{"arxiv_id":"2609.21474","title":"MT-WAM: Reorienting the One-Pass Predictive Representation Toward Action Generation","abstract":"Fast-WAM shows that video-action co-training improves control without generating future video at inference, making the representation from a single video diffusion Transformer forward central to action generation. However, future-observation prediction does not explicitly prioritize the future dynamics and visual structure needed for control. We present MT-WAM, which retains the original training objectives and adds complementary supervision for future two-dimensional point trajectories and visual features. A lightweight dual-stream branch copied from the video backbone's final blocks provides target-specific processing, while a structured attention mask prevents cross-stream attention. Motion-stream tokens supply additional dynamics conditions to the action expert. Future visual-feature prediction provides supervision in a feature space that captures object and spatial structure. This supervision trains the video backbone to provide more informative visual context for action generation under changing visual conditions, without adding visual-feature-stream tokens to action conditioning. At inference, MT-WAM uses video and motion caches computed once per replan and skips future-video prediction. Without additional embodied policy pretraining, MT-WAM achieves 98.2% success on LIBERO and 73.7% on LIBERO-Plus, exceeding Fast-WAM by 23.8 percentage points on the latter. On RoboTwin 2.0 Clean2Rand, Random success increases from 6.30% to 19.40%; across four real-world tasks, average success increases from 67.0% to 77.8%.","primary_cat":"cs.CV","cross_cats":["cs.RO"],"submitted_at":"2026-09-18T08:23:15+00:00","latest_version":1,"source":"arxiv","source_label":"arXiv","source_url":null,"has_pdf":true,"has_source":false,"verdict":"CONDITIONAL","confidence":"MODERATE","one_line_summary":"MT-WAM improves Fast-WAM by supervising its video backbone with future point trajectories and visual features during training, raising LIBERO-Plus success from 49.9% to 73.7% with no future-video generation at inference.","novelty_score":5.0,"correctness_risk":"medium","formal_verification":"none","upvotes":0,"downvotes":0,"pith_score":0.0,"inbound_count":1,"_links":{"html":"https://pith.science/paper/2609.21474","verdict":"/api/v1/verdicts/2609.21474"}}