Zuojin Tang

Zuojin Tang, Bo Sun, Tongwei Ma et al. · pku

The annotation of 3D datasets is required for semantic-segmentation and object detection in scene understanding. In this paper we present a framework for the weakly supervision of a point clouds transformer that is used for 3D object detection. The aim is to decrease the required amount of supervision needed for training, as a result of the high cost of annotating a 3D datasets. We propose an Unsupervised Voting Proposal Module, which learns randomly preset anchor points and uses voting network to select prepared anchor points of high quality. Then it distills information into student and teacher network. In terms of student network, we apply ResNet network to efficiently extract local characteristics. However, it also can lose much global information. To provide the input which incorporates the global and local information as the input of student networks, we adopt the self-attention mechanism of transformer to extract global features, and the ResNet layers to extract region proposals. The teacher network supervises the classification and regression of the student network using the pre-trained model on ImageNet. On the challenging KITTI datasets, the experimental results have achieved the highest level of average precision compared with the most recent weakly supervised 3D object detectors.

Zuojin Tang, Haoyun Liu, Xinyuan Chang et al.

Vision-language-action (VLA) models remain constrained by the scarcity of action-labeled robot data, whereas action-free videos provide abundant evidence of how the physical world changes. Latent action models offer a promising way to extract such priors from videos, but reconstruction-trained latent codes are not necessarily suitable for policy generation: they may predict future observations while lacking the structure needed to be reused or generated coherently with robot actions. We introduce ALAM (Algebraic Latent Action Model), an Algebraically Consistent Latent Action Model that turns temporal relations in action-free video into structural supervision. Given frame triplets, ALAM learns latent transitions that are grounded by reconstruction while being regularized by composition and reversal consistency, encouraging a locally additive transition space. For downstream VLA learning, we freeze the pretrained encoder and use its latent transition sequences as auxiliary generative targets, co-generated with robot actions under a joint flow-matching objective. This couples structured latent transitions with flow-based policy generation, allowing the policy to exploit ALAM's locally consistent transition geometry without requiring latent-to-action decoding. Representation probes show that ALAM reduces additivity and reversibility errors by 25-85 times over unstructured latent-action baselines and improves long-horizon cumulative reconstruction. When transferred to VLA policies, ALAM raises the average success rate from 47.9% to 85.0% on MetaWorld MT50 and from 94.1% to 98.1% on LIBERO, with consistent gains on real-world manipulation tasks. Ablations further confirm that the strongest improvements arise from the synergy between algebraically structured latent transitions and joint flow matching.

Zuojin Tang, Shengchao Yuan, Xiaoxin Bai et al.

Vision-language-action (VLA) models increasingly rely on auxiliary world modules to plan over long horizons, yet how such modules should be parameterized on top of a pretrained VLA remains an open design question. Existing world-model-augmented VLAs typically pass the per-frame visual stream into the world module at high visual bandwidth and treat its rollout as a side product of action prediction; under a constrained adaptation budget on a frozen backbone, this leaves both the per-frame representation and the latent action coupling under-examined. We introduce OneWM-VLA, which compresses each view into a single semantic token per frame through an Adaptive Attention Pooling, and produces the resulting latent stream and the action trajectory under a single flow-matching objective rather than connecting them through a separate decoder. Empirically, we find that per-frame visual bandwidth can be reduced to a single token without compromising long-horizon performance under our setup. Trained with 14.71M LoRA parameters on a $π_0$ (2B) backbone, OneWM-VLA improves the average success rate from 47.9% to 61.3% on MetaWorld~MT50, reaches 95.6% on LIBERO-Long (vs.85.2% for $π_0$), and reaches 60.0% on the long-horizon deformable task Fold Cloth on a real Piper arm (vs.20.0% for $π_0$).

Ronghan Chen, Yandan Yang, Zuojin Tang et al.

Mobile manipulation is a key capability for general-purpose robots, yet remains challenging for current embodied learning methods. VLA policies are typically reactive and lack explicit world modeling, while existing World Action Models (WAMs) are still poorly aligned with the structure of mobile manipulation: they operate on coarse video chunks, model entangled navigation-manipulation actions, and train inverse dynamics under supervision that does not match autoregressive inference. As a result, they often miss fine-grained contact dynamics, suffer from action-distribution conflicts, and accumulate errors over long-horizon rollouts. We propose ABot-M0.5, a new WAM built on the insight that mobile manipulation requires alignment at three levels: temporal granularity, action space, and train-test consistency. To align temporal granularity, we introduce intermediate latent actions that capture local visual state transitions and serve as an bridging action space between video latents and embodiment-specific controls. To align action space, we design a dual-level Mixture-of-Transformers architecture that disentangles both modality representations and heterogeneous action subspaces such as base movement and arm manipulation. To align inference conditions, we propose the dream-forcing training strategy that progressively trains inverse dynamics on model-predicted videos, improving train-test alignment and robustness during autoregressive prediction. Experiments on challenging mobile and fine-grained manipulation benchmarks demonstrate that ABot-M0.5 achieves state-of-the-art performance in both long-horizon task success and finegrained control accuracy. These results highlight the critical importance of granularity-aligned, action-disentangled, and inference-consistent world-action modeling.

Zuojin Tang, Bin Hu, Chenyang Zhao et al.

Recent large pretrained models such as LLMs (e.g., GPT series) and VLAs (e.g., OpenVLA) have achieved notable progress on multimodal tasks, yet they are built upon a multi-input single-output (MISO) paradigm. We show that this paradigm fundamentally limits performance in multi-input multi-output (MIMO) scenarios, where parallel task execution is required. In MISO architectures, tasks compete for a shared output channel, creating mutual exclusion effects that cause unbalanced optimization and degraded performance. To address this gap, we introduce MIMO-VLA (VLASCD), a unified training framework that enables concurrent multi-task outputs, exemplified by simultaneous dialogue generation and decision-making. Inspired by human cognition, MIMO-VLA eliminates interference between tasks and supports efficient parallel processing. Experiments on the CARLA autonomous driving platform demonstrate that MIMO-VLA substantially outperforms state-of-the-art MISO-based LLMs, reinforcement learning models, and VLAs in MIMO settings, establishing a new direction for multimodal and multitask learning.