{"arxiv_id":"2512.20276","incoming":{"papers":6,"sentences":8,"groups":[{"kind":"background","label":"Cites it as background","papers":3,"sentences":4,"quotes":[{"arxiv_id":"2608.15502","title":"EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints","url":"/paper/2608.15502","section":"VLA Deployment and Acceleration","sentence":"At the system level, ActionFlow [ref] and Real-time VLA [ref] lower on-device latency through operator fusion and pipelined scheduling, while VLASH [ref] overlaps inference with action execution to mitigate structural idle time.","intent_p":0.9,"contests_p":null},{"arxiv_id":"2603.19199","title":"FASTER: Rethinking Real-Time Flow VLAs","url":"/paper/2603.19199","section":"Related Work","sentence":"Existing approaches include adopting smaller VLM backbones [ref] , compressing LLM layers [ref] , accelerating action decoding [ref] , distilling diffusion models [ref] , pruning visual tokens [ref] , and applying optimization or quantization [ref] .","intent_p":0.93,"contests_p":null},{"arxiv_id":"2607.14695","title":"Reflex: Real-Time VLA Control through Streaming Inference","url":"/paper/2607.14695","section":"The Cache Reuse Dilemma","sentence":"ActionFlow [ref] pipelined prefill and decode phases for 2.55$×$ throughput on edge devices.","intent_p":0.82,"contests_p":null}]}],"unlabelled_sentences":4},"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/2512.20276"}}