| { |
| "schema_version": 2, |
| "title": "Reproduction: DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models", |
| "emoji": "🎯", |
| "space_id": "Yashp2003/repro-diffthinker-towards-generative-multimodal-reasoning-with-diffusion-models", |
| "paper": { |
| "arxiv_id": "2512.24165" |
| }, |
| "tags": [ |
| "icml2026-repro", |
| "paper-jQ2DRkSir0" |
| ], |
| "updated_at": "2026-07-23T06:31:57+00:00", |
| "root": { |
| "slug": "index", |
| "title": "Reproduction: DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models", |
| "file": "pages/index.md", |
| "children": [ |
| { |
| "slug": "executive-summary", |
| "title": "Executive summary", |
| "file": "pages/executive-summary/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-1-diffthinker-achieves-an-87-4-average-score-across-vision-centric-reasoning-tasks-outperforming-gpt-5-21-1-avg-by-314-2-table-1", |
| "title": "Claim 1: DiffThinker achieves an 87.4% average score across vision-centric reasoning tasks, outperforming GPT-5 (21.1% avg) by 314.2% (Table 1).", |
| "file": "pages/claim-1-diffthinker-achieves-an-87-4-average-score-across-vision-centric-reasoning-tasks-outperforming-gpt-5-21-1-avg-by-314-2-table-1/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-2-diffthinker-outperforms-gemini-3-flash-41-3-avg-by-111-6-on-the-same-multimodal-reasoning-benchmark-table-1", |
| "title": "Claim 2: DiffThinker outperforms Gemini-3-Flash (41.3% avg) by 111.6% on the same multimodal reasoning benchmark (Table 1).", |
| "file": "pages/claim-2-diffthinker-outperforms-gemini-3-flash-41-3-avg-by-111-6-on-the-same-multimodal-reasoning-benchmark-table-1/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-3-diffthinker-outperforms-a-fine-tuned-qwen3-vl-32b-baseline-62-9-avg-by-39-0-table-1", |
| "title": "Claim 3: DiffThinker outperforms a fine-tuned Qwen3-VL-32B baseline (62.9% avg) by 39.0% (Table 1).", |
| "file": "pages/claim-3-diffthinker-outperforms-a-fine-tuned-qwen3-vl-32b-baseline-62-9-avg-by-39-0-table-1/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-4-diffthinker-reformulates-multimodal-reasoning-as-an-image-to-image-generative-task-using-flow-matching-rather-than-text-centric-chain-of-thought-section-3", |
| "title": "Claim 4: DiffThinker reformulates multimodal reasoning as an image-to-image generative task using Flow Matching rather than text-centric chain-of-thought (Section 3).", |
| "file": "pages/claim-4-diffthinker-reformulates-multimodal-reasoning-as-an-image-to-image-generative-task-using-flow-matching-rather-than-text-centric-chain-of-thought-section-3/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-5-diffthinker-s-inference-latency-is-reported-at-approximately-1-1-seconds-with-training-efficiency-comparable-to-sft-baselines-figure-5", |
| "title": "Claim 5: DiffThinker's inference latency is reported at approximately 1.1 seconds, with training efficiency comparable to SFT baselines (Figure 5).", |
| "file": "pages/claim-5-diffthinker-s-inference-latency-is-reported-at-approximately-1-1-seconds-with-training-efficiency-comparable-to-sft-baselines-figure-5/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-6-ablations-show-performance-scales-consistently-with-training-data-size-and-peaks-at-a-classifier-free-guidance-scale-of-w-4-figures-8-9", |
| "title": "Claim 6: Ablations show performance scales consistently with training data size and peaks at a classifier-free guidance scale of w=4 (Figures 8-9).", |
| "file": "pages/claim-6-ablations-show-performance-scales-consistently-with-training-data-size-and-peaks-at-a-classifier-free-guidance-scale-of-w-4-figures-8-9/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "conclusion", |
| "title": "Conclusion", |
| "file": "pages/conclusion/page.md", |
| "children": [] |
| } |
| ] |
| }, |
| "traces": [], |
| "workspace": { |
| "file": "workspace.json", |
| "file_count": 0, |
| "total_size": 0, |
| "bucket_id": null |
| }, |
| "agent_view_tokens": 9554, |
| "trace_view_tokens": 430, |
| "workspace_view_tokens": 8, |
| "revision": "ecb34318fe73fec66de2", |
| "traces_ref": { |
| "repo_id": "Yashp2003/repro-diffthinker-towards-generative-multimodal-reasoning-with-diffusion-models-traces", |
| "repo_type": "dataset", |
| "repo_url": "https://huggingface.co/datasets/Yashp2003/repro-diffthinker-towards-generative-multimodal-reasoning-with-diffusion-models-traces", |
| "private": true |
| }, |
| "trace_dataset": "https://huggingface.co/datasets/Yashp2003/repro-diffthinker-towards-generative-multimodal-reasoning-with-diffusion-models-traces", |
| "workspace_ref": { |
| "repo_id": "Yashp2003/repro-diffthinker-towards-generative-multimodal-reasoning-with-diffusion-models-artifacts", |
| "repo_type": "bucket", |
| "repo_url": "https://huggingface.co/buckets/Yashp2003/repro-diffthinker-towards-generative-multimodal-reasoning-with-diffusion-models-artifacts", |
| "private": true |
| }, |
| "workspace_bucket": "https://huggingface.co/buckets/Yashp2003/repro-diffthinker-towards-generative-multimodal-reasoning-with-diffusion-models-artifacts" |
| } |
