{"total":14,"items":[{"citing_arxiv_id":"2606.12814","ref_index":4,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Stubborn: A Streamlined and Unified Reinforcement Learning Framework for Robust Motion Tracking and Fall Recovery for Humanoids","primary_cat":"cs.RO","submitted_at":"2026-06-11T02:13:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Stubborn introduces a unified RL framework with yaw-aligned representation, Bernoulli probabilistic termination, and adaptive sampling for robust humanoid motion tracking and fall recovery.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06953","ref_index":30,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"LIMMT: Less is More for Motion Tracking","primary_cat":"cs.RO","submitted_at":"2026-06-05T06:33:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A data-centric approach shows that less than 3% of AMASS motion data, filtered by physics feasibility, diversity, and complexity, yields better humanoid tracking policies than the full dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.04829","ref_index":19,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"M3imic: Learning a Versatile Whole-Body Controller for Multimodal Motion Mimicking","primary_cat":"cs.RO","submitted_at":"2026-06-03T12:52:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"M3imic unifies heterogeneous motion modalities via encoders into a shared latent space for a single RL-trained whole-body controller achieving high sim success and sim-to-real transfer on Unitree G1.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03985","ref_index":39,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking","primary_cat":"cs.RO","submitted_at":"2026-06-02T17:59:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Humanoid-GPT is a causal Transformer pre-trained on a unified billion-scale motion dataset that tracks dynamic behaviors with zero-shot generalization to unseen motions and tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03536","ref_index":39,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Bionic Human-Motion Style Transfer for Physically Executable Whole-Body Control of Humanoid Robots","primary_cat":"cs.RO","submitted_at":"2026-06-02T11:59:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A multi-condition latent diffusion model transfers human motion styles to diverse humanoid robot contents with physics regularizations, achieving 96% success in real-robot trials on Unitree G1.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19981","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"CEER: Compliant End-Effector and Root Control as a Unified Interface for Hierarchical Humanoid Loco-Manipulation","primary_cat":"cs.RO","submitted_at":"2026-05-19T15:23:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CEER proposes a compliant end-effector and root control interface that unifies loco-manipulation for humanoids via a distilled low-level policy and hierarchical planners.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05110","ref_index":23,"ref_count":2,"confidence":0.9,"is_internal_anchor":true,"paper_title":"LineRides: Line-Guided Reinforcement Learning for Bicycle Robot Stunts","primary_cat":"cs.RO","submitted_at":"2026-05-06T16:43:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LineRides enables commandable bicycle robot stunts via line-guided RL that uses spatial guidelines, a tracking margin for feasibility, distance-based progress, and sparse key-orientations.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[3], [12], [13], while wheeled platforms have also learned diverse and agile motion skills [14]-[18]. Beyond skill learn- ing, legged robots have achieved robustness across various terrains [19], [20] and even exhibited high-speed running near their physical limits [21], [22]. More recently, bipedal robots have also demonstrated the ability to acquire a wide range of agile behaviors [23]-[27]. Here, we highlight how diverse efforts have been required to enable robots to learn agile behaviors. For instance, to train a relatively simplejumpskill, [1] introduced a virtual obstacle and penalized the robot's body overlap with it to induce a jumping motion. [2] designed a phase-based reward that distinguishes between pre-landing and post-landing stages,"},{"citing_arxiv_id":"2604.17807","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Re$^2$MoGen: Open-Vocabulary Motion Generation via LLM Reasoning and Physics-Aware Refinement","primary_cat":"cs.CV","submitted_at":"2026-04-20T04:59:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Re²MoGen generates open-vocabulary motions via MCTS-enhanced LLM keyframe planning, pose-prior optimization with dynamic temporal matching fine-tuning, and physics-aware RL post-training, claiming SOTA performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14834","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Switch: Learning Agile Skills Switching for Humanoid Robots","primary_cat":"cs.RO","submitted_at":"2026-04-16T10:11:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Switch enables humanoid robots to perform agile, seamless transitions between locomotion skills via a kinematic skill graph, DRL tracking policy, and real-time graph-search scheduler.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12909","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Tree Learning: A Multi-Skill Continual Learning Framework for Humanoid Robots","primary_cat":"cs.RO","submitted_at":"2026-04-14T15:57:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Tree Learning uses root-branch parameter inheritance and multi-modal adaptation to enable continual multi-skill learning in humanoid robots, achieving higher rewards and 100% retention versus joint training in Unity simulations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.15827","ref_index":40,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching","primary_cat":"cs.RO","submitted_at":"2026-02-17T18:59:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A modular system uses motion matching to compose long-horizon human skill chains, trains RL experts, and distills them into a depth-based policy that lets a Unitree G1 humanoid autonomously climb, vault, and roll over obstacles up to 1.25 m tall.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.11758","ref_index":65,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model","primary_cat":"cs.RO","submitted_at":"2026-02-12T09:34:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HAIC enables robust humanoid interactions with underactuated objects by predicting their dynamics from proprioceptive history and using a world model for adaptive control.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.03205","ref_index":42,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"HUSKY: Humanoid Skateboarding System via Physics-Aware Whole-Body Control","primary_cat":"cs.RO","submitted_at":"2026-02-03T07:18:01+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HUSKY combines humanoid-skateboard dynamics modeling with adversarial motion priors and physics-guided lean-to-steer strategies to achieve real-world stable skateboarding on a humanoid robot.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2508.08241","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion","primary_cat":"cs.RO","submitted_at":"2025-08-11T17:55:26+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"BeyondMimic combines compact motion tracking with a unified guided latent diffusion model to master diverse agile behaviors from human demos and solve unseen downstream tasks via test-time classifier guidance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}