No items found.
7:30
7:30
9:00
9:10
9:30
9:30
9:45
9:50
10:00
10:15
10:30
10:30
10:30
10:45
10:50
11:00
11:00
11:30
11:30
11:30
11:45
11:50
12:00
12:00
12:15
12:30
12:30
12:45
13:00
13:00
13:30
14:00
14:00
14:00
14:15
14:30
14:40
14:45
15:00
15:00
15:05
15:10
15:15
15:20
15:20
15:25
15:30
15:30
15:35
15:40
15:40
15:45
15:50
15:55
16:00
16:00
16:20
16:30
16:40
16:45
17:00
17:10
17:15
17:30
17:30
17:35
18:00
7:30
9:00
9:10
9:30
9:30
9:50
10:00
10:00
10:10
10:15
10:30
10:30
10:50
11:00
11:00
11:05
11:10
11:15
11:25
11:30
11:35
11:45
11:50
11:55
12:00
12:15
12:30
12:30
12:45
13:00
13:00
13:00
14:00
14:00
14:00
14:15
14:30
14:30
14:40
14:45
15:00
15:10
15:15
15:30
15:30
15:40
15:45
16:00
16:00
16:00
16:15
16:30
16:30
16:45
17:00
17:00
17:10
17:15
17:30
17:35
17:40
17:40
17:45
17:50
17:50
17:55
18:00
18:00
Go back to Agenda
Thu
11 Jun
2:00 pm
-
2:15 pm

Emergent Trends in Large Multimodal Models

This talk highlights the three emerging trends in Large Multimodal Models: encoder-free unified architectures, spatial intelligence, and video reasoning. Together, these developments are reshaping how multimodal systems perceive, understand, and reason about the world.

15 min
WEKA Stage

About

This talk highlights the three emerging trends in Large Multimodal Models: encoder-free unified architectures, spatial intelligence, and video reasoning. Together, these developments are reshaping how multimodal systems perceive, understand, and reason about the world.

Powered By

Speakers

3D wireframe model of a human brain in gray on a white background.
Zhongang Cai
Principal Research Scientist
SenseTime
LLMs (Large Language Models)

Moderator

No items found.
Previous Session
Previous
Next Session
Next
All tickets sold out

Ticket sales now closed

SuperAI KV key visual