{"list":"other","total":78,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2311.12908","title":"Diffusion Model Alignment Using Direct Preference Optimization","created":"2023-11-21","cited_by_count":790},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"id":"1910.00935","title":"DiffTaichi: Differentiable Programming for Physical Simulation","created":"2019-10-01","cited_by_count":258},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255},{"id":"2403.14773","title":"StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text","created":"2024-03-21","cited_by_count":251},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174},{"id":"2410.05363","title":"Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation","created":"2024-10-07","cited_by_count":174},{"id":"2502.10248","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","created":"2025-02-14","cited_by_count":168},{"id":"2501.09038","title":"Do generative video models understand physical principles?","created":"2025-01-14","cited_by_count":161},{"id":"2412.14167","title":"VideoDPO: Omni-Preference Alignment for Video Diffusion Generation","created":"2024-12-18","cited_by_count":108},{"id":"2503.10639","title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing","created":"2025-03-13","cited_by_count":104},{"id":"2505.23656","title":"VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models","created":"2025-05-29","cited_by_count":98},{"id":"2503.08153","title":"WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation","created":"2025-03-11","cited_by_count":90},{"id":"2412.00596","title":"PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation","created":"2024-11-30","cited_by_count":80},{"id":"2309.00398","title":"VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation","created":"2023-09-01","cited_by_count":74},{"id":"2502.08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation","created":"2025-02-12","cited_by_count":74},{"id":"2501.08453","title":"Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models","created":"2025-01-14","cited_by_count":60},{"id":"2503.23368","title":"VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior","created":"2025-03-30","cited_by_count":52},{"id":"2411.17189","title":"PhysMotion: Physics-Grounded Dynamics From a Single Image","created":"2024-11-26","cited_by_count":45},{"id":"2509.06945","title":"Interleaving Reasoning for Better Text-to-Image Generation","created":"2025-09-08","cited_by_count":41},{"id":"2509.20358","title":"PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation","created":"2025-09-24","cited_by_count":41},{"id":"2407.13759","title":"Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion","created":"2024-07-18","cited_by_count":39},{"id":"2408.11475","title":"TrackGo: A Flexible and Efficient Method for Controllable Video Generation","created":"2024-08-21","cited_by_count":39},{"id":"2601.10553","title":"Inference-time Physics Alignment of Video Generative Models with Latent World Models","created":"2026-01-15","cited_by_count":37},{"id":"2507.13428","title":"\"PhyWorldBench\": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models","created":"2025-07-17","cited_by_count":36},{"id":"2308.13812","title":"Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs","created":"2023-08-26","cited_by_count":35},{"id":"2510.05094","title":"VChain: Chain-of-Visual-Thought for Reasoning in Video Generation","created":"2025-10-06","cited_by_count":32},{"id":"2603.07145","title":"LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models","created":"2026-03-07","cited_by_count":28},{"id":"2411.02394","title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions","created":"2024-11-04","cited_by_count":27},{"id":"2404.16306","title":"TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models","created":"2024-04-25","cited_by_count":25},{"id":"2412.07730","title":"STIV: Scalable Text and Image Conditioned Video Generation","created":"2024-12-10","cited_by_count":25},{"id":"2512.24551","title":"PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation","created":"2025-12-31","cited_by_count":23},{"id":"2504.10825","title":"OmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding","created":"2025-04-15","cited_by_count":22},{"id":"2508.10858","title":"Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation","created":"2025-08-14","cited_by_count":21},{"id":"2504.00010","title":"LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration","created":"2025-03-25","cited_by_count":19},{"id":"2504.08296","title":"Generative AI for Film Creation: A Survey of Recent Advances","created":"2025-04-11","cited_by_count":17},{"id":"2601.11087","title":"PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models","created":"2026-01-16","cited_by_count":17},{"id":"2503.23284","title":"SketchVideo: Sketch-based Video Generation and Editing","created":"2025-03-30","cited_by_count":16},{"id":"2501.07647","title":"BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations","created":"2025-01-13","cited_by_count":15},{"id":"2603.06408","title":"Physical Simulator In-the-Loop Video Generation","created":"2026-03-06","cited_by_count":14},{"id":"2509.24702","title":"Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility","created":"2025-09-29","cited_by_count":13},{"id":"2604.08503","title":"Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics","created":"2026-04-09","cited_by_count":12},{"id":"2605.18396","title":"NEWTON: Agentic Planning for Physically Grounded Video Generation","created":"2026-05-18","cited_by_count":12},{"id":"2412.08948","title":"Mojito: Motion Trajectory and Intensity Control for Video Generation","created":"2024-12-12","cited_by_count":9},{"id":"2506.18655","title":"RDPO: Real Data Preference Optimization for Physics Consistency Video Generation","created":"2025-06-23","cited_by_count":9},{"id":"2511.20562","title":"PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding","created":"2025-11-25","cited_by_count":9},{"id":"2502.19868","title":"C-Drag: Chain-of-Thought Driven Motion Controller for Video Generation","created":"2025-02-27","cited_by_count":6},{"id":"2504.15032","title":"DyST-XL: Dynamic Layout Planning and Content Control for Compositional Text-to-Video Generation","created":"2025-04-21","cited_by_count":6},{"id":"2603.09094","title":"Chain of Event-Centric Causal Thought for Physically Plausible Video Generation","created":"2026-03-10","cited_by_count":6},{"id":"2603.26285","title":"PhysVid: Physics Aware Local Conditioning for Generative Video Models","created":"2026-03-27","cited_by_count":6},{"id":"2605.28230","title":"Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation","created":"2026-05-27","cited_by_count":6},{"id":"2603.01893","title":"Generative Visual Chain-of-Thought for Image Editing","created":"2026-03-02","cited_by_count":3},{"id":"2601.21081","title":"Shape of Thought: Progressive Object Assembly via Visual Chain-of-Thought","created":"2026-01-28","cited_by_count":1},{"id":"2603.09104","title":"Training-free Motion Factorization for Compositional Video Generation","created":"2026-03-10","cited_by_count":1},{"id":"2605.22818","title":"MotiMotion: Motion-Controlled Video Generation with Visual Reasoning","created":"2026-05-21","cited_by_count":1}],"next_cursor":null}