Paper Citation Record · LEDGER

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding

As of 8 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2607.20467.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.20467 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T13:42:26.952910Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy0
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 616293b9-def1-4abc-9e81-22c4f7612938 · outbound

This paper cites Program Synthesis with Large Language Models.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Program Synthesis with Large Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:23.821096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ff5951a-8a44-4d34-81e6-8436442d1993 · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:24.273802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3865e8f-c6c1-4e7b-9bbc-c6da994fbb97 · outbound

This paper cites The Llama 3 Herd of Models.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding The Llama 3 Herd of Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:24.457562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ad13206-24c1-4f27-bd69-f44cf71a5ccf · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:24.528341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98cf8dae-f94e-43bf-a1c7-c20a013df18c · outbound

This paper cites Empirical analysis of decoding biases in masked diffusion models.arXiv:2508.13021,.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Empirical analysis of decoding biases in masked diffusion models.arXiv:2508.13021,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:24.592693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4bd8e67-7a9d-449f-9f37-dc808febd0b9 · outbound

This paper cites Accelerating diffusion llm inference via local deter- minism propagation.arXiv preprint arXiv:2510.07081,.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Accelerating diffusion llm inference via local deter- minism propagation.arXiv preprint arXiv:2510.07081,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:24.829332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ad3e2a1-1796-4da4-ae1e-a62d7563a082 · outbound

This paper cites Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:24.987811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ad4f409-1e20-4e09-8cd2-faf89b638128 · outbound

This paper cites Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:25.132171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a02f626-1fca-44ae-bedd-8c23a35f2520 · outbound

This paper cites Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:25.353013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 880be54c-ecb7-4242-af6b-4aa594fc84d7 · outbound

This paper cites dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:25.497970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7a6fdb1-b5d4-494a-8482-fd2a4103fc1c · outbound

This paper cites Large language diffusion models.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Large language diffusion models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:25.596364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8daa6cea-3707-4c39-a05a-fa3b3ec6e825 · outbound

This paper cites Scalable Language Model with Generalized Continual Learning.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Scalable Language Model with Generalized Continual Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:25.714439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2648fb87-7a24-4a22-bfd8-9cbc79320386 · outbound

This paper cites Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:25.796548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc2c8fec-4adb-4d11-bc4b-07cfc3bdd1f7 · outbound

This paper cites Qwen3 Technical Report.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Qwen3 Technical Report

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:25.885006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06260476-1ef6-4756-89a0-1bf4e3ae113a · outbound

This paper cites Dream 7B: Diffusion Large Language Models.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Dream 7B: Diffusion Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:26.006034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02e8daa0-e477-424b-a15c-c102f0bb703e · outbound

This paper cites LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:26.123398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0bdada5-263c-4c38-bbed-f0835187c65c · outbound

This paper cites Related Work B.1.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Related Work B.1

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:26.236548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d44c4db4-a2fa-4d16-9211-502c3a1d5ffa · outbound

This paper cites an unresolved cited work.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:26.354834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f192dead-2d76-4edc-bb77-31db269e28a2 · outbound

This paper cites While these methods effectively mitigate the overhead of AR architectures, they remain bound by the causal requirement of sequential drafting.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding While these methods effectively mitigate the overhead of AR architectures, they remain bound by the causal requirement of sequential drafting

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:26.413562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b39ddd4f-afd0-4561-b022-0e78802da216 · outbound

This paper cites Efficient representations in these spaces are also key to downstream generation tasks, such as multi-angle 3D asset editing (Huang et al., 2025).

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Efficient representations in these spaces are also key to downstream generation tasks, such as multi-angle 3D asset editing (Huang et al., 2025)

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:26.504377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa3615c1-6c6f-43fd-8e73-86f24544ddc1 · outbound

This paper cites an unresolved cited work.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:26.622923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77061a81-7d80-474e-b0ad-dc4faa8659da · outbound

This paper cites However, a critical limitation in these parallel approaches is the independence assumption.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding However, a critical limitation in these parallel approaches is the independence assumption

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:26.727462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a7b0a9b-a5e4-4166-adb6-a5daa4291b88 · outbound

This paper cites an unresolved cited work.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:26.868664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b974f93-96ce-4cb2-9f71-9e71d44c84a1 · outbound

This paper cites However, DC-Leap demonstrates its robustness in this constrained scenario, successfully delivering additional throughput gains with comparable accuracy.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding However, DC-Leap demonstrates its robustness in this constrained scenario, successfully delivering additional throughput gains with comparable accuracy

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:26.952910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6316b7d5-bfbf-4565-9b3e-cca229163550 · outbound

This paper cites Qwen3-VL Technical Report.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Qwen3-VL Technical Report

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:23.907037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f897abd-8868-4151-b05f-2845cbbfeee4 · outbound

This paper cites Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:25.191504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b379e167-72ef-40d7-a137-b1dc49ec511a · outbound

This paper cites Evaluating Large Language Models Trained on Code.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Evaluating Large Language Models Trained on Code

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:24.131133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b395f8f5-2b10-4bf2-9241-81353502650e · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Accelerating Large Language Model Decoding with Speculative Sampling

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:23.971116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87ca3e62-7d12-4f6a-91e1-09e546d7f30d · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Training Verifiers to Solve Math Word Problems

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:24.365769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e88c7fc-7d55-4859-9e5a-15190ac30d4b · outbound

This paper cites Mistral 7B.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Mistral 7B

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:24.721990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.