{"arxiv_id":"2606.15768","incoming":{"papers":20,"sentences":50,"groups":[{"kind":"extends","label":"Builds on it","papers":1,"sentences":1,"quotes":[{"arxiv_id":"2608.29937","title":"AcrossWAM1.0:A Modular Latent World-Action Stack for Compact Robot Policies","url":"/paper/2608.29937","section":"Related Work","sentence":"LaWAM showed that a latent visual subgoal can preserve the control benefit of future prediction without reconstructing pixels [ref] . builds on this result by exposing the policy/world boundary in the implementation and evaluating a compact policy configuration.","intent_p":0.91,"contests_p":null}]},{"kind":"method_or_tool","label":"Uses its method or tool","papers":1,"sentences":1,"quotes":[{"arxiv_id":"2608.11605","title":"Foresight Without Seeing: Latent Futures for World Action Models","url":"/paper/2608.11605","section":"Introduction","sentence":"To further encourage these implicit future states to focus on scene transitions induced by robot interaction, we introduce dynamics registers supervised by a frozen LaWM latent-action teacher [ref] .","intent_p":0.91,"contests_p":null}]},{"kind":"comparison","label":"Compares with it","papers":3,"sentences":4,"quotes":[{"arxiv_id":"2608.27259","title":"Making Latent Evolution Explicit: Operator-Structured Transitions for World Action Models","url":"/paper/2608.27259","section":"Policy Performance Across Prediction–Policy Couplings","sentence":"For additional context, the four-task LaWAM + LEON model also remains competitive with the corresponding published four-task slice of LaWAM [ref] trained on the full 50-task mixture, achieving 84.13% versus 83.50% in combined performance.","intent_p":0.96,"contests_p":null},{"arxiv_id":"2608.09876","title":"Energy-Structured Latent World Models with Neural Time Fields for Physically Constistent Open-World Motion Planning","url":"/paper/2608.09876","section":"Experimental Setup","sentence":"The main comparison includes Active Neural Time Fields [ref] , Generic world models (the capacity matched generative action-consistent world model) [ref] with the MPC budget, and the complete ELWM+PC-NTF system.","intent_p":1.0,"contests_p":null},{"arxiv_id":"2607.28993","title":"ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts","url":"/paper/2607.28993","section":"Experimental Setup","sentence":"These include VLAs such as $π_0$ [ref] , $π_0.5$ [ref] ; video-generative WAMs such as Fast-WAM [ref] , Motus [ref] , and LingBot-VA [ref] ; and methods exploring alternative future representations, such as LaWAM [ref] , Mask World Model [ref] , MaskWAM [ref] .","intent_p":0.98,"contests_p":null}]},{"kind":"background","label":"Cites it as background","papers":10,"sentences":14,"quotes":[{"arxiv_id":"2608.09492","title":"Rethink Before You Execute: Adaptive Execution for World Action Models","url":"/paper/2608.09492","section":"Related Work","sentence":"A parallel line of work reduces the deployment cost: FastWAM [ref] questions whether test-time future imagination is needed, AHA-WAM [ref] amortizes world planning across multiple action updates through asynchronous execution, and LaWAM [ref] exposes predictive dynamics through compact latent visual subgoals instead of future video.","intent_p":0.97,"contests_p":null},{"arxiv_id":"2608.27259","title":"Making Latent Evolution Explicit: Operator-Structured Transitions for World Action Models","url":"/paper/2608.27259","section":"Introduction","sentence":"World Action Models (WAMs) incorporate such future prediction into robot policy learning and control [ref] .","intent_p":0.88,"contests_p":null},{"arxiv_id":"2608.05903","title":"Robust-WAM: Bridging Generative Pretraining and Semantic Foresight in World-Action Models","url":"/paper/2608.05903","section":"Related Work","sentence":"LDA-1B first scales this into a semantic-latent world-action model that jointly denoises future DINO states and action chunks [ref] , and later work extends this semantic-latent world-action modeling [ref] .","intent_p":0.84,"contests_p":null},{"arxiv_id":"2608.01397","title":"SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space","url":"/paper/2608.01397","section":"Related Work","sentence":"Existing WAMs obtain future supervision from future-observation or target encoders [ref] , pretrained feature spaces or latent visual subgoals [ref] , future-informed posterior branches [ref] , compact condition spaces [ref] , or jointly modeled spatial-temporal latents and actions [ref] .","intent_p":0.83,"contests_p":null},{"arxiv_id":"2608.09381","title":"JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling","url":"/paper/2608.09381","section":"Related Work","sentence":"A third line uses a dedicated latent dynamics model to predict future representations or latent subgoals, which are then used to condition action generation [ref] .","intent_p":0.95,"contests_p":null}]}],"unlabelled_sentences":30},"outgoing":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"claims":[],"thresholds":{"intent_p":0.8,"supports_p":0.95,"contests_p":0.7},"method":"Citing sentences come from each paper's LaTeX source; every \\cite marks the sentence and the works it cites. Pith's classifier typed each sentence. A label is shown at intent probability 0.8 or more (0.95 for support), a contest at 0.7 or more. Measured accuracy against two blind model families is at https://pith.science/accuracy. The quoted sentences are the citing authors' own.","held_up":null,"_links":{"html":"https://pith.science/paper/2606.15768"}}