Skip to content

[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

active 2025-03-132026-05-14 (UTC)

Partial coverage11,438 / 12,376 hourly files (92%) · 2 absent upstream · 935 failed, retryable2025-03-132026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
360
Pushes
4
Pull requests
2
Issues
29
Stars
262
Forks
16

Activity over time

Daily event counts in the loaded window

Line chart, 428 days from 2025-03-13 to 2026-05-14. Pushes: 4 total, peak 1 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 29 total, peak 3 in a day. Comments: 47 total, peak 6 in a day. Stars: 262 total, peak 10 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue comment#137dreamer1211212026-05-14 04:39
    About loss/accuracy curve
  • Pull request#139octo-patch2026-03-24 07:37
  • Issue comment#119HELLORPG2026-03-18 10:08
    Poor pretraining results on 2b model
  • Issue comment#119BoMingZhao2026-01-26 03:29
    Poor pretraining results on 2b model
  • Issue#135Deer11112026-01-20 12:58
    Why is ada_lin computation (e.g., cond_BD) and get_logits explicitly required to be in float32?
  • Issue comment#132Paul-Liyb2026-01-20 07:16
    Missing kernel/function for customized_flash_attn
  • Issue#132CameronBraunstein2025-12-17 10:18
    Missing kernel/function for customized_flash_attn
  • Issue comment#119BoMingZhao2025-12-10 11:44
    Poor pretraining results on 2b model
  • Issue#128ShengYang-pixel2025-12-10 08:39
    Fine-tuning model memory usage
  • Issue comment#119HELLORPG2025-12-10 02:58
    Poor pretraining results on 2b model
  • Issue comment#119BoMingZhao2025-12-09 08:38
    Poor pretraining results on 2b model
  • Issue comment#119HELLORPG2025-12-09 08:28
    Poor pretraining results on 2b model
  • Issue#119daveboat2025-12-08 14:59
    Poor pretraining results on 2b model
  • Issue comment#119daveboat2025-12-08 14:58
    Poor pretraining results on 2b model
  • Issue comment#119HELLORPG2025-11-27 11:38
    Poor pretraining results on 2b model
  • Issue#128ShengYang-pixel2025-10-30 07:19
    Fine-tuning model memory usage
  • Issue comment#31Ziad-El3assal2025-10-21 13:10
    torch._dynamo.exc.BackendCompilerFailed: backend='inductor' raised:
  • Issue comment#115smileyenot9832025-10-20 06:47
    Recommended fine-tuning recipe for 2b model
  • Issue comment#116smileyenot9832025-10-20 06:46
    Questions about training speed and memory usage when finetuning the model.
  • Issue#126znavidi2025-09-29 19:57
    too many values to unpack scale_schedule
  • Issue comment#118hhchang782025-09-25 01:47
    Release of 512x512 2b model weight
  • Issue comment#123hhchang782025-09-25 01:43
    Question about 365M and 1B model weights
  • Issue comment#45smileyenot9832025-09-10 14:42
    out of resource: shared memory, Required: 131074, Hardware limit: 101376. Reducing block sizes or `num_stages` may help.
  • Issue comment#124znavidi2025-08-25 15:06
    8B model fine-tuning configuration
  • Issue#124znavidi2025-08-18 18:21
    8B model fine-tuning configuration

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 262 stars here means stars gained during the window, not the repo's star count.