{"list":"other","total":54,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2411.10440","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","created":"2024-11-15","cited_by_count":454},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347},{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268},{"id":"2002.12212","title":"Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image","created":"2020-02-27","cited_by_count":172},{"id":"2403.01248","title":"SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code","created":"2024-03-02","cited_by_count":134},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116},{"id":"2402.07207","title":"GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting","created":"2024-02-11","cited_by_count":109},{"id":"2412.02193","title":"LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models","created":"2024-12-03","cited_by_count":96},{"id":"1803.08999","title":"LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image","created":"2018-03-23","cited_by_count":95},{"id":"2103.06422","title":"Holistic 3D Scene Understanding from a Single Image with Implicit Representation","created":"2021-03-11","cited_by_count":94},{"id":"2404.02838","title":"I-Design: Personalized LLM Interior Designer","created":"2024-04-03","cited_by_count":87},{"id":"1808.02201","title":"Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image","created":"2018-08-07","cited_by_count":69},{"id":"2412.04383","title":"SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding","created":"2024-12-05","cited_by_count":67},{"id":"2505.02836","title":"Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation","created":"2025-05-05","cited_by_count":67},{"id":"2401.17807","title":"Advances in 3D Generation: A Survey","created":"2024-01-31","cited_by_count":63},{"id":"2509.06266","title":"Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes","created":"2025-09-08","cited_by_count":63},{"id":"2403.12409","title":"ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance","created":"2024-03-19","cited_by_count":59},{"id":"2410.13860","title":"VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding","created":"2024-10-17","cited_by_count":56},{"id":"2503.06072","title":"A Survey on Post-training of Large Language Models","created":"2025-03-08","cited_by_count":54},{"id":"2503.13439","title":"Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images","created":"2025-03-17","cited_by_count":54},{"id":"2508.15769","title":"SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass","created":"2025-08-21","cited_by_count":54},{"id":"2311.05461","title":"Control3D: Towards Controllable Text-to-3D Generation","created":"2023-11-09","cited_by_count":46},{"id":"2504.05786","title":"How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLM","created":"2025-04-08","cited_by_count":42},{"id":"2507.12465","title":"PhysX-3D: Physical-Grounded 3D Asset Generation","created":"2025-07-16","cited_by_count":42},{"id":"2410.16770","title":"The Scene Language: Representing Scenes with Programs, Words, and Embeddings","created":"2024-10-22","cited_by_count":36},{"id":"2108.10743","title":"DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization","created":"2021-08-24","cited_by_count":33},{"id":"2512.16561","title":"N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models","created":"2025-12-18","cited_by_count":29},{"id":"2506.00742","title":"ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary","created":"2025-05-31","cited_by_count":28},{"id":"2506.05341","title":"Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning","created":"2025-06-05","cited_by_count":28},{"id":"2410.15391","title":"Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint","created":"2024-10-20","cited_by_count":21},{"id":"2502.15601","title":"WorldCraft: Photo-Realistic 3D World Creation and Customization via LLM Agents","created":"2025-02-21","cited_by_count":21},{"id":"2402.14812","title":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition","created":"2024-02-22","cited_by_count":10},{"id":"2410.20723","title":"CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians","created":"2024-10-28","cited_by_count":10},{"id":"2511.21945","title":"GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence","created":"2025-11-26","cited_by_count":6},{"id":"2506.19798","title":"CoCo4D: Comprehensive and Complex 4D Scene Generation","created":"2025-06-24","cited_by_count":4}],"next_cursor":null}