Skip to content

EvolvingLMMs-Lab/multimodal-search-r1

View on GitHub ↗Related repositories →

MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with real-world multimodal search tools.

active 2025-04-032026-05-07 (UTC)

Partial coverage11,309 / 12,130 hourly files (93%) · 2 absent upstream · 818 failed, retryable2025-03-232026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
279
Pushes
4
Pull requests
0
Issues
21
Stars
196
Forks
11

Activity over time

Daily event counts in the loaded window

Line chart, 400 days from 2025-04-03 to 2026-05-07. Pushes: 4 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 21 total, peak 2 in a day. Comments: 47 total, peak 4 in a day. Stars: 196 total, peak 16 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

ContributorContributionsPushesPRsComments
vvukimy314019
vishwassathish9007
Helen1p4002
wyd994003
ZZZYYYLL3003
Haelles3002
fc205672001
hl07372001
Curry-Christopher2001
VAN-QIAN1001
jianpugh1000
circlePi1000
zhangxy-20191001
BlueBlueFF1001
suyan-liang1001
DietDietDiet1001
bixie68681000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#29vishwassathish2026-01-20 06:38
    Which LiveVQA dataset were the models evaluated on?
  • Issue#29vvukimy2026-01-15 06:15
    Which LiveVQA dataset were the models evaluated on?
  • Issue comment#8wyd992025-12-10 06:12
    training with image search api
  • Issue#27wyd992025-12-10 06:07
    FSDPVLLMShardingManager' is deprecated
  • Issue comment#27wyd992025-12-10 06:07
    FSDPVLLMShardingManager' is deprecated
  • Issue comment#23vvukimy2025-12-08 03:52
    Does the current implementation support GRPO training with LoRA adapters?
  • Issue comment#28VAN-QIAN2025-12-08 03:37
    Questions about the ground truth answers of sampled 2000 Infoseek Test Split
  • Issue comment#13wyd992025-12-02 05:55
    Hello, I would like to know what version of verl you are using. I currently get the error ImportError: cannot import name '_timer' from 'verl.trainer.ppo.ray_trainer'
  • Issue#26Curry-Christopher2025-11-05 12:56
    can't open image search results cache
  • Issue comment#26Curry-Christopher2025-11-05 12:56
    can't open image search results cache
  • Issue comment#7Helen1p2025-09-18 11:29
    meet error when attach model responses to vllm_inputs
  • Issue#19vishwassathish2025-09-16 03:38
    Model Hallucinates after a few steps when training
  • Issue#22Helen1p2025-09-15 17:58
    ZeroDivisionError: integer modulo by zero
  • Issue comment#22Helen1p2025-09-15 17:58
    ZeroDivisionError: integer modulo by zero
  • Issue comment#22vvukimy2025-09-15 11:41
    ZeroDivisionError: integer modulo by zero
  • Issue#22Helen1p2025-09-15 09:38
    ZeroDivisionError: integer modulo by zero
  • Issue comment#20ZZZYYYLL2025-09-15 01:54
    ValueError: Image features and image tokens do not match during training with multi-image inputs and multiple image search calls
  • Issue comment#20vvukimy2025-09-14 03:47
    ValueError: Image features and image tokens do not match during training with multi-image inputs and multiple image search calls
  • Issue comment#19vvukimy2025-09-14 03:09
    Model Hallucinates after a few steps when training
  • Issue comment#20ZZZYYYLL2025-09-11 18:25
    ValueError: Image features and image tokens do not match during training with multi-image inputs and multiple image search calls
  • Issue comment#19vvukimy2025-09-10 03:10
    Model Hallucinates after a few steps when training
  • Issue comment#19vishwassathish2025-09-09 22:49
    Model Hallucinates after a few steps when training
  • Issue comment#19vishwassathish2025-09-02 22:34
    Model Hallucinates after a few steps when training
  • Issue comment#20ZZZYYYLL2025-09-02 07:35
    ValueError: Image features and image tokens do not match during training with multi-image inputs and multiple image search calls
  • Issue comment#19vishwassathish2025-09-02 06:31
    Model Hallucinates after a few steps when training

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 196 stars here means stars gained during the window, not the repo's star count.