Xinyu Shao

Yifan Pu, Jixuan Ying, Qixiu Li et al.

Vision Transformers (ViTs) have become a universal backbone for both image recognition and image generation. Yet their Multi-Head Self-Attention (MHSA) layer still performs a quadratic query-key interaction for every token pair, spending the bulk of computation on visually weak or redundant correlations. We introduce Visual-Contrast Attention (VCA), a drop-in replacement for MHSA that injects an explicit notion of discrimination while reducing the theoretical complexity from O(N N C) to O(N n C) with n << N. VCA first distils each head's dense query field into a handful of spatially pooled visual-contrast tokens, then splits them into a learnable positive and negative stream whose differential interaction highlights what truly separates one region from another. The module adds fewer than 0.3M parameters to a DeiT-Tiny backbone, requires no extra FLOPs, and is wholly architecture-agnostic. Empirically, VCA lifts DeiT-Tiny top-1 accuracy on ImageNet-1K from 72.2% to 75.6% (+3.4) and improves three strong hierarchical ViTs by up to 3.1%, while in class-conditional ImageNet generation it lowers FID-50K by 2.1 to 5.2 points across both diffusion (DiT) and flow (SiT) models. Extensive ablations confirm that (i) spatial pooling supplies low-variance global cues, (ii) dual positional embeddings are indispensable for contrastive reasoning, and (iii) combining the two in both stages yields the strongest synergy. VCA therefore offers a simple path towards faster and sharper Vision Transformers. The source code is available at https://github.com/LeapLabTHU/LinearDiff.

Xinyu Shao, Keru Zhou, Guowei Huang et al.

Learning manipulation from few demonstrations requires visual priors that capture not only where to interact, but also how the interaction should begin; static priors such as segmentation masks encode only the former. We present KAM-WM, a framework that extracts a coarse directional interaction cue from a frozen latent video world model without rollout or world-model fine-tuning. KAM-WM queries a Flow Matching image-to-video backbone once and interprets its single-step latent velocity as a Kinematic Affordance Map (KAM), which provides task-conditioned interaction regions and coarse motion structure. A lightweight Perceiver compresses KAM into tokens that condition a diffusion policy together with RGB observations and proprioception. Across LIBERO and RoboTwin2.0, KAM-WM reaches 90.6% average success on LIBERO and achieves 65.7% and 22.4% success rates in the Easy and Hard settings on RoboTwin2.0, respectively. Controlled comparisons against a zero-order mask prior suggest that part of the gains comes from directional information beyond spatial localization alone. These results indicate that, in the evaluated settings, a frozen video model can provide a useful first-order visual prior for control without the test-time cost of future rollout.

Yanzhe Tang, Xinyu Shao, Yuxuan Hu et al.

While end-to-end Vision-Language-Action (VLA) models show promise in robotic manipulation, their monolithic paradigm inherently couples semantic reasoning and spatial control. This creates a severe alignment bottleneck, limiting precise target disambiguation in data-constrained imitation learning. To overcome this, we propose SVP-IL, a decoupled architecture that explicitly extracts spatial visual grounding from the action generation loop. By leveraging vision-language foundation models, we parse instructions into zero-shot geometric masks, translating language into explicit Spatial Visual Prompts (SVP). These priors are injected into a continuous action generator via a lightweight direct feature-level fusion mechanism. This integration provides explicit and uncorrupted spatial gradient guidance while ensuring highly stable optimization under low-data regimes. Extensive experiments demonstrate that SVP-IL significantly outperforms state-of-the-art VLAs and pure visuomotor baselines. Trained on as few as 50 to 100 demonstrations, SVP-IL improves average success rates on highly ambiguous language-conditioned tasks from 24.0% to 39.5%, achieving 67.8% on standard benchmarks. Real-world robotic experiments further validate its robustness and data efficiency in unstructured physical environments.