kcz

kcz358's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 4 days ago

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

Paper • 2607.24904 • Published Jul 27 • 37

authored a paper 28 days ago

Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation

Paper • 2608.08469 • Published Aug 9 • 2

upvoted a paper 28 days ago

VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning

Paper • 2608.26105 • Published about 1 month ago • 190

updated a collection about 1 month ago

Aero-Realtime

Collection

4 items • Updated about 1 month ago

upvoted a paper about 1 month ago

Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation

Paper • 2608.08469 • Published Aug 9 • 2

authored a paper about 1 month ago

StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding

Paper • 2608.16320 • Published Aug 17 • 9

upvoted a paper about 1 month ago

StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding

Paper • 2608.16320 • Published Aug 17 • 9

updated a collection about 1 month ago

Aero-Realtime

Collection

4 items • Updated about 1 month ago

updated a dataset about 1 month ago

kcz358/aero-realtime-data

Preview • Updated Aug 13 • 118

updated a model about 1 month ago

kcz358/aero-realtime-4B

Video-Text-to-Text • 5B • Updated Aug 13 • 186 • 10

liked a Space about 1 month ago

Running on Zero

Agents

4

Aero Realtime 4B

📺

4

Proactive real-time commentary on audio-video streams

New activity in kcz358/aero-realtime-4B about 1 month ago

Demo for this model on Spaces

2

#1 opened about 1 month ago by

multimodalart

published a model about 2 months ago

kcz358/aero-realtime-4B

Video-Text-to-Text • 5B • Updated Aug 13 • 186 • 10

New activity in microsoft/Mage-VL about 2 months ago

Fix <|image_pad|> misalignment when images= and videos= coexist

#3 opened about 2 months ago by

kcz358

upvoted a paper about 2 months ago

HumanCLAW: Can Vision-Language Models Act Through a Body?

Paper • 2607.27180 • Published Jul 29 • 76

published a dataset about 2 months ago

kcz358/aero-realtime-data

Preview • Updated Aug 13 • 118

New activity in microsoft/Mage-VL about 2 months ago

docs: add install-free Transformers usage section

#2 opened about 2 months ago by

kcz358

upvoted a paper about 2 months ago

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

Paper • 2607.24904 • Published Jul 27 • 37