TransMamba: Flexibly Switching between Transformer and Mamba
Paper
ā¢
2503.24067
ā¢
Published
ā¢
14
Dmitry Ryumin
DmitryRyumin
AI & ML interests
Machine Learning and Applications, Multi-Modal Understanding
Recent Activity
upvoted
a
paper
2 days ago
TransMamba: Flexibly Switching between Transformer and Mamba
liked
a Space
3 days ago
openfree/Llama-4-Scout-17B-Research
upvoted
an
article
3 days ago
Welcome Llama 4 Maverick & Scout on Hugging Face!
Organizations
DmitryRyumin's activity
upvoted
a
paper
2 days ago
liked
a
Space
3 days ago
upvoted
an
article
3 days ago
Article
Welcome Llama 4 Maverick & Scout on Hugging Face!
ā¢
137
liked
a
dataset
7 days ago
upvoted
a
paper
8 days ago
reacted to
AdinaY's
post with š„
10 days ago
Post
1914
AReal-Boba š„ a fully open RL Frameworks released by AntGroup, an affiliate company of Alibaba.
inclusionAI/areal-boba-67e9f3fa5aeb74b76dcf5f0a
āØ 7B/32B - Apache2.0
āØ Outperform on math reasoning
āØ Replicating QwQ-32B with 200 data under $200
āØ All-in-one: weights, datasets, code & tech report
inclusionAI/areal-boba-67e9f3fa5aeb74b76dcf5f0a
āØ 7B/32B - Apache2.0
āØ Outperform on math reasoning
āØ Replicating QwQ-32B with 200 data under $200
āØ All-in-one: weights, datasets, code & tech report
- 1 reply
liked
a
Space
10 days ago
updated
a
collection
15 days ago
commented
a
paper
15 days ago
liked
a
model
16 days ago
upvoted
a
collection
16 days ago
liked
a
model
16 days ago
updated
a
collection
17 days ago
upvoted
2
papers
17 days ago
TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting
Paper
ā¢
2503.17032
ā¢
Published
ā¢
23
MAPS: A Multi-Agent Framework Based on Big Seven Personality and Socratic Guidance for Multimodal Scientific Problem Solving
Paper
ā¢
2503.16905
ā¢
Published
ā¢
53
liked
2
Spaces
21 days ago
liked
a
Space
22 days ago
reacted to
KaiChen1998's
post with š
25 days ago
Post
4815
š¢ Our EMOVA paper has been accepted by CVPR 2025, and we are glad to release all resources, including code (training & inference), datasets (training & evaluation), and checkpoints (EMOVA-3B/7B/72B)!
š¤ EMOVA is a novel end-to-end omni-modal LLM that can see, hear and speak. Given omni-modal (i.e., textual, visual and speech) inputs, EMOVA can generate both textual and speech responses with vivid emotional controls by utilizing the speech decoder and a style controller.
āØ EMOVA Highlights
ā State-of-the-art omni-modality: EMOVA achieves SoTA comparable results on both vision-language and speech benchmarks simultaneously.
ā Device adaptation: our codebase supports training/inference on both NVIDIA GPUs (e.g., A800 & H20) and Ascend NPUs (e.g., 910B3)!
ā Modular design: we integrate multiple implementations of vision encoder, vision projector, and language model, even including the most recent DeepSeekMoE-tiny!
š„ You are all welcome to try and star!
- Project page: https://emova-ollm.github.io/
- Github: https://github.com/emova-ollm/EMOVA
- Demo: Emova-ollm/EMOVA-demo
š¤ EMOVA is a novel end-to-end omni-modal LLM that can see, hear and speak. Given omni-modal (i.e., textual, visual and speech) inputs, EMOVA can generate both textual and speech responses with vivid emotional controls by utilizing the speech decoder and a style controller.
āØ EMOVA Highlights
ā State-of-the-art omni-modality: EMOVA achieves SoTA comparable results on both vision-language and speech benchmarks simultaneously.
ā Device adaptation: our codebase supports training/inference on both NVIDIA GPUs (e.g., A800 & H20) and Ascend NPUs (e.g., 910B3)!
ā Modular design: we integrate multiple implementations of vision encoder, vision projector, and language model, even including the most recent DeepSeekMoE-tiny!
š„ You are all welcome to try and star!
- Project page: https://emova-ollm.github.io/
- Github: https://github.com/emova-ollm/EMOVA
- Demo: Emova-ollm/EMOVA-demo
liked
a
model
27 days ago
