Introduces the TVR active viewpoint-matching task and TVRBench indoor simulation benchmark, where foundation models start at low single-digit success rates but reach 51.4% after visual-action SFT and multi-turn GRPO post-training.
hub Canonical reference
Robopoint: A vision-language model for spatial affordance prediction for robotics
Canonical reference. 78% of citing Pith papers cite this work as background.
38
Pith papers citing it
2
external citations · external index
Background
78% of classified citations
hub tools
citation-role summary
background 7
baseline 1
method 1
citation-polarity summary
representative citing papers
VEGA improves spatial reasoning in VLA models for robotics by aligning visual encoder features with 3D-supervised DINOv2 representations via a temporary projector and cosine similarity loss.
Fine-tuning multimodal models on a new synthetic spatial benchmark improves generative spatial compliance on real and synthetic tasks and transfers to better spatial understanding.
ReKep encodes robotic tasks as optimizable Python functions over 3D keypoints that are generated automatically from language and RGB-D input, enabling real-time hierarchical planning on single- and dual-arm platforms without task-specific data.
A plug-in Q-Synth Module plus Attention-to-Point Decoder converts text-conditioned attention in frozen MLLMs into point heatmaps, improving part-level grounding accuracy on multiple datasets.
TAP-VLA improves VLA performance in contact-rich manipulation by visually annotating tactile shear fields onto input images, reaching 78% success versus under 50% for vision-only and other tactile methods.
CoStream composes semantic, predictive, and reactive behaviors on an SE(3) interface to enable precise, generalizable performance on eight real-world contact-rich manipulation tasks.
CVSBench benchmark shows VLMs struggle with cross-view spatial consistency but improve substantially when given 3D scene imagination inputs.
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.
MaskWAM unifies mask prompting and prediction in world-action models via Mixture of Transformers to improve robotic policy generalization on language-ambiguous tasks.
SVoT uses RL with GRPO to train MLLMs on interleaved textual and visual reasoning chains for multi-hop spatial tasks, achieving up to 65% accuracy gains on new domains with quantitative state verification.
AxisGuide augments RGB images with rendered robot base-frame axis cues to improve generalization of visuomotor manipulation policies under distribution shifts.
Afford-VLA internalizes task-conditioned affordance as an explicit visual planning interface within VLA models via learnable <AFF> tokens, achieving SOTA on LIBERO and SimplerEnv benchmarks.
SceneParser introduces hierarchical scene parsing as object-part-affordance chains, a VLM trained with pseudo labels and curriculum learning, and SceneParser-Bench with 1.74M affordance annotations, showing better structure-aware results than existing MLLMs.
A task-oriented robotic system organizes heterogeneous planar objects on desks using perception-augmented datasets and environment-assisted manipulation primitives such as contact grasping, edge push-grasping, and levering.
PRTS pretrains VLA models with contrastive goal-conditioned RL to embed goal-reachability probabilities from offline data, yielding SOTA results on robotic benchmarks especially for long-horizon and novel instructions.
VLMs generalize affordance inference to non-humanoid robots but produce inconsistent results with a conservative bias of low false positives and high false negatives, especially for novel object manipulations.
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.
LAST augments MLLMs with a tool-abstraction sandbox and three-stage training to deliver around 20% gains on spatial reasoning tasks, outperforming closed-source models.
PALM improves long-horizon robotic manipulation success by distilling affordance representations for object interaction and predicting within-subtask progress in a VLA model.
MiMo-Embodied is a single foundation model that achieves state-of-the-art results on 17 embodied AI benchmarks and 12 autonomous driving benchmarks through multi-stage learning, curated data, and CoT/RL fine-tuning that produces positive cross-domain transfer.
LACY is a VLM framework jointly trained on L2A, A2L, and L2C tasks that uses an active augmentation cycle to self-improve robotic manipulation policies, reporting a 56.46% average success rate gain in simulation and real-world experiments.
InternVLA-M1 uses spatially guided pre-training on 2.3M examples followed by action post-training to deliver up to 17% gains on robot manipulation benchmarks and 20.6% on unseen objects.
citing papers explorer
-
Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?
Introduces the TVR active viewpoint-matching task and TVRBench indoor simulation benchmark, where foundation models start at low single-digit success rates but reach 51.4% after visual-action SFT and multi-turn GRPO post-training.
-
VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models
VEGA improves spatial reasoning in VLA models for robotics by aligning visual encoder features with 3D-supervised DINOv2 representations via a temporary projector and cosine similarity loss.
-
Exploring Spatial Intelligence from a Generative Perspective
Fine-tuning multimodal models on a new synthetic spatial benchmark improves generative spatial compliance on real and synthetic tasks and transfers to better spatial understanding.
-
ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation
ReKep encodes robotic tasks as optimizable Python functions over 3D keypoints that are generated automatically from language and RGB-D input, enabling real-time hierarchical planning on single- and dual-arm platforms without task-specific data.
-
Enhancing Part-Level Point Grounding for Any Open-Source MLLMs
A plug-in Q-Synth Module plus Attention-to-Point Decoder converts text-conditioned attention in frozen MLLMs into point heatmaps, improving part-level grounding accuracy on multiple datasets.
-
TAP-VLA: Tactile Annotation Prompting for Vision Language Action Models
TAP-VLA improves VLA performance in contact-rich manipulation by visually annotating tactile shear fields onto input images, reaching 78% success versus under 50% for vision-only and other tactile methods.
-
CoStream: Composing Simple Behaviors for Generalizable Complex Manipulation
CoStream composes semantic, predictive, and reactive behaviors on an SE(3) interface to enable precise, generalizable performance on eight real-world contact-rich manipulation tasks.
-
CVSBench: A Comprehensive Benchmark for Cross-view Spatial Reasoning and Dreaming
CVSBench benchmark shows VLMs struggle with cross-view spatial consistency but improve substantially when given 3D scene imagination inputs.
-
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.
-
MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models
MaskWAM unifies mask prompting and prediction in world-action models via Mixture of Transformers to improve robotic policy generalization on language-ambiguous tasks.
-
SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning
SVoT uses RL with GRPO to train MLLMs on interleaved textual and visual reasoning chains for multi-hop spatial tasks, achieving up to 65% accuracy gains on new domains with quantitative state verification.
-
AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor Manipulation
AxisGuide augments RGB images with rendered robot base-frame axis cues to improve generalization of visuomotor manipulation policies under distribution shifts.
-
Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance
Afford-VLA internalizes task-conditioned affordance as an explicit visual planning interface within VLA models via learnable <AFF> tokens, achieving SOTA on LIBERO and SimplerEnv benchmarks.
-
SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding
SceneParser introduces hierarchical scene parsing as object-part-affordance chains, a VLM trained with pseudo labels and curriculum learning, and SceneParser-Bench with 1.74M affordance annotations, showing better structure-aware results than existing MLLMs.
-
Robotic Desk Organization: A Multi-Primitive Approach to Manipulating Heterogeneous Objects via Environmental Constraints
A task-oriented robotic system organizes heterogeneous planar objects on desks using perception-augmented datasets and environment-assisted manipulation primitives such as contact grasping, edge push-grasping, and levering.
-
PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations
PRTS pretrains VLA models with contrastive goal-conditioned RL to embed goal-reachability probabilities from offline data, yielding SOTA results on robotic benchmarks especially for long-horizon and novel instructions.
-
Assessing VLM-Driven Semantic-Affordance Inference for Non-Humanoid Robot Morphologies
VLMs generalize affordance inference to non-humanoid robots but produce inconsistent results with a conservative bias of low false positives and high false negatives, especially for novel object manipulations.
-
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.
-
LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models
LAST augments MLLMs with a tool-abstraction sandbox and three-stage training to deliver around 20% gains on spatial reasoning tasks, outperforming closed-source models.
-
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.
-
MiMo-Embodied: X-Embodied Foundation Model Technical Report
MiMo-Embodied is a single foundation model that achieves state-of-the-art results on 17 embodied AI benchmarks and 12 autonomous driving benchmarks through multi-stage learning, curated data, and CoT/RL fine-tuning that produces positive cross-domain transfer.
-
LACY: A Vision-Language Model-based Language-Action Cycle for Self-Improving Robotic Manipulation
LACY is a VLM framework jointly trained on L2A, A2L, and L2C tasks that uses an active augmentation cycle to self-improve robotic manipulation policies, reporting a 56.46% average success rate gain in simulation and real-world experiments.
-
InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
InternVLA-M1 uses spatially guided pre-training on 2.3M examples followed by action post-training to deliver up to 17% gains on robot manipulation benchmarks and 20.6% on unseen objects.
-
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
DreamVLA uses dynamic-region-guided world knowledge prediction, block-wise attention to disentangle information types, and a diffusion transformer for actions, reaching 76.7% success on real robot tasks and 4.44 average length on CALVIN ABC-D.
-
A Survey on Vision-Language-Action Models for Embodied AI
This is the first survey on vision-language-action models, providing a taxonomy across three lines, plus summaries of datasets, simulators, benchmarks, challenges, and future directions in embodied AI.
-
OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping
OmniView-Space framework with MPSM, tool-guided reasoning, and distillation achieves SOTA on spatial reasoning benchmarks for MLLMs while reducing external geometry dependencies.
-
ZeroDex: Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning
ZeroDex grounds VLM outputs into 3D keypoints via multi-view triangulation and ray voting to enable zero-shot long-horizon dexterous manipulation with closed-loop replanning.
-
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.
-
GeoAlign: Beyond Semantics with State-Guided Spatial Alignment in VLA Models
GeoAlign post-trains an RGB geometry branch on robot RGB-D data to produce GEP features that are queried by proprioceptive state to generate phase-dependent geometry tokens, yielding 99.0% on LIBERO, 85.3% on SimplerEnv-Fractal, and 78.8% on real ALOHA tasks.
-
Wall-OSS-0.5 Technical Report
Wall-OSS-0.5 is a 4B VLA model pretrained across many embodiments that achieves zero-shot real-robot performance on a 17-task suite and outperforms π_0.5 after fine-tuning.
-
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.
-
Extending Embodied Question Answering from Perception to Decision
Introduces EQA-Decision dataset with 4M+ QA pairs across four embodied reasoning dimensions and RoboDecision baseline for joint perception-reasoning-decision evaluation.
-
Humanoid Whole-Body Manipulation via Active Spatial Brain and Generalizable Action Cerebellum
A multi-agent large-model framework (Active Spatial Brain + Generalizable Action Cerebellum) enables spatial-aware humanoid whole-body manipulation without task-specific real-robot data.
-
X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose Interaction
X-Imitator is a bidirectional action-pose interaction framework for spatial-aware imitation learning that outperforms vanilla policies and explicit pose guidance on 24 simulated and 3 real-world robotic tasks.
-
AnySlot: Goal-Conditioned Vision-Language-Action Policies for Zero-Shot Slot-Level Placement
AnySlot decouples language slot selection from control via an explicit visual goal marker and reports large zero-shot gains on SlotBench, but the provided body text does not match the abstract.
-
ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
ThinkAct introduces reinforced visual latent planning in a dual VLA system to enable better long-horizon reasoning and adaptation for embodied tasks.
-
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
An 8B embodied foundation model trained on 15B tokens with multi-task RL and a Planner-Grounder-Corrector loop claims SOTA on 16/24 embodied VLM benchmarks and strong VLA/real-robot transfer.