ikki's picture
3

ikki

ikkitr
ยท

AI & ML interests

None yet

Recent Activity

liked a Space 19 minutes ago
cha69/README
liked a Space 1 day ago
SkalskiP/RF-DETR
liked a Space 1 day ago
SkalskiP/YOLO-ARENA
View all activity

Organizations

None yet

ikkitr's activity

liked a Space 19 minutes ago
reacted to ProCreations's post with ๐Ÿš€ 1 day ago
view post
Post
2039
Come check out my new dataset Mistake to Meaning as an attempt to help smaller models understand user typos better! Hope you guys enjoy it

ProCreations/Mistake-To-Meaning
replied to ZennyKenny's post 1 day ago
reacted to daavoo's post with ๐Ÿ‘ 1 day ago
view post
Post
968
We have just released a new version ofโญhttps://github.com/mozilla-ai/any-agent โญexposing an API to be used in async contexts:

import asyncio
from any_agent import AgentConfig, AnyAgent, TracingConfig
from any_agent.tools import search_web

async def main():
    agent = await AnyAgent.create_async(
        "openai",
        AgentConfig(
            model_id="gpt-4.1-mini",
            instructions="You are the main agent. Use the other available agents to find an answer",
        ),
        managed_agents=[
            AgentConfig(
                name="search_web_agent",
                description="An agent that can search the web",
                model_id="gpt-4.1-nano",
                tools=[search_web]
            )
        ],
        tracing=TracingConfig()
    )

    await agent.run_async("Which Agent Framework is the best??")

if __name__ == "__main__":
    asyncio.run(main())
reacted to merve's post with ๐Ÿ”ฅ 1 day ago
view post
Post
1292
Don't sleep on new AI at Meta Vision-Language release! ๐Ÿ”ฅ

facebook/perception-encoder-67f977c9a65ca5895a7f6ba1
facebook/perception-lm-67f9783f171948c383ee7498

Meta dropped swiss army knives for vision with A2.0 license ๐Ÿ‘
> image/video encoders for vision language modelling and spatial understanding (object detection etc) ๐Ÿ‘
> The vision LM outperforms InternVL3 and Qwen2.5VL ๐Ÿ‘
> They also release gigantic video and image datasets

The authors attempt to come up with single versatile vision encoder to align on diverse set of tasks.

They trained Perception Encoder (PE) Core: a new state-of-the-art family of vision encoders that can be aligned for both vision-language and spatial tasks. For zero-shot image tasks, it outperforms latest sota SigLIP2 ๐Ÿ‘



> Among fine-tuned ones, first one is PE-Spatial. It's a model to detect bounding boxes, segmentation, depth estimation and it outperforms all other models ๐Ÿ˜ฎ



> Second one is PLM, Perception Language Model, where they combine PE-Core with Qwen2.5 LM 7B. it outperforms all other models (including InternVL3 which was trained with Qwen2.5LM too!)

The authors release the following checkpoints in sizes base, large and giant:

> 3 PE-Core checkpoints (224, 336, 448)
> 2 PE-Lang checkpoints (L, G)
> One PE-Spatial (G, 448)
> 3 PLM (1B, 3B, 8B)
> Datasets



Authors release following datasets ๐Ÿ“‘
> PE Video: Gigantic video datasete of 1M videos with 120k expert annotations โฏ๏ธ
> PLM-Video and PLM-Image: Human and auto-annotated image and video datasets on region-based tasks
> PLM-VideoBench: New video benchmark on MCQA
  • 1 reply
ยท