VIGIL decouples world-state completion from terminal commitment in embodied agents, exposing up to 19.7 pp gaps in benchmark success despite comparable execution across 20 models.
hub Mixed citations
MiMo-Embodied: X-Embodied Foundation Model Technical Report
Mixed citation behavior. Most common role is background (67%).
21
Pith papers citing it
Background
67% of classified citations
abstract
We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in both Autonomous Driving and Embodied AI. MiMo-Embodied sets new records across 17 embodied AI benchmarks in Task Planning, Affordance Prediction and Spatial Understanding, while also excelling in 12 autonomous driving benchmarks across Environmental Perception, Status Prediction, and Driving Planning. Across these tasks, MiMo-Embodied significantly outperforms existing open-source, closed-source, and specialized baselines. Our results indicate that through multi-stage learning, curated data construction, and CoT/RL fine-tuning, these two domains exhibit strong positive transfer and mutually reinforce one another. We provide a detailed analysis of our model design and training methodologies to facilitate further research. Code and models are available at https://github.com/XiaomiMiMo/MiMo-Embodied.
hub tools
citation-role summary
background 4
baseline 2
citation-polarity summary
years
2026 21representative citing papers
RAG-KT frames cross-platform knowledge tracing as context-constrained LLM inference by building unified multi-source context via Question Group abstractions and retrieving complementary reliable context for grounded predictions and interpretable diagnosis.
Vesta is a unified embodied generalist model that outperforms specialist baselines by over 20% on average and improves real-world robotic task success by over 35%.
Training a 4B vision-language model to emit identity-tracked, visually grounded reasoning anchors improves embodied spatial, multi-view, and pointing task performance over 7B baselines.
Introduces a new diagnostic benchmark and million-scale reasoning corpus showing that training on explicit causal traces improves next-state prediction in embodied planning, with reported gains from data scaling.
OneVLA is a unified VLA model using a shared action head and multi-stage progressive training with CoT fine-tuning that reports state-of-the-art results on both navigation and manipulation in simulation and real-world settings.
A co-evolutionary VLM-VGM loop on 500 unlabeled images raises planner success by 30 points and simulator success by 48 percent while beating fully supervised baselines.
In LVLMs, attention can be replaced by random Gaussian weights with little or no performance loss, indicating that current models get lost in attention rather than efficiently using visual context.
OneVL achieves superior accuracy to explicit chain-of-thought reasoning at answer-only latency by supervising latent tokens with a visual world model decoder that predicts future frames.
State-of-the-art vision-language-action models catastrophically fail dynamic embodied reasoning due to lexical-kinematic shortcuts, behavioral inertia, and semantic feature collapse caused by architectural bottlenecks, as shown by the new BeTTER benchmark with real-world validation.
A routing framework maintains three parallel 3D feature streams for LiDAR, 4D radar, and fusion, with a lightweight router using weather prompts to dynamically weight them and auxiliary supervision to keep branches distinct, achieving SOTA on K-Radar.
FASTER adds a Horizon-Aware Schedule to flow VLAs that compresses immediate-action denoising to one step while keeping long-horizon trajectory quality, lowering real-robot reaction latency.
PALM improves long-horizon robotic manipulation success by distilling affordance representations for object interaction and predicting within-subtask progress in a VLA model.
Training-free Sim(3) alignment method with hallucination filtering for generative 3D to partial monocular registration, plus new GenPMOAlign benchmark showing outperformance over classical and learning baselines.
FutureNav proposes a 4B-scale VLM that jointly optimizes action prediction, inverse/forward dynamics, and future state generation for VLN and reports SOTA results on multiple benchmarks.
SPARC generates reliable spatial annotations for robot demonstrations by leveraging spatio-temporal task structure, outperforming detection baselines on localization accuracy while retaining more samples and enabling competitive model performance without manual annotations.
Introduces embodied trajectory-coupled data and a three-stage training recipe to bridge VLMs to generalizable VLAs without steep degradation of pre-trained representations.
GEM adds generative depth supervision to VLM pre-training and reports improved results on embodied benchmarks plus real-world robot execution.
XEmbodied achieves SOTA on 18 embodied VQA benchmarks by fusing 3D geometric tokens and distilled physical cues into a 30B VLM with progressive curriculum training.
XEmbodied is a foundation model that integrates 3D geometric and physical signals into VLMs using a 3D Adapter and Efficient Image-Embodied Adapter, plus progressive curriculum and RL post-training, to improve spatial reasoning and embodied performance on 18 benchmarks.
SPG-Layout combines statistical object priors with hierarchical large-object-first placement to produce physically plausible text-driven 3D scenes in non-Manhattan rooms and outperforms baselines on a new 500-scene benchmark.
citing papers explorer
-
Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents
VIGIL decouples world-state completion from terminal commitment in embodied agents, exposing up to 19.7 pp gaps in benchmark success despite comparable execution across 20 models.
-
RAG-KT: Cross-platform Explainable Knowledge Tracing with Multi-view Fusion Retrieval Generation
RAG-KT frames cross-platform knowledge tracing as context-constrained LLM inference by building unified multi-source context via Question Group abstractions and retrieving complementary reliable context for grounded predictions and interpretable diagnosis.
-
Vesta: A Generalist Embodied Reasoning Model
Vesta is a unified embodied generalist model that outperforms specialist baselines by over 20% on average and improves real-world robotic task success by over 35%.
-
RoboPIN: Grounded Embodied Reasoning via Pinned Chain-of-Thought
Training a 4B vision-language model to emit identity-tracked, visually grounded reasoning anchors improves embodied spatial, multi-view, and pointing task performance over 7B baselines.
-
Token Predictors Are Not Planners: Building Physically Grounded Causal Reasoners
Introduces a new diagnostic benchmark and million-scale reasoning corpus showing that training on explicit causal traces improves next-state prediction in embodied planning, with reported gains from data scaling.
-
OneVLA: A Unified Framework for Embodied Tasks
OneVLA is a unified VLA model using a shared action head and multi-stage progressive training with CoT fine-tuning that reports state-of-the-art results on both navigation and manipulation in simulation and real-world settings.
-
RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data
A co-evolutionary VLM-VGM loop on 500 unlabeled images raises planner success by 30 points and simulator success by 48 percent while beating fully supervised baselines.
-
Large Vision-Language Models Get Lost in Attention
In LVLMs, attention can be replaced by random Gaussian weights with little or no performance loss, indicating that current models get lost in attention rather than efficiently using visual context.
-
Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
OneVL achieves superior accuracy to explicit chain-of-thought reasoning at answer-only latency by supervising latent tokens with a visual world model decoder that predicts future frames.
-
Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models
State-of-the-art vision-language-action models catastrophically fail dynamic embodied reasoning due to lexical-kinematic shortcuts, behavioral inertia, and semantic feature collapse caused by architectural bottlenecks, as shown by the new BeTTER benchmark with real-world validation.
-
Weather-Conditioned Branch Routing for Robust LiDAR-Radar 3D Object Detection
A routing framework maintains three parallel 3D feature streams for LiDAR, 4D radar, and fusion, with a lightweight router using weather prompts to dynamically weight them and auxiliary supervision to keep branches distinct, achieving SOTA on K-Radar.
-
FASTER: Rethinking Real-Time Flow VLAs
FASTER adds a Horizon-Aware Schedule to flow VLAs that compresses immediate-action denoising to one step while keeping long-horizon trajectory quality, lowering real-robot reaction latency.
-
PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation
PALM improves long-horizon robotic manipulation success by distilling affordance representations for object interaction and predicting within-subtask progress in a VLA model.
-
Robust 3D Alignment of Generative Reconstructions via Partial Monocular Observations
Training-free Sim(3) alignment method with hallucination filtering for generative 3D to partial monocular registration, plus new GenPMOAlign benchmark showing outperformance over classical and learning baselines.
-
FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation
FutureNav proposes a 4B-scale VLM that jointly optimizes action prediction, inverse/forward dynamics, and future state generation for VLN and reports SOTA results on multiple benchmarks.
-
SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale
SPARC generates reliable spatial annotations for robot demonstrations by leveraging spatio-temporal task structure, outperforming detection baselines on localization accuracy while retaining more samples and enabling competitive model performance without manual annotations.
-
Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data
Introduces embodied trajectory-coupled data and a three-stage training recipe to bridge VLMs to generalizable VLAs without steep degradation of pre-trained representations.
-
GEM: Generative Supervision Helps Embodied Intelligence
GEM adds generative depth supervision to VLM pre-training and reports improved results on embodied benchmarks plus real-world robot execution.
-
Steadily moving semi-infinite fracture in plane poroelasticity
XEmbodied achieves SOTA on 18 embodied VQA benchmarks by fusing 3D geometric tokens and distilled physical cues into a 30B VLM with progressive curriculum training.
-
XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments
XEmbodied is a foundation model that integrates 3D geometric and physical signals into VLMs using a 3D Adapter and Efficient Image-Embodied Adapter, plus progressive curriculum and RL post-training, to improve spatial reasoning and embodied performance on 18 benchmarks.
-
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
SPG-Layout combines statistical object priors with hierarchical large-object-first placement to produce physically plausible text-driven 3D scenes in non-Manhattan rooms and outperforms baselines on a new 500-scene benchmark.