{"arxiv_id":"2608.22035","incoming":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"outgoing":{"papers":13,"sentences":16,"groups":[{"kind":"method_or_tool","label":"Uses the method or tool of","papers":2,"sentences":2,"quotes":[{"arxiv_id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","url":"/paper/2503.14734","section":": An Agentic Approach","sentence":"In our current implementation, these manipulation policies are based on GR00T N1.7 [ref] .","intent_p":1.0,"contests_p":null},{"arxiv_id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","url":"/paper/1712.05474","section":"Closed-Loop Simulation for Interactive Robot Agents","sentence":"We run these closed-loop interactions in AI2-THOR [ref] , an interactive indoor simulator, using ProcTHOR [ref] to generate diverse 3D homes with different room layouts, furnishings, and object placements.","intent_p":1.0,"contests_p":null}]},{"kind":"background","label":"Cites as background","papers":11,"sentences":12,"quotes":[{"arxiv_id":"2412.04453","title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","url":"/paper/2412.04453","section":"Introduction","sentence":"Models built on pretrained large language and vision–language models exhibit increasingly general perception, reasoning, and language-conditioned control across navigation and manipulation [ref] , while more recent approaches have begun to incorporate generative world models to support prediction and action generation [ref] .","intent_p":0.93,"contests_p":null},{"arxiv_id":"2602.15922","title":"World Action Models are Zero-shot Policies","url":"/paper/2602.15922","section":"Introduction","sentence":"Models built on pretrained large language and vision–language models exhibit increasingly general perception, reasoning, and language-conditioned control across navigation and manipulation [ref] , while more recent approaches have begun to incorporate generative world models to support prediction and action generation [ref] .","intent_p":0.93,"contests_p":null},{"arxiv_id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","url":"/paper/2503.14734","section":"Introduction","sentence":"Models built on pretrained large language and vision–language models exhibit increasingly general perception, reasoning, and language-conditioned control across navigation and manipulation [ref] , while more recent approaches have begun to incorporate generative world models to support prediction and action generation [ref] .","intent_p":0.93,"contests_p":null},{"arxiv_id":"2403.09631","title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","url":"/paper/2403.09631","section":"Introduction","sentence":"Models built on pretrained large language and vision–language models exhibit increasingly general perception, reasoning, and language-conditioned control across navigation and manipulation [ref] , while more recent approaches have begun to incorporate generative world models to support prediction and action generation [ref] .","intent_p":0.93,"contests_p":null},{"arxiv_id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","url":"/paper/2207.05608","section":"Related Work","sentence":"Inner Monologue closes this loop by returning scene descriptions, success signals, and human feedback to the model so that it can revise its plan [ref] .","intent_p":0.86,"contests_p":null}]}],"unlabelled_sentences":2},"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/2608.22035"}}