MLLM
Meow
Lick
Lick
Meow
Meow
Lick
Lick
Meow
April 22, 2026 at 4:20 PM
MLLM
Meow
Lick
Lick
Meow
Meow
Lick
Lick
Meow
has anyone done this yet: "MLLM"
oh i guess i could hve asked chatgpt but i'm too much of a LUDDITE
oh i guess i could hve asked chatgpt but i'm too much of a LUDDITE
April 22, 2026 at 4:16 PM
has anyone done this yet: "MLLM"
oh i guess i could hve asked chatgpt but i'm too much of a LUDDITE
oh i guess i could hve asked chatgpt but i'm too much of a LUDDITE
yeah my cat did a mllm the other day
April 22, 2026 at 4:19 PM
yeah my cat did a mllm the other day
New 7-8B OCR model release from AliBaba. Integrated structures data approach looks promising for specialized use cases with complex visual inputs. huggingface.co/Logics-MLLM/...
September 29, 2025 at 12:01 PM
New 7-8B OCR model release from AliBaba. Integrated structures data approach looks promising for specialized use cases with complex visual inputs. huggingface.co/Logics-MLLM/...
MLLM Enterprises
February 12, 2026 at 11:02 PM
MLLM Enterprises
Just to share a bit of academic content… have you heard of VoRA? arxiv.org/abs/2503.20680 🙃
Vision as LoRA
We introduce Vision as LoRA (VoRA), a novel paradigm for transforming an LLM into an MLLM. Unlike prevalent MLLM architectures that rely on external vision modules for vision encoding, VoRA internaliz...
arxiv.org
March 27, 2025 at 6:25 PM
Just to share a bit of academic content… have you heard of VoRA? arxiv.org/abs/2503.20680 🙃
Same here… not going back. So currently just hanging around and hopeful that my students will catch any fancy trends … btw … interesting paper arxiv.org/abs/2503.20680 🙃
Vision as LoRA
We introduce Vision as LoRA (VoRA), a novel paradigm for transforming an LLM into an MLLM. Unlike prevalent MLLM architectures that rely on external vision modules for vision encoding, VoRA internaliz...
arxiv.org
March 27, 2025 at 6:23 PM
Same here… not going back. So currently just hanging around and hopeful that my students will catch any fancy trends … btw … interesting paper arxiv.org/abs/2503.20680 🙃
Why Do Multimodal LLMs (MLLM) Struggle with Spatial Understanding?
Is it just because of not enough data? Nope!
Researchers finds that current MLLMs have fundamental limitations, and they suggest that real progress in spatial reasoning will require targeted reasoning injection
Is it just because of not enough data? Nope!
Researchers finds that current MLLMs have fundamental limitations, and they suggest that real progress in spatial reasoning will require targeted reasoning injection
September 11, 2025 at 11:54 PM
Why Do Multimodal LLMs (MLLM) Struggle with Spatial Understanding?
Is it just because of not enough data? Nope!
Researchers finds that current MLLMs have fundamental limitations, and they suggest that real progress in spatial reasoning will require targeted reasoning injection
Is it just because of not enough data? Nope!
Researchers finds that current MLLMs have fundamental limitations, and they suggest that real progress in spatial reasoning will require targeted reasoning injection
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
huggingface.co/papers/2607....
huggingface.co/papers/2607....
Paper page - VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
Join the discussion on this paper page
huggingface.co
July 19, 2026 at 8:18 PM
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
huggingface.co/papers/2607....
huggingface.co/papers/2607....
LLM? MLM?? MLLM??? WLW??????? some of you need to be Loving the Lord More, More Lord More, More Loving the Lord Mas, and Worshiping the Lord in Wonder
October 30, 2025 at 3:10 PM
LLM? MLM?? MLLM??? WLW??????? some of you need to be Loving the Lord More, More Lord More, More Loving the Lord Mas, and Worshiping the Lord in Wonder
MLLM (Millenium) - Ти Чуєш
Listen to MLLM (Millenium) - Ти Чуєш by thomas.brnf #np on #SoundCloud
soundcloud.com
January 22, 2025 at 3:43 PM
Ming-flash-omni 2.0 🚀 New open omni-MLLM released by Ant Group
huggingface.co/inclusionAI/...
✨ MIT license
✨ MoE - 100B/6B active
✨ Zero-shot voice cloning + controllable audio
✨ Fine-grained visual knowledge grounding
huggingface.co/inclusionAI/...
✨ MIT license
✨ MoE - 100B/6B active
✨ Zero-shot voice cloning + controllable audio
✨ Fine-grained visual knowledge grounding
February 11, 2026 at 10:52 AM
Ming-flash-omni 2.0 🚀 New open omni-MLLM released by Ant Group
huggingface.co/inclusionAI/...
✨ MIT license
✨ MoE - 100B/6B active
✨ Zero-shot voice cloning + controllable audio
✨ Fine-grained visual knowledge grounding
huggingface.co/inclusionAI/...
✨ MIT license
✨ MoE - 100B/6B active
✨ Zero-shot voice cloning + controllable audio
✨ Fine-grained visual knowledge grounding
The open-source multimodal large language model (MLLM) for real-time vision and speech interaction, VITA, has released version 1.5.
www.luok.ai/x/1343D5AE-F...
www.luok.ai/x/1343D5AE-F...
VITA 1.5
www.luok.ai
January 6, 2025 at 3:28 PM
The open-source multimodal large language model (MLLM) for real-time vision and speech interaction, VITA, has released version 1.5.
www.luok.ai/x/1343D5AE-F...
www.luok.ai/x/1343D5AE-F...
MiniCPM V4.6 🔥 a 1B MLLM that actually runs on your phone, just released by OpenBMB
huggingface.co/openbmb/Mini...
✨ 1B - Apache2.0
✨ Runs on iOS, Android, HarmonyOS
✨ ~1.5× faster throughput than Qwen3.5 0.8B
✨ Mixed 4x/16x visual token compression
huggingface.co/openbmb/Mini...
✨ 1B - Apache2.0
✨ Runs on iOS, Android, HarmonyOS
✨ ~1.5× faster throughput than Qwen3.5 0.8B
✨ Mixed 4x/16x visual token compression
May 11, 2026 at 3:27 PM
MiniCPM V4.6 🔥 a 1B MLLM that actually runs on your phone, just released by OpenBMB
huggingface.co/openbmb/Mini...
✨ 1B - Apache2.0
✨ Runs on iOS, Android, HarmonyOS
✨ ~1.5× faster throughput than Qwen3.5 0.8B
✨ Mixed 4x/16x visual token compression
huggingface.co/openbmb/Mini...
✨ 1B - Apache2.0
✨ Runs on iOS, Android, HarmonyOS
✨ ~1.5× faster throughput than Qwen3.5 0.8B
✨ Mixed 4x/16x visual token compression
Nowun wants tuo here dat sentence agin. But dat doez remind mee of dis
youtube.com/watch?v=MLlm...
youtube.com/watch?v=MLlm...
Tina Turner - Private Dancer - (1986) • TopPop
YouTube video by TopPop
youtube.com
September 11, 2026 at 12:08 AM
Nowun wants tuo here dat sentence agin. But dat doez remind mee of dis
youtube.com/watch?v=MLlm...
youtube.com/watch?v=MLlm...
Kleiner (hoffentlich in Zukunft größerer) Überblick über DSGVO-konforme Zugänge zu #ChatGPT.
Bisher mit:
- @fobizz.bsky.social und
- @schulki.de
Bin gespannt, welche MLLM & KI uns in Zukunft erwarten und wie Schulen Zugang erhalten können... #LernenmitKI #Schule
unterrichten.digital/2023/11/12/c...
Bisher mit:
- @fobizz.bsky.social und
- @schulki.de
Bin gespannt, welche MLLM & KI uns in Zukunft erwarten und wie Schulen Zugang erhalten können... #LernenmitKI #Schule
unterrichten.digital/2023/11/12/c...
ChatGPT & DSGVO - 2 Plattformen für die datenschutzkonforme ChatGPT-Nutzung in Schule und Untericht...
Wie lassen sich ChatGPT und andere Sprachmodelle/KI DSGVO- und datenschutzkonform in Schule und Unterricht nutzen? Ein erster Überblick mit fobizz und SchulKI.
unterrichten.digital
November 12, 2023 at 2:19 PM
Kleiner (hoffentlich in Zukunft größerer) Überblick über DSGVO-konforme Zugänge zu #ChatGPT.
Bisher mit:
- @fobizz.bsky.social und
- @schulki.de
Bin gespannt, welche MLLM & KI uns in Zukunft erwarten und wie Schulen Zugang erhalten können... #LernenmitKI #Schule
unterrichten.digital/2023/11/12/c...
Bisher mit:
- @fobizz.bsky.social und
- @schulki.de
Bin gespannt, welche MLLM & KI uns in Zukunft erwarten und wie Schulen Zugang erhalten können... #LernenmitKI #Schule
unterrichten.digital/2023/11/12/c...
Qwen image edit uses Qwen2.5-VL multimodal large language model (MLLM) for text conditioning and semantic understanding.
August 26, 2025 at 2:57 PM
Qwen image edit uses Qwen2.5-VL multimodal large language model (MLLM) for text conditioning and semantic understanding.
- Advanced OCR & video understanding
- Offline iPad-compatible multimodal live streaming
Repo: github.com/OpenBMB/Mini...
Models: huggingface.co/openbmb/Mini...
Demo: minicpm-omni-webdemo-us.modelbest.cn
- Offline iPad-compatible multimodal live streaming
Repo: github.com/OpenBMB/Mini...
Models: huggingface.co/openbmb/Mini...
Demo: minicpm-omni-webdemo-us.modelbest.cn
GitHub - OpenBMB/MiniCPM-o: MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone
MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone - OpenBMB/MiniCPM-o
github.com
January 14, 2025 at 6:49 PM
- Advanced OCR & video understanding
- Offline iPad-compatible multimodal live streaming
Repo: github.com/OpenBMB/Mini...
Models: huggingface.co/openbmb/Mini...
Demo: minicpm-omni-webdemo-us.modelbest.cn
- Offline iPad-compatible multimodal live streaming
Repo: github.com/OpenBMB/Mini...
Models: huggingface.co/openbmb/Mini...
Demo: minicpm-omni-webdemo-us.modelbest.cn
