{"arxiv_id":"2510.00294","incoming":{"papers":5,"sentences":10,"groups":[{"kind":"comparison","label":"Compares with it","papers":1,"sentences":1,"quotes":[{"arxiv_id":"2601.12247","title":"Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Models","url":"/paper/2601.12247","section":"Introduction","sentence":"By proactively securing high-leverage anchors, PVF breaks the bottleneck of confidence-based strategies, achieving NFE reductions of over 60% on GSM8K, MMLU-Pro, ARC-C and WinoGrande, and over 40% on complex reasoning tasks compared to strong baselines like Fast-dLLM [ref] and FreeDave [ref] .","intent_p":1.0,"contests_p":null}]},{"kind":"background","label":"Cites it as background","papers":3,"sentences":3,"quotes":[{"arxiv_id":"2605.09536","title":"TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM","url":"/paper/2605.09536","section":"Inference Acceleration for dLLMs","sentence":"To enhance parallelism, current approaches are categorized into training-free [ref] and training-based [ref] methods.","intent_p":0.91,"contests_p":null},{"arxiv_id":"2601.12247","title":"Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Models","url":"/paper/2601.12247","section":"Related Work","sentence":"Algorithmically, strategies have evolved from rigid schedules [ref] to adaptive strategies [ref] that leverage position-specific calibration and uncertainty-driven exploration for more efficient decoding.","intent_p":0.87,"contests_p":null},{"arxiv_id":"2602.08404","title":"TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration","url":"/paper/2602.08404","section":"Related work","sentence":"A separate line of work [ref] integrates speculative decoding [ref] into dLLMs to further increase decoding parallelism.","intent_p":0.96,"contests_p":null}]}],"unlabelled_sentences":6},"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/2510.00294"}}