Paper Citation Record · LEDGER

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation

As of 19 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2608.09226.

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

pith.paper-citation-record.v1
2608.09226 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T21:17:26.218371Z

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+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

21 of 21 outbound references displayed

verified exact2
verified fuzzy1
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b6ef6fb9-7cad-456b-ab7e-3c58bc6b4177 · outbound

This paper cites Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-11T21:17:28.103221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d7066390-cbaf-47dd-86c0-ced4649d5272 · outbound

This paper cites Directly fine-tuning diffusion models on differentiable rewards.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Directly fine-tuning diffusion models on differentiable rewards

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:25.922513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 473df447-f9ed-4b85-bac9-148502b865f4 · outbound

This paper cites Distribution Matching Distillation Meets Reinforcement Learning.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Distribution Matching Distillation Meets Reinforcement Learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:25.986375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cf23804-0409-40a2-a7ac-130234d1aedd · outbound

This paper cites Offline Reinforcement Learning with Implicit Q-Learning.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Offline Reinforcement Learning with Implicit Q-Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:26.006383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 726c62d7-b23a-43ee-a52a-c9ca6d1d4cd1 · outbound

This paper cites Flow Matching for Generative Modeling.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Flow Matching for Generative Modeling

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:26.064758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb059e99-97e5-4fd3-8d70-a2b1e5072936 · outbound

This paper cites Flow-GRPO: Training Flow Matching Models via Online RL.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Flow-GRPO: Training Flow Matching Models via Online RL

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:26.093900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58454eb9-a254-4c74-9123-1530b1d4479a · outbound

This paper cites Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:26.123274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f9b5254-5703-4054-93e1-300d8d3225a6 · outbound

This paper cites Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:26.140360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12332ecc-eda5-460c-91b0-0c5567f77b29 · outbound

This paper cites Progressive Distillation for Fast Sampling of Diffusion Models.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Progressive Distillation for Fast Sampling of Diffusion Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:26.153697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcac9a15-986f-4b5b-aa93-474bfd6e79f6 · outbound

This paper cites LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:26.163274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7019b0b7-0339-470b-b30c-56e65343f8e4 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:26.177481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22624f64-5525-4fb1-bba9-625fa3e55efe · outbound

This paper cites Denoising Diffusion Implicit Models.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Denoising Diffusion Implicit Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:26.187733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ba2f7f8-2b04-4470-8eed-cb7efd88b471 · outbound

This paper cites Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:26.194183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation feeea68e-5c33-4454-a6b1-4ba886e1b374 · outbound

This paper cites Advantage weighted matching: Aligning rl with pretraining in diffusion models.arXiv preprint arXiv:2509.25050, 2025a.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Advantage weighted matching: Aligning rl with pretraining in diffusion models.arXiv preprint arXiv:2509.25050, 2025a

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:26.211239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 699355d9-77ee-4507-aec4-0762aac548ec · outbound

This paper cites DiffusionNFT: Online Diffusion Reinforcement with Forward Process.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation DiffusionNFT: Online Diffusion Reinforcement with Forward Process

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:26.218371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ec2ee1a-cdde-476c-bd51-62f397d79f91 · outbound

This paper cites MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:26.024780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be0e1a16-fb43-456c-92b7-5598315f6930 · outbound

This paper cites Reinforcing Few-step Generators via Reward-Tilted Distribution Matching.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Reinforcing Few-step Generators via Reward-Tilted Distribution Matching

Reference 2022

Resolution: verified exact; local_arxiv, observed 2026-08-11T21:17:27.654762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cd14edf4-76b2-492d-bce1-b10f91f398f6 · outbound

This paper cites Classifier-Free Diffusion Guidance.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Classifier-Free Diffusion Guidance

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:25.964609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ededbd3-4a34-4779-850e-d592ca3d1107 · outbound

This paper cites Rdm: Re-conceptualizing distribution matching as a reward for diffusion distillation.arXiv preprint arXiv:2603.28460,.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Rdm: Re-conceptualizing distribution matching as a reward for diffusion distillation.arXiv preprint arXiv:2603.28460,

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:25.951206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a4f1880-265e-4a55-9d69-9cd75a243207 · outbound

This paper cites Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-11T21:17:26.109193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2a10241-16b8-4513-b328-2d4e8bdb95de · outbound

This paper cites Nft: Bridging supervised learning and reinforcement learning in math reasoning.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation Nft: Bridging supervised learning and reinforcement learning in math reasoning

Reference 2026

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:17:28.329247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

No inbound Pith citation observations are available.