Describe Anything: Detailed Localized Image and Video Captioning
Paper
•
2504.16072
•
Published
•
63
interesting
-
-
EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment
Paper • 2410.09604 • Published -
Geospatial Mechanistic Interpretability of Large Language Models
Paper • 2505.03368 • Published • 10 -
Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation
Paper • 2505.02836 • Published • 8 -
Constructing a 3D Town from a Single Image
Paper • 2505.15765 • Published • 24 -
SpatialScore: Towards Unified Evaluation for Multimodal Spatial Understanding
Paper • 2505.17012 • Published • 12 -
Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models
Paper • 2505.17015 • Published • 9 -
Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces
Paper • 2506.00123 • Published • 35 -
Point-MoE: Towards Cross-Domain Generalization in 3D Semantic Segmentation via Mixture-of-Experts
Paper • 2505.23926 • Published • 5 -
TaskCraft: Automated Generation of Agentic Tasks
Paper • 2506.10055 • Published • 31 -
Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
Paper • 2506.16406 • Published • 126 -
RLPR: Extrapolating RLVR to General Domains without Verifiers
Paper • 2506.18254 • Published • 31 -
Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs
Paper • 2506.21656 • Published • 14 -
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Paper • 2507.00432 • Published • 79 -
Reconstructing 4D Spatial Intelligence: A Survey
Paper • 2507.21045 • Published • 35 -
Exploitation Is All You Need... for Exploration
Paper • 2508.01287 • Published • 6 -
3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding
Paper • 2507.23478 • Published • 15 -
MolmoAct: Action Reasoning Models that can Reason in Space
Paper • 2508.07917 • Published • 43 -
Has GPT-5 Achieved Spatial Intelligence? An Empirical Study
Paper • 2508.13142 • Published • 34 -
MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds
Paper • 2508.14879 • Published • 65 -
VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space
Paper • 2508.19247 • Published • 41 -
Spacer: Towards Engineered Scientific Inspiration
Paper • 2508.17661 • Published • 32 -
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Paper • 2509.02547 • Published • 216 -
Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings
Paper • 2508.18733 • Published • 8 -
Bootstrapping Task Spaces for Self-Improvement
Paper • 2509.04575 • Published • 5 -
3D Aware Region Prompted Vision Language Model
Paper • 2509.13317 • Published • 12 -
CAD-Tokenizer: Towards Text-based CAD Prototyping via Modality-Specific Tokenization
Paper • 2509.21150 • Published • 3 -
Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls
Paper • 2510.00184 • Published • 16 -
Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning
Paper • 2510.03259 • Published • 50 -
Watch and Learn: Learning to Use Computers from Online Videos
Paper • 2510.04673 • Published • 9