VoxAfford fuses multi-scale voxel features into MLLM output tokens using cross-attention with a learned compatibility gate to achieve SOTA open-vocabulary 3D affordance detection with ~8% mIoU gain and zero-shot robot transfer.
hub
Grounded 3d-llm with referent tokens
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 2
dataset 1
citation-polarity summary
representative citing papers
SpatialMosaic introduces a 2M-pair multi-view QA dataset and 1M-pair benchmark for MLLMs on spatial reasoning under partial visibility, plus a hybrid baseline that integrates 3D reconstruction models as geometry encoders.
GUIDE unrolls multi-granularity geometric priors layer-wise into early MLLM layers with gating to improve spatial reasoning and perception.
Chat-Scene++ improves 3D scene understanding in multimodal LLMs by representing scenes as context-rich object sequences with identifier tokens and grounded chain-of-thought reasoning, reaching state-of-the-art on five benchmarks using pre-trained encoders.
Motion-MLLM integrates IMU egomotion data into MLLMs using cascaded filtering and asymmetric fusion to ground visual content in physical trajectories for scale-aware 3D understanding, achieving competitive accuracy at higher speed.
DEGround presents a unified homogeneous framework for 3D visual grounding with shared queries and two plug-in modules for better instruction alignment, reporting a 7.52% improvement on the EmbodiedScan benchmark.
Spatial-MLLM adds a 3D spatial encoder initialized from a visual geometry model and space-aware frame sampling to MLLMs to improve spatial understanding and reasoning from purely 2D visual inputs.
Efficient3D prunes visual tokens in 3D MLLMs via DVTIE and ATR modules, reporting better performance than unpruned baselines on Scan2Cap and other benchmarks.
3D awareness emerges implicitly in MLLMs via self-supervised geometric constraints that create an information bottleneck, removing depth and pose dependencies at inference and cutting latency by 55%.
Geometric Reward Credit Assignment disentangles rewards to geometric tokens and adds reprojection consistency to boost 3D keypoint accuracy from 0.64 to 0.93 and bounding box IoU to 0.686 on a ShapeNetCore benchmark while preserving 2D performance.
Presents an open ROS2-based end-to-end navigation system for quadruped robots achieving over 88% success in zero-shot real-world indoor navigation tasks using semantic scene graphs and LLM planning.
citing papers explorer
-
VoxAfford: Multi-Scale Voxel-Token Fusion for Open-Vocabulary 3D Affordance Detection
VoxAfford fuses multi-scale voxel features into MLLM output tokens using cross-attention with a learned compatibility gate to achieve SOTA open-vocabulary 3D affordance detection with ~8% mIoU gain and zero-shot robot transfer.
-
SpatialMosaic: A Multiview VLM Dataset for Partial Visibility
SpatialMosaic introduces a 2M-pair multi-view QA dataset and 1M-pair benchmark for MLLMs on spatial reasoning under partial visibility, plus a hybrid baseline that integrates 3D reconstruction models as geometry encoders.
-
Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMs
GUIDE unrolls multi-granularity geometric priors layer-wise into early MLLM layers with gating to improve spatial reasoning and perception.
-
Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM
Chat-Scene++ improves 3D scene understanding in multimodal LLMs by representing scenes as context-rich object sequences with identifier tokens and grounded chain-of-thought reasoning, reaching state-of-the-art on five benchmarks using pre-trained encoders.
-
Feeling the Space: Egomotion-Aware Video Representation for Efficient and Accurate 3D Scene Understanding
Motion-MLLM integrates IMU egomotion data into MLLMs using cascaded filtering and asymmetric fusion to ground visual content in physical trajectories for scale-aware 3D understanding, achieving competitive accuracy at higher speed.
-
DEGround: An Effective Baseline for Ego-centric 3D Visual Grounding with a Homogeneous Framework
DEGround presents a unified homogeneous framework for 3D visual grounding with shared queries and two plug-in modules for better instruction alignment, reporting a 7.52% improvement on the EmbodiedScan benchmark.
-
Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
Spatial-MLLM adds a 3D spatial encoder initialized from a visual geometry model and space-aware frame sampling to MLLMs to improve spatial understanding and reasoning from purely 2D visual inputs.
-
Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs
Efficient3D prunes visual tokens in 3D MLLMs via DVTIE and ATR modules, reporting better performance than unpruned baselines on Scan2Cap and other benchmarks.
-
3D-IDE: 3D Implicit Depth Emergent
3D awareness emerges implicitly in MLLMs via self-supervised geometric constraints that create an information bottleneck, removing depth and pose dependencies at inference and cutting latency by 55%.
-
Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment
Geometric Reward Credit Assignment disentangles rewards to geometric tokens and adds reprojection consistency to boost 3D keypoint accuracy from 0.64 to 0.93 and bounding box IoU to 0.686 on a ShapeNetCore benchmark while preserving 2D performance.
-
Open-Architecture End-to-End System for Real-World Autonomous Robot Navigation
Presents an open ROS2-based end-to-end navigation system for quadruped robots achieving over 88% success in zero-shot real-world indoor navigation tasks using semantic scene graphs and LLM planning.
- EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs