ACC: Compiling Agent Trajectories for Long-Context Training
Paper โข 2605.21850 โข Published โข 56
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
ACC: Compiling Agent Trajectories for Long-Context Training
Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning
groundhogLLMย
submitted a
paper to Daily Papers 2 days ago
nielsrย
submitted a
paper to Daily Papers 3 days ago
Hanbo-Chengย
submitted a
paper to Daily Papers 9 days ago
nielsrย
submitted 2
papers to Daily Papers about 1 month ago
nielsrย
submitted 2
papers to Daily Papers about 2 months ago
nielsrย
submitted 3
papers to Daily Papers 2 months ago
Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders
Paper โข 2603.19209 โข Published โข 5
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
Paper โข 2603.14482 โข Published โข 35
Omnilingual MT: Machine Translation for 1,600 Languages
Paper โข 2603.16309 โข Published โข 23
nielsrย
authored a
paper 2 months ago
nielsrย
submitted 2
papers to Daily Papers 3 months ago
nielsrย
submitted 2
papers to Daily Papers 4 months ago
nielsrย
submitted a
paper to Daily Papers 5 months ago
ariG23498ย
authored a
paper 7 months ago
Post
12481
deepseek-ai/DeepSeek-OCR is out! ๐ฅ my take โคต๏ธ
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
- 4 replies
Post
7023
large AI labs open-sourced a ton of models last week ๐ฅ
here's few picks, find even more here merve/sep-16-releases-68d13ea4c547f02f95842f05 ๐ค
> IBM released a new Docling model with 258M params based on Granite (A2.0) ๐ ibm-granite/granite-docling-258M
> Xiaomi released 7B audio LM with base and instruct variants (MIT) XiaomiMiMo/mimo-audio-68cc7202692c27dae881cce0
> DecartAI released Lucy Edit, open Nano Banana ๐ (NC) decart-ai/Lucy-Edit-Dev
> OpenGVLab released a family of agentic computer use models (3B/7B/32B) with the dataset ๐ป OpenGVLab/scalecua-68c912cf56f7ff4c8e034003
> Meituan Longcat released thinking version of LongCat-Flash ๐ญ meituan-longcat/LongCat-Flash-Thinking
here's few picks, find even more here merve/sep-16-releases-68d13ea4c547f02f95842f05 ๐ค
> IBM released a new Docling model with 258M params based on Granite (A2.0) ๐ ibm-granite/granite-docling-258M
> Xiaomi released 7B audio LM with base and instruct variants (MIT) XiaomiMiMo/mimo-audio-68cc7202692c27dae881cce0
> DecartAI released Lucy Edit, open Nano Banana ๐ (NC) decart-ai/Lucy-Edit-Dev
> OpenGVLab released a family of agentic computer use models (3B/7B/32B) with the dataset ๐ป OpenGVLab/scalecua-68c912cf56f7ff4c8e034003
> Meituan Longcat released thinking version of LongCat-Flash ๐ญ meituan-longcat/LongCat-Flash-Thinking
- 2 replies
Post
3544
IBM just released small swiss army knife for the document models: granite-docling-258M on Hugging Face ๐ฅ
> not only a document converter but also can do document question answering, understand multiple languages ๐คฏ
> best part: released with Apache 2.0 license ๐ use it with your commercial projects!
> it supports transformers, vLLM and MLX from the get-go! ๐ค
> built on SigLIP2 & granite-165M
model: ibm-granite/granite-docling-258M
demo: ibm-granite/granite-docling-258m-demo ๐
> not only a document converter but also can do document question answering, understand multiple languages ๐คฏ
> best part: released with Apache 2.0 license ๐ use it with your commercial projects!
> it supports transformers, vLLM and MLX from the get-go! ๐ค
> built on SigLIP2 & granite-165M
model: ibm-granite/granite-docling-258M
demo: ibm-granite/granite-docling-258m-demo ๐