{"total":56,"rows":[{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179,"area":null},{"id":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160,"area":null},{"id":"2505.14357","title":"Vid2World: Crafting Video Diffusion Models to Interactive World Models","created":"2025-05-20","cited_by_count":76,"area":"wm"},{"id":"2405.14205","title":"Agent Planning with World Knowledge Model","created":"2024-05-23","cited_by_count":70,"area":"wm"},{"id":"2412.14135","title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","created":"2024-12-18","cited_by_count":50,"area":"lr"},{"id":"2410.07869","title":"Benchmarking Agentic Workflow Generation","created":"2024-10-10","cited_by_count":37,"area":"agents"},{"id":"2503.21765","title":"Exploring the Evolution of Physics Cognition in Video Generation: A Survey","created":"2025-03-27","cited_by_count":31,"area":"diffusion"},{"id":"2507.02092","title":"Energy-Based Transformers are Scalable Learners and Thinkers","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29,"area":null},{"id":"2409.01369","title":"Imitating Language via Scalable Inverse Reinforcement Learning","created":"2024-09-02","cited_by_count":21,"area":"offlinerl"},{"id":"2410.02429","title":"IoT-LLM: a framework for enhancing Large Language Model reasoning from real-world sensor data","created":"2024-10-03","cited_by_count":18,"area":"lr"},{"id":"2402.00854","title":"SymbolicAI: A framework for logic-based approaches combining generative models and solvers","created":"2024-02-01","cited_by_count":16,"area":null},{"id":"2402.16631","title":"GenAINet: Enabling Wireless Collective Intelligence via Knowledge Transfer and Reasoning","created":"2024-02-26","cited_by_count":13,"area":"lr"},{"id":"2409.05929","title":"M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture","created":"2024-09-09","cited_by_count":13,"area":"moe"},{"id":"2505.03176","title":"seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models","created":"2025-05-06","cited_by_count":7,"area":"wm"},{"id":"2605.23993","title":"Nano World Models: A Minimalist Implementation of Future Video Prediction","created":"2026-05-17","cited_by_count":5,"area":"wm"},{"id":"2607.06401","title":"A Definition and Roadmap for World Models","created":"2026-07-07","cited_by_count":5,"area":"wm"},{"id":"2511.20095","title":"WPT: World-to-Policy Transfer via Online World Model Distillation","created":"2025-11-25","cited_by_count":4,"area":"wm"},{"id":"2605.03517","title":"Understanding Self-Supervised Learning via Latent Distribution Matching","created":"2026-05-05","cited_by_count":4,"area":null},{"id":"2607.26924","title":"Temporally Centered SIGReg Improves LeWorldModel Representations for Robot Policy Learning","created":"2026-07-29","cited_by_count":4,"area":"wm"},{"id":"2506.23546","title":"Neural Langevin Machine: a local asymmetric learning rule can be creative","created":"2025-06-30","cited_by_count":3,"area":null},{"id":"2605.15391","title":"PanoWorld: Geometry-Consistent Panoramic Video World Modeling","created":"2026-05-14","cited_by_count":3,"area":"wm"},{"id":"2502.11646","title":"Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2510.03591","title":"A Hybrid Co-Finetuning Approach for Visual Bug Detection in Video Games","created":"2025-10-04","cited_by_count":2,"area":null},{"id":"2511.05936","title":"10 Open Challenges Steering the Future of Vision-Language-Action Models","created":"2025-11-08","cited_by_count":2,"area":"vla"},{"id":"2602.05202","title":"GT-SVJ: Generative-Transformer-Based Self-Supervised Video Judge For Efficient Video Reward Modeling","created":"2026-02-05","cited_by_count":2,"area":"mllm"},{"id":"2502.19240","title":"Enhancing Gradient-based Discrete Sampling via Parallel Tempering","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2601.14096","title":"Remapping and navigation of an embedding space via error minimization: a fundamental organizational principle of cognition in natural and artificial systems","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2602.04583","title":"PEPR: Privileged Event-based Predictive Regularization for Domain Generalization","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2606.18250","title":"Future Dynamic 3D Reconstruction: Toward 3D World Modeling with Disentangled Ego-Motion","created":"2026-06-16","cited_by_count":1,"area":"wm"},{"id":"2609.02350","title":"LookStep: Efficient Vision-Language Navigation with Linguistic Foresight and Event Driven Memory","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2308.04600","title":"Model of models -- Part 1","created":"2023-08-08","cited_by_count":0,"area":null},{"id":"2406.02699","title":"Operational Latent Spaces","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2410.23988","title":"JEMA: A Joint Embedding Framework for Scalable Co-Learning with Multimodal Alignment","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2411.16695","title":"Recurrent Joint Embedding Predictive Architecture with Recurrent Forward Propagation Learning","created":"2024-11-10","cited_by_count":0,"area":null},{"id":"2411.19370","title":"Machine learning the Ising transition: A comparison between discriminative and generative approaches","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2412.14085","title":"Future Research Avenues for Artificial Intelligence in Digital Gaming: An Exploratory Report","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2508.17275","title":"Deep Learning-Assisted Detection of Sarcopenia in Cross-Sectional Computed Tomography Imaging","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2509.07009","title":"Computational Concept of the Psyche (in Russian)","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2509.22468","title":"Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2603.15586","title":"Computational Concept of the Psyche","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.08116","title":"A unifying view of contrastive learning, importance sampling, and bridge sampling for energy-based models","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.18064","title":"Towards Human Motion World Models via Executable Behaviour Representations","created":"2026-04-20","cited_by_count":0,"area":"wm"},{"id":"2604.23336","title":"Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA","created":"2026-04-25","cited_by_count":0,"area":"distill"},{"id":"2608.08309","title":"Three Necessary Principles for Self-Supervised Visual Representation Learning","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.15309","title":"Physiological World Models for Human State Transitions","created":"2026-08-15","cited_by_count":0,"area":"wm"},{"id":"2608.15456","title":"AlignJEPA: Predictive Vision-Language Alignment for Remote Sensing Foundation Models","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.20516","title":"When Graph-JEPA Learns the Wrong Thing: Diagnosing and Repairing Category-Conditional Collapse","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.20693","title":"TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator data","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.28416","title":"Agent-Editing World Model: Rethinking World Modeling for LLM Agents","created":"2026-09-23","cited_by_count":0,"area":"wm"},{"id":"2609.37789","title":"Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39111","title":"Bongard: Training Machine Intuition","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01947","title":"Latent JEPA: Abstract Future Prediction for Latent Reasoning in Chemistry","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.03093","title":"LS-AR: Future-Predictive Latent Steering in Autoregressive LLMs","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.19636","title":"Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching","created":"2026-10-14","cited_by_count":0,"area":"mechinterp"},{"id":"2610.19955","title":"Neurosymbolic Learning of Interpretable World Models","created":"2026-10-14","cited_by_count":0,"area":"wm"}],"next_cursor":null}