and person-following — in a single 30M-sample multi-task checkpoint, further aligned by GRPO post-training with format/target/safety rewards. Two closed-loop benchmarks are released (ABotN-PointBench and ABotN-POIBench). ABot-N1 sets new SOTA on all five benchmarks, boosting POI entrance arrival to 77.3% (+35.0 pp) and reaching 92.9%/95.4% outdoor/indoor point-goal SR, with full deployment on the TuTu quadruped running on a Jetson AGX Orin.
Zetta is a closed-loop embodied harness that keeps the base VLA frozen and evolves code-based runtime critics and recovery skills through three timescale-separated loops: action-frequency governance, rollout-batch failure diagnosis, and validation-gated skill updates. With the Z-Infra rollout infrastructure (20.6x throughput), it reaches 90.8% on LIBERO-Pro and 93.6% on RoboCasa, with zero-shot skill transfer and robotic Aha moments.
Vision-language-action (VLA) models leverage pretrained vision-language representations for robot control, yet simply adding historical frames does not reliably capture recent physical change. This is especially problematic in multi-stage manipulation, where visually similar states may require different actions depending on prior execution. To address this challenge, we present TemporalFlow-VLA, which learns compact execution history through physically grounded temporal supervision. Using recorded robot states, robot geometry, and calibrated cameras, we construct robot-surface temporal flow as a training-only target and supervise two execution-aligned temporal queries that provide structured history to the action expert. The geometric supervision path is not evaluated at deployment. TemporalFlow-VLA achieves 97.63 +/- 0.26% average success on LIBERO, including 96.60 +/- 0.87% on LIBERO Long, and 85.5%/84.2% Clean/Randomized success across 12 RoboTwin tasks. It shows its clearest advantage over prior methods on longer-horizon, multi-stage manipulation. Controlled history interventions show that action prediction depends on both historical content and temporal order. With asynchronous feature caching, temporal conditioning maintains single-frame-level server-side sampling latency without additional historical-encoding overhead. Overall, TemporalFlow-VLA provides a compact, physically grounded interface for exploiting ordered execution history without explicit motion estimation or geometric processing at deployment.
LAC is a general humanoid whole-body controller that simultaneously realizes commanded linear and angular compliance for wrenches applied to the upper body. Sampled force and couple events imposed on contact frames from human interaction data synthesize a large-scale compliant-response dataset; teacher-student RL then trains a single policy to track compliant motions under external wrenches, with sim and real experiments showing monotonic stiffness modulation and teleoperated loco-manipulation.
RoboNav-Arm lets an LLM decision agent orchestrate scene understanding, contextual memory and trajectory planning modules, adaptively selecting RRT-family planners with safety-inflated collision validation; collision-free success rates range from 100% to 83.3% across four clutter scenarios.
LeVJEPA performs video self-supervised pretraining with a single encoder, a single loss and one fixed hyperparameter (λ=0.02): an invariance loss plus SIGReg regularization provably rule out representation collapse, with no target encoder, predictor, stop-gradient or pixel reconstruction. It uses 5.6–20.8× less training compute than V-JEPA 2, leads by 7.6 points on ImageNet-1K under a FLOP-matched budget, and gets block-causal attention for free — paving the way to streaming perception and autoregressive world models.
Q-Planning freezes a large behaviour-cloning policy and trains an approximately one-billion-parameter off-policy Q function. At inference, Q performs single-step weighted averaging over BC action-chunk draws; during online self-improvement, both successful and failed rollouts update only Q. Ten iterations raise mean LIBERO success from 92.1% to 97.6%, while two bimanual real-robot tasks improve from 40%/25% to 90%/80%.
Zero-shot cross-task generalization, where a policy must execute manipulation tasks never seen during training, remains a central challenge in robot learning. In large language models, a novel task can be performed simply by specifying it in the context, without any parameter update. This form of in-context learning (ICL) turns generalization into a problem of task specification. To achieve cross-task generalization, we bring this paradigm to robotic manipulation, and argue that the natural task specification for manipulation is a human video: unlike language, it provides rich visual cues about the intended task evolution. We present Zero-WAM, a causal video-action model that executes unseen tasks by following in-context human video guidance. To address the scarcity of task-rich paired human-robot data, we propose an automatic pipeline that converts task-sampled robot trajectories into semantically matched human videos, yielding HumanGen, a dataset of 74.2K human-robot ICL pairs across 8.6K tasks. For model training, we further introduce an in-context future chunk prediction (IFP) objective that suppresses shortcuts learned from seen tasks and forces the policy to draw task information from the video prompt. On seven unseen tasks in RoboTwin 2.0 simulation, Zero-WAM achieves a 47.0% average success rate, an absolute improvement of 29.5 percentage points over the strongest video-action baseline. In real-world evaluations, it follows human video guidance to generalize to unseen task configurations involving multi-object scenes, long-horizon manipulation, and fine-grained insertion.
