{"total":11,"items":[{"citing_arxiv_id":"2606.27581","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SceneBot: Contact-Prompted General Humanoid Whole Body Tracking with Scene-Interaction","primary_cat":"cs.RO","submitted_at":"2026-06-25T22:13:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SceneBot conditions a humanoid tracking policy on motion references and contact labels, using reconstructed scene-interaction data to unify free-space locomotion with contact-rich manipulation and terrain tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22174","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulation","primary_cat":"cs.RO","submitted_at":"2026-06-20T18:02:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"OpenHLM is an empirical recipe yielding a whole-body humanoid VLA model that outperforms GR00T N1.6 and Ψ0 baselines on long-horizon tasks using less than half the demonstration time.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20990","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Duet: Dual-Robot Understanding via Efficient Teaching","primary_cat":"cs.RO","submitted_at":"2026-06-18T23:47:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"DUET pretrains collaborative policies on human-human VR demonstrations then fine-tunes on minimal robot teleoperation data, achieving equal or better performance than robot-only baselines with 5.4x faster collection across four tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.17833","ref_index":41,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning","primary_cat":"cs.RO","submitted_at":"2026-06-16T12:01:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"HumanoidArena is a new benchmark of 7 leg-critical HOI/HSI tasks that evaluates egocentric hierarchical whole-body policies in humanoids and finds performance is strongly conditioned on the low-level GMT used.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.12995","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GenHOI: Contact-Aware Humanoid-Object Interaction by Imitating Generated Videos without Task-Specific Training","primary_cat":"cs.RO","submitted_at":"2026-06-11T07:31:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"GenHOI reconstructs robot-object scenes, generates task videos from language and first-frame images, extracts contact constraints, optimizes reference trajectories, and executes them via closed-loop control for zero-shot humanoid-object interaction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09215","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation","primary_cat":"cs.RO","submitted_at":"2026-06-08T08:50:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MotionWAM conditions a policy on intermediate features from a video world model to predict unified whole-body motion tokens, enabling real-time humanoid loco-manipulation that outperforms VLA baselines by over 30% on nine Unitree G1 tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08548","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"OASIS: From Simulation Data Collection to Real-World Humanoid Loco-Manipulation","primary_cat":"cs.RO","submitted_at":"2026-06-07T10:01:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"OASIS generates scalable simulation data for humanoid loco-manipulation via 3D generative asset reconstruction and domain randomization, yielding a policy with higher zero-shot real-world success than real-robot teleoperation data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08278","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation","primary_cat":"cs.RO","submitted_at":"2026-06-06T17:55:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SIMPLE is a new large-scale simulation benchmark for humanoid loco-manipulation that integrates accurate dynamics and photorealistic rendering and demonstrates policy transfer from simulation to physical robots.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06493","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers","primary_cat":"cs.RO","submitted_at":"2026-06-04T17:59:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HANDOFF is a distilled mixture-of-experts humanoid whole-body controller that follows a compact task-space interface, matches SOTA velocity tracking, provides large manipulation workspace on Unitree G1, and supports VLM-driven agentic planning with no task-specific data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06194","ref_index":53,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ActiveMimic: Egocentric Video Pretraining with Active Perception","primary_cat":"cs.RO","submitted_at":"2026-06-04T14:01:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ActiveMimic pretrains on egocentric human video by recovering and modeling active camera motion as viewpoint actions, matching robot-data pretraining performance on real-world tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01458","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World","primary_cat":"cs.RO","submitted_at":"2026-05-31T21:36:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LEGS shows synthetic data from a 3DGS-mesh hybrid simulator trains VLA policies for humanoid pick-and-place that match or exceed human teleoperation performance across multiple backbones and tasks while enabling low-cost robustness to appearance shifts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}