OpenCodePapers

robot-manipulation-on-simplerenv-widow-x

RoboticsRobot Manipulation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAveragePut Spoon on TowelPut Carrot on PlateStack Green Block on Yellow BlockPut Eggplant in Yellow BasketPut Eggplant in Yellow BasketModelNameReleaseDate
CORAL: Scalable Multi-Task Robot Learning via LoRA Experts0.979CORAL (SimVLA)2026-03-10
X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model✓ Link0.958X-VLA-0.9B2025-10-11
SimVLA: A Simple VLA Baseline for Robotic Manipulation✓ Link0.958SimVLA2026-02-20
Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models✓ Link0.847INDI (GR00T-N1.7)2026-08-24
WorldBridge: Bridging Video and Action for Task Generalization in World Action Models0.844WorldBridge (extra data)2026-10-29
Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models0.833Coarse-to-Control2026-06-05
PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations0.815PDRVLA2026-10-27
Guide, Think, Act: Interactive Embodied Reasoning for Vision-Language-Action Model0.812GTA-VLA2026-09-08
InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization✓ Link0.808InternVLA-A1.52026-07-06
Green-VLA: Staged Vision-Language-Action Model for Generalist Robots✓ Link0.805Green-VLA (Qwen3-VL-4B-Instruct, R2)2026-01-31
PhysBrain 1.0 Technical Report✓ Link0.802PhysBrain 1.02026-05-14
FM-Steer: Enhance Generalist Policies with Value-Guided Cascaded Denoising0.795FM-Steer (π0)2026-06-03
OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation0.793OA-WAM2026-05-07
Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution✓ Link0.792Xiaomi-Robotics-02026-02-13
LaMP: Learning Vision-Language-Action Policies with 3D Scene Flow as Latent Motion Prior✓ Link0.792LaMP2026-09-08
Recursive Harness Distillation across Agents for Robot Manipulation0.792Astra + GR00T (Refined Playbook)2026-09-27
World-in-Loop: Online Correction via Event-Triggered World Models for Robust VLA Policies0.782World-in-Loop + MemoryVLA2026-09-08
Chain of World: World Model Thinking in Latent Motion✓ Link0.760Chain of World2026-03-03
Beyond Dense Futures: World Models as Structured Planners for Robotic Manipulation✓ Link0.750StructVLA2026-03-13
DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning0.748DepthVLA2025-10-15
RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics0.7480.6250.7190.771RoboStream-8B2026-03-13
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models✓ Link0.740Embodied-R1.5-VLA2026-06-09
Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation✓ Link0.739LaMem-VLA2026-07-08
Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments✓ Link0.737Qwen-VLA-Instruct2026-05-28
IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation✓ Link0.729IntentVLA2026-05-14
TRM-VLA: Temporal-Aware Chain-of-Thought Reasoning and Memorization for Vision-Language-Action Models0.729TRM-VLA2026-06-03
Hume: Introducing System-2 Thinking in Visual-Language-Action Model✓ Link0.726Hume2025-05-27
In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool Use0.724VLA-Talker2026-08-06
MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation0.719MemoryVLA2025-08-26
RLDX-1 Technical Report✓ Link0.719RLDX-1 (extra data)2026-05-05
ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models✓ Link0.719ActionPiece2026-09-16
InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy✓ Link0.717InternVLA-M12025-10-15
Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text Instructions✓ Link0.710Interleave-VLA (Full, SimplerEnv-Bridge)2025-05-04
Unified Vision-Language-Action Model✓ Link0.698UniVLA2025-06-24
Memory as Weights: Internalizing Long-Term History for Streaming Videos✓ Link0.688MaLoW (Qwen3.5-2B-MLP)2026-10-15
Juno: Taming Predictive Latents for Vision-Language-Action Models0.685Juno2026-10-07
PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence0.674PhysBrain-8B2025-12-18
GEM: Generative Supervision Helps Embodied Intelligence✓ Link0.670GEM-VLA2026-05-27
TBD-VLA: Temporal Block Diffusion Vision Language Action Model0.668TBD-VLA2026-06-05
BayesianVLA: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries✓ Link0.665LangForce + Qwen3-VL-4B2026-01-21
Less is More: Reducing Complexity in Vision-Language-Action Systems✓ Link0.652StarVLA-α (Generalist)2026-09-08
SemanticVLA: Towards Semantic Reasoning over Action Memorization via Synergistic Explicit Trace and Latent Action Planning0.651SemanticVLA2026-06-03
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing✓ Link0.646StarVLA-OFT2026-04-06
World Guidance: World Modeling in Condition Space for Action Generation✓ Link0.635World Guidance2026-02-25
Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning✓ Link0.626Vlaser-QA2025-10-13
villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models✓ Link0.625villa-X (WidowX)2025-07-31
Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process✓ Link0.625UD-VLA2025-11-03
PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning✓ Link0.625PoLAR2026-06-19
SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models✓ Link0.625SIEVE (Qwen3-VL-4B-GR00T, 70% selection)2026-07-07
AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models0.615AR-VLA2026-05-11
DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models✓ Link0.615DRIFT (Qwen3-VL-2B)2026-06-04
Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone✓ Link0.604Dream-VLA2025-12-27
VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models0.604VLM4VLA (KosMos-2, SimplerEnv Bridge/WidowX)2026-01-06
Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models✓ Link0.599K-MF (GR00T-N1.6)2026-10-01
Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation0.594IVLR2026-05-01
Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance0.593Fast-dVLA2026-03-26
SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation✓ Link0.5830.5830.6670.7080.375SoFar2025-02-18
VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models✓ Link0.583VP-VLA + Qwen3VL2026-03-23
Latent Action Pretraining from Videos✓ Link0.573LAPA (BridgeV2 pretraining)2024-10-15
VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model✓ Link0.573VLA-JEPA2026-02-10
SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration0.5729SP-VLA (WidowX)2025-06-15
mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs✓ Link0.563mimic-video (per-task tau_v tuning)2025-12-17
EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training0.563InternVL3.5-1B + EmbodiedMidtrain2026-04-21
Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach✓ Link0.555π0 + TACO2025-12-02
Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies✓ Link0.542Discrete Diffusion VLA2025-08-27
VideoVLA: Video Generators Can Be Generalizable Robot Manipulators0.531VideoVLA2025-12-07
CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation0.513CogACT (WidowX Visual Matching)2024-11-29
Reinforcing Action Policies by Prophesying✓ Link0.510Pi0.5-3B + FA-GRPO & FlowScale2025-11-25
Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models0.507π0 + SVA2026-07-04
UniVLA: Learning to Act Anywhere with Task-centric Latent Actions✓ Link0.479UniVLA (Task-centric Latent Actions)2025-05-09
ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning0.477ReFineVLA2026-04-20
FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies✓ Link0.450FLOWER2025-09-05
Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance✓ Link0.38V-GPS (Octo-small)2024-10-17
MoEActok: A MoE-based Action Tokenizer for Vision-Language-Action Models✓ Link0.38MoEActok2026-06-03
SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model0.3440.2080.2080.250SpatialVLA2025-01-27
PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model0.338PixelVLA-π02025-11-03
Octo: An Open-Source Generalist Robot Policy0.3000.4720.0970.042Octo-Small2024-05-20
PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model0.167PixelVLA2025-11-03
Octo: An Open-Source Generalist Robot Policy0.1600.1250.0830.000Octo-Base2024-05-20
Towards Generalist Robot Policies: What Matters in Building Vision-Language-Action Models✓ Link0.1350.2080.2500.0830.000RoboVLM2024-12-18
RT-1: Robotics Transformer for Real-World Control at Scale✓ Link0.0110.0000.0420.000RT-1-X2022-12-13
OpenVLA: An Open-Source Vision-Language-Action Model✓ Link0.0100.0000.0000.000OpenVLA2024-06-13
Check out how to contribute new results. Then edit this file on GitLab or GitHub.