InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions
Paper
•
2412.09596
•
Published
•
91
VLMEval
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
VLMEval's activity
KennyUTC
authored
a
paper
10 days ago
KennyUTC
authored
a
paper
29 days ago
KennyUTC
updated
a
dataset
about 2 months ago
KennyUTC
authored
3
papers
2 months ago
MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models
Paper
•
2410.17637
•
Published
•
34
CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution
Paper
•
2410.16256
•
Published
•
58
ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs
Paper
•
2410.12405
•
Published
•
13
KennyUTC
authored
2
papers
4 months ago
KennyUTC
updated
a
dataset
4 months ago
KennyUTC
authored
a
paper
5 months ago
KennyUTC
authored
a
paper
6 months ago
KennyUTC
updated
a
dataset
6 months ago
KennyUTC
authored
3
papers
6 months ago
MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning
Paper
•
2406.17770
•
Published
•
18
Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs
Paper
•
2406.14544
•
Published
•
34
MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
Paper
•
2406.14515
•
Published
•
32
KennyUTC
updated
a
dataset
6 months ago
KennyUTC
authored
a
paper
7 months ago
Post
1461
OPEN VLM LEADERBOARD JUST RELEASED the FULL EVALUATION RESULTS of GPT-4o
[TL;DR]
GPT-4o shows steady progress compared to GPT-4v (0419), with a 3% improvement on the average score (68.7% -> 72.1%). GPT-4o displays stronger perception and less hallucination.
opencompass/open_vlm_leaderboard
[TL;DR]
GPT-4o shows steady progress compared to GPT-4v (0419), with a 3% improvement on the average score (68.7% -> 72.1%). GPT-4o displays stronger perception and less hallucination.
opencompass/open_vlm_leaderboard
- 1 reply
KennyUTC
authored
2
papers
8 months ago