{"list":"other","total":59,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"1908.00222","title":"Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling","created":"2019-08-01","cited_by_count":286},{"id":"2403.13298","title":"Rotary Position Embedding for Vision Transformer","created":"2024-03-20","cited_by_count":236},{"id":"2405.14832","title":"Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer","created":"2024-05-23","cited_by_count":210},{"id":"2412.12392","title":"MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors","created":"2024-12-16","cited_by_count":205},{"id":"2509.18154","title":"MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe","created":"2025-09-16","cited_by_count":186},{"id":"2402.09181","title":"OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM","created":"2024-02-14","cited_by_count":184},{"id":"2412.07825","title":"3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark","created":"2024-12-10","cited_by_count":139},{"id":"2308.08769","title":"Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes","created":"2023-08-17","cited_by_count":129},{"id":"2006.05682","title":"H3DNet: 3D Object Detection Using Hybrid Geometric Primitives","created":"2020-06-10","cited_by_count":123},{"id":"2503.16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","created":"2025-03-20","cited_by_count":110},{"id":"2403.13064","title":"SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model","created":"2024-03-19","cited_by_count":96},{"id":"2412.10360","title":"Apollo: An Exploration of Video Understanding in Large Multimodal Models","created":"2024-12-13","cited_by_count":89},{"id":"2502.19680","title":"M-LLM Based Video Frame Selection for Efficient Video Understanding","created":"2025-02-27","cited_by_count":88},{"id":"2404.15269","title":"Aligning LLM Agents by Learning Latent Preference from User Edits","created":"2024-04-23","cited_by_count":69},{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65},{"id":"2311.15599","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","created":"2023-11-27","cited_by_count":64},{"id":"2307.14620","title":"NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection","created":"2023-07-27","cited_by_count":51},{"id":"2211.15658","title":"Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries","created":"2022-11-28","cited_by_count":49},{"id":"2410.15926","title":"Mitigating Object Hallucination via Concentric Causal Attention","created":"2024-10-21","cited_by_count":49},{"id":"2209.02778","title":"Multi-skill Mobile Manipulation for Object Rearrangement","created":"2022-09-06","cited_by_count":46},{"id":"2409.15146","title":"COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models","created":"2024-09-23","cited_by_count":45},{"id":"1904.08963","title":"VoteNet: A Deep Learning Label Fusion Method for Multi-Atlas Segmentation","created":"2019-04-18","cited_by_count":44},{"id":"2303.13497","title":"TriPlaneNet: An Encoder for EG3D Inversion","created":"2023-03-23","cited_by_count":41},{"id":"2406.09401","title":"MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations","created":"2024-06-13","cited_by_count":40},{"id":"2412.17739","title":"Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization","created":"2024-12-23","cited_by_count":39},{"id":"2404.03656","title":"MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation","created":"2024-04-04","cited_by_count":35},{"id":"2212.06858","title":"LidarCLIP or: How I Learned to Talk to Point Clouds","created":"2022-12-13","cited_by_count":33},{"id":"2412.09530","title":"Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM","created":"2024-12-12","cited_by_count":32},{"id":"2403.07535","title":"Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving","created":"2024-03-12","cited_by_count":30},{"id":"2405.03690","title":"How Good is my Video LMM? Complex Video Reasoning and Robustness Evaluation Suite for Video-LMMs","created":"2024-05-06","cited_by_count":30},{"id":"2409.01392","title":"ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems","created":"2024-09-02","cited_by_count":30},{"id":"2412.18450","title":"3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding","created":"2024-12-24","cited_by_count":27},{"id":"2503.23297","title":"ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning","created":"2025-03-30","cited_by_count":25},{"id":"2505.22657","title":"3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model","created":"2025-05-28","cited_by_count":25},{"id":"2411.17221","title":"AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM","created":"2024-11-26","cited_by_count":24},{"id":"2403.07874","title":"Beyond Text: Frozen Large Language Models in Visual Signal Comprehension","created":"2024-03-12","cited_by_count":23},{"id":"2404.07989","title":"Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding","created":"2024-04-11","cited_by_count":23},{"id":"2409.04234","title":"UniDet3D: Multi-dataset Indoor 3D Object Detection","created":"2024-09-06","cited_by_count":20},{"id":"2506.03737","title":"ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices","created":"2025-06-04","cited_by_count":18},{"id":"2406.08654","title":"Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization","created":"2024-06-12","cited_by_count":17},{"id":"2410.21216","title":"HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation","created":"2024-10-28","cited_by_count":17},{"id":"2411.16072","title":"Language Driven Occupancy Prediction","created":"2024-11-25","cited_by_count":17},{"id":"2412.16919","title":"TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction","created":"2024-12-22","cited_by_count":16},{"id":"2505.16416","title":"Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models","created":"2025-05-22","cited_by_count":14},{"id":"2404.04363","title":"Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs","created":"2024-04-05","cited_by_count":12},{"id":"2507.09184","title":"MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models","created":"2025-07-12","cited_by_count":12},{"id":"1710.01328","title":"Reuleaux: Robot Base Placement by Reachability Analysis","created":"2017-10-03","cited_by_count":11},{"id":"2409.16030","title":"MHRC: Closed-loop Decentralized Multi-Heterogeneous Robot Collaboration with Large Language Models","created":"2024-09-24","cited_by_count":10},{"id":"2503.15029","title":"DRoPE: Directional Rotary Position Embedding for Efficient Agent Interaction Modeling","created":"2025-03-19","cited_by_count":9},{"id":"2504.12643","title":"RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding","created":"2025-04-17","cited_by_count":7},{"id":"2505.00156","title":"V3LMA: Visual 3D-enhanced Language Model for Autonomous Driving","created":"2025-04-30","cited_by_count":7},{"id":"2506.06279","title":"CoMemo: LVLMs Need Image Context with Image Memory","created":"2025-06-06","cited_by_count":4},{"id":"2508.04732","title":"LumiGen: An LVLM-Enhanced Iterative Framework for Fine-Grained Text-to-Image Generation","created":"2025-08-05","cited_by_count":1}],"next_cursor":null}