{"total":98,"rows":[{"id":"2507.07982","title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","created":"2025-07-10","cited_by_count":96,"area":"wm"},{"id":"2512.10794","title":"What matters for Representation Alignment: Global Information or Spatial Structure?","created":"2025-12-11","cited_by_count":84,"area":null},{"id":"2509.07979","title":"Visual Representation Alignment for Multimodal Large Language Models","created":"2025-09-09","cited_by_count":41,"area":"lr"},{"id":"2509.21309","title":"NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics","created":"2025-09-25","cited_by_count":41,"area":null},{"id":"2601.10553","title":"Inference-time Physics Alignment of Video Generative Models with Latent World Models","created":"2026-01-15","cited_by_count":37,"area":"wm"},{"id":"2507.13428","title":"\"PhyWorldBench\": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models","created":"2025-07-17","cited_by_count":36,"area":null},{"id":"2603.06507","title":"Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis","created":"2026-03-06","cited_by_count":31,"area":"diffusion"},{"id":"2605.18324","title":"Improved Baselines with Representation Autoencoders","created":"2026-05-18","cited_by_count":31,"area":null},{"id":"2601.09881","title":"Transition Matching Distillation for Fast Video Generation","created":"2026-01-14","cited_by_count":30,"area":"diffusion"},{"id":"2512.00425","title":"What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards","created":"2025-11-29","cited_by_count":25,"area":"diffusion"},{"id":"2510.19022","title":"MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models","created":"2025-10-21","cited_by_count":16,"area":"diffusion"},{"id":"2603.14366","title":"Representation Alignment for Just Image Transformers is not Easier than You Think","created":"2026-03-15","cited_by_count":14,"area":"diffusion"},{"id":"2509.24702","title":"Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility","created":"2025-09-29","cited_by_count":13,"area":"diffusion"},{"id":"2512.02622","title":"RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligence","created":"2025-12-02","cited_by_count":13,"area":"lr"},{"id":"2604.03118","title":"Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation","created":"2026-04-03","cited_by_count":13,"area":"inference"},{"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,"area":null},{"id":"2605.18396","title":"NEWTON: Agentic Planning for Physically Grounded Video Generation","created":"2026-05-18","cited_by_count":12,"area":"agents"},{"id":"2512.05564","title":"ProPhy: Progressive Physical Alignment for Dynamic World Simulation","created":"2025-12-05","cited_by_count":11,"area":null},{"id":"2606.12217","title":"Making Foresight Actionable: Repurposing Representation Alignment in World Action Models","created":"2026-06-10","cited_by_count":11,"area":"wm"},{"id":"2511.22249","title":"Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective","created":"2025-11-27","cited_by_count":10,"area":"diffusion"},{"id":"2602.10104","title":"Olaf-World: Orienting Latent Actions for Video World Modeling","created":"2026-02-10","cited_by_count":10,"area":"wm"},{"id":"2603.25743","title":"RefAlign: Representation Alignment for Reference-to-Video Generation","created":"2026-03-26","cited_by_count":10,"area":null},{"id":"2606.28128","title":"PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation","created":"2026-06-26","cited_by_count":10,"area":null},{"id":"2510.12581","title":"LayerSync: Self-aligning Intermediate Layers","created":"2025-10-14","cited_by_count":9,"area":"diffusion"},{"id":"2601.17830","title":"SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training","created":"2026-01-25","cited_by_count":9,"area":"diffusion"},{"id":"2603.19228","title":"SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing","created":"2026-03-19","cited_by_count":8,"area":null},{"id":"2605.22882","title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","created":"2026-05-20","cited_by_count":8,"area":"wm"},{"id":"2603.00466","title":"DreamWorld: Unified World Modeling in Video Generation","created":"2026-02-28","cited_by_count":7,"area":"wm"},{"id":"2603.12267","title":"EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation","created":"2026-03-12","cited_by_count":7,"area":null},{"id":"2512.04483","title":"DeRA: Decoupled Representation Alignment for Video Tokenization","created":"2025-12-04","cited_by_count":6,"area":null},{"id":"2603.09094","title":"Chain of Event-Centric Causal Thought for Physically Plausible Video Generation","created":"2026-03-10","cited_by_count":6,"area":"lr"},{"id":"2603.26285","title":"PhysVid: Physics Aware Local Conditioning for Generative Video Models","created":"2026-03-27","cited_by_count":6,"area":null},{"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,"area":null},{"id":"2606.17800","title":"MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model","created":"2026-06-16","cited_by_count":6,"area":"wm"},{"id":"2512.01843","title":"PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models","created":"2025-12-01","cited_by_count":5,"area":null},{"id":"2512.02016","title":"Objects in Generated Videos Are Slower Than They Appear: Models Suffer Sub-Earth Gravity and Don't Know Galileo's Principle...for now","created":"2025-12-01","cited_by_count":5,"area":"wm"},{"id":"2512.03350","title":"SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation","created":"2025-12-03","cited_by_count":5,"area":null},{"id":"2601.01720","title":"FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing","created":"2026-01-05","cited_by_count":5,"area":null},{"id":"2606.02564","title":"VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization","created":"2026-06-01","cited_by_count":5,"area":"lr"},{"id":"2510.07310","title":"MATRIX: Mask Track Alignment for Interaction-aware Video Generation","created":"2025-10-08","cited_by_count":4,"area":null},{"id":"2511.18991","title":"View-Consistent Diffusion Representations for 3D-Consistent Video Generation","created":"2025-11-24","cited_by_count":4,"area":"diffusion"},{"id":"2603.13770","title":"PhysAlign: Physics-Coherent Image-to-Video Generation through Feature and 3D Representation Alignment","created":"2026-03-14","cited_by_count":4,"area":"diffusion"},{"id":"2605.20290","title":"PhysOmni: Physics-Grounded Multi-Object Scene Generation from a Single Image with Real-Time Interaction","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2605.23878","title":"LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation","created":"2026-05-22","cited_by_count":4,"area":"diffusion"},{"id":"2510.04978","title":"Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI","created":"2025-10-06","cited_by_count":3,"area":"wm"},{"id":"2511.20280","title":"Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement","created":"2025-11-25","cited_by_count":3,"area":"synth"},{"id":"2603.10408","title":"Motion Forcing: A Decoupled Framework for Robust Video Generation in Motion Dynamics","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2604.01693","title":"From Understanding to Erasing: Towards Complete and Stable Video Object Removal","created":"2026-04-02","cited_by_count":3,"area":null},{"id":"2604.02817","title":"MMPhysVideo: Physically Plausible Video Generation Through Joint RGB-Perception Modeling","created":"2026-04-03","cited_by_count":3,"area":"diffusion"},{"id":"2606.06361","title":"Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them","created":"2026-06-04","cited_by_count":3,"area":"diffusion"},{"id":"2607.04653","title":"Enhancing Video Physical Consistency via Role-aware Joint Training and Modality-decoupled Denoising","created":"2026-07-06","cited_by_count":3,"area":"diffusion"},{"id":"2607.14088","title":"VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders","created":"2026-07-15","cited_by_count":3,"area":null},{"id":"2608.13556","title":"V-RAE: Rethinking Video Latent Spaces for Generation","created":"2026-08-13","cited_by_count":3,"area":null},{"id":"2603.03485","title":"Phys4D: Fine-Grained Physics-Consistent 4D Modeling from Video Diffusion","created":"2026-03-03","cited_by_count":2,"area":"wm"},{"id":"2603.16792","title":"V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising","created":"2026-03-17","cited_by_count":2,"area":"diffusion"},{"id":"2605.18365","title":"GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation","created":"2026-05-18","cited_by_count":2,"area":"diffusion"},{"id":"2605.19957","title":"World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks","created":"2026-05-19","cited_by_count":2,"area":"wm"},{"id":"2607.04311","title":"Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2607.28624","title":"PhiZero: A World Model Built Around Physical Language","created":"2026-07-30","cited_by_count":2,"area":"wm"},{"id":"2608.29904","title":"Off-Manifold Refinement: Guiding Video Generators with a Frozen World Model","created":"2026-08-30","cited_by_count":2,"area":"wm"},{"id":"2609.04200","title":"Principia: Relational Physics Tests for Video Models","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2609.23658","title":"Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms","created":"2026-09-20","cited_by_count":2,"area":"diffusion"},{"id":"2512.11792","title":"Structure From Tracking: Distilling Structure-Preserving Motion for Video Generation","created":"2025-12-12","cited_by_count":1,"area":"diffusion"},{"id":"2512.12083","title":"RePack then Refine: Efficient Diffusion Transformer with Vision Foundation Model","created":"2025-12-12","cited_by_count":1,"area":"diffusion"},{"id":"2602.17636","title":"CORAL: Correspondence Alignment for Improved Virtual Try-On","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2603.14294","title":"Seeking Physics in Diffusion Noise","created":"2026-03-15","cited_by_count":1,"area":"diffusion"},{"id":"2603.27520","title":"TokenDial: Continuous Attribute Control for Text-to-Video Generation in Visual Dial Space","created":"2026-03-29","cited_by_count":1,"area":"diffusion"},{"id":"2604.11707","title":"Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2605.20808","title":"Spatial Gram Alignment for Ultra-High-Resolution Image Synthesis","created":"2026-05-20","cited_by_count":1,"area":"diffusion"},{"id":"2605.24962","title":"Tempered Self-Similarity Alignment for Physically Plausible Video Generation","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2606.04737","title":"Physics-Informed Video Generation via Mixture-of-Experts Latent Alignment","created":"2026-06-03","cited_by_count":1,"area":"diffusion"},{"id":"2607.22241","title":"AgentHOI: Multi-Agent Reasoning for Human-Object-Interaction Video Generation via Implicit Representation Alignment","created":"2026-07-24","cited_by_count":1,"area":"diffusion"},{"id":"2604.01053","title":"PHASOR: Anatomy- and Phase-Consistent Volumetric Diffusion for CT Virtual Contrast Enhancement","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.16503","title":"Motif-Video 2B: Technical Report","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.01896","title":"Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models","created":"2026-05-03","cited_by_count":0,"area":"wm"},{"id":"2605.07800","title":"SARA: Semantically Adaptive Relational Alignment for Video Diffusion Models","created":"2026-05-08","cited_by_count":0,"area":"diffusion"},{"id":"2606.26916","title":"PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation","created":"2026-06-25","cited_by_count":0,"area":"rag"},{"id":"2606.27741","title":"SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models","created":"2026-06-26","cited_by_count":0,"area":"diffusion"},{"id":"2607.28581","title":"ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.07463","title":"MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation","created":"2026-08-07","cited_by_count":0,"area":"diffusion"},{"id":"2608.10864","title":"Multi-View Relational Distillation for Spatial Reasoning with Vision-Language Models","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.24068","title":"Representation Learning in Diffusion and Flow-based Model: An Application Aspect","created":"2026-08-25","cited_by_count":0,"area":"diffusion"},{"id":"2609.00656","title":"Physically Plausible Video Generation via Visual-Semantic Chain-of-Events Conditioning","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.03563","title":"FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.08253","title":"Revisiting Spectral Representations in Generative Diffusion Models","created":"2026-09-08","cited_by_count":0,"area":"diffusion"},{"id":"2609.13118","title":"CMA-OT: Hierarchical Expert Supervision for Dance-to-Music Generation","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.15980","title":"A Chosen Future Can Still Be Rewritten: Causal Writability in Video Models","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.35292","title":"Scaffold Then Internalize: Representation Injection for Diffusion Transformers","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2610.00812","title":"Video Generation Models: A Survey of Post-Training and Alignment","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01039","title":"Bootstrapping Video Interaction Generation with Synthetic State Transitions","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02197","title":"HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.03664","title":"ProAR: Learning Prospective Reasoning with Autoregressive Video Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.13187","title":"Destination-Conditioned Adaptation with Semantic-Geometric Alignment for Generative Inbetweening","created":"2026-10-09","cited_by_count":0,"area":"diffusion"},{"id":"2610.16365","title":"World Models Need a Physical Registry: Learning Internal Predictive States for Physically Plausible World Models","created":"2026-10-12","cited_by_count":0,"area":"wm"},{"id":"2610.16482","title":"MiMaAlign: Hierarchical Micro-Macro Alignment for Physically Plausible Video Generation","created":"2026-10-12","cited_by_count":0,"area":"diffusion"},{"id":"2610.17532","title":"CrossPortrait: Cross-Species Portrait Animation via Adversarial Motion Alignment","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18779","title":"GAD: Geometry Attention Distillation for Consistent Video Generation","created":"2026-10-13","cited_by_count":0,"area":"diffusion"},{"id":"2610.19050","title":"Focus, Align, and Diffuse: Time-Series-Aware Keyframe Diffusion for Cardiac Dynamic Synthesis from Sparse Observations","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}