OmniAudio: Generating Spatial Audio from 360-Degree Video
Paper
β’
2504.14906
β’
Published
MeissonFlow Research
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
MeissonFlow's activity
LXTΒ
authored
9
papers
4 days ago
Towards Semantic Equivalence of Tokenization in Multimodal LLM
Paper
β’
2406.05127
β’
Published
So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection
Paper
β’
2505.18660
β’
Published
β’
1
PixelThink: Towards Efficient Chain-of-Pixel Reasoning
Paper
β’
2505.23727
β’
Published
β’
4
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
Paper
β’
2505.23606
β’
Published
β’
14
Conditional Panoramic Image Generation via Masked Autoregressive Modeling
Paper
β’
2505.16862
β’
Published
MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
Paper
β’
2506.03144
β’
Published
β’
3
BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation
Paper
β’
2505.12620
β’
Published
CyberV: Cybernetics for Test-time Scaling in Video Understanding
Paper
β’
2506.07971
β’
Published
β’
4
LXTΒ
authored
a
paper
10 days ago
WeiChowΒ
authored
a
paper
11 days ago
BryanWΒ
authored
a
paper
16 days ago
QingyuShiΒ
authored
a
paper
16 days ago
WeiChowΒ
updated
a
dataset
about 1 month ago
LXTΒ
authored
a
paper
about 1 month ago
QingyuShiΒ
authored
a
paper
about 1 month ago
LXTΒ
authored
a
paper
about 2 months ago
Post
1216
π Introducing Video-MMLU, a new benchmark for evaluating large multimodal models on classroom-style lectures in math, physics, and chemistry!
π§βπ«πVideo-MMLU requires strong reasoning capabilities and world knowledge compared to the previous benchmarks for video LMMs.
Each video comes with two tasks:
π Take Notes β detailed captioning of multi-discipline lectures
π§ Do Quiz β open-ended QA to test reasoning over visuals & proofs
We evaluated 90+ models, including vision-blind baselines, open-source models and proprietary ones.
π We find that existing models generally perform poorly, with accuracy ranging from only 10% to 50%.
πWe also explore how the number of visual tokens and the base LLMs influence performance, offering insights into the interplay between multimodal perception and reasoning in lecture comprehension.
For more details, please check belowοΌ
π Paper: https://arxiv.org/abs/2504.14693
π» Code: https://github.com/Espere-1119-Song/Video-MMLU
π§ Data: Enxin/Video-MMLU
π Website: https://enxinsong.com/Video-MMLU-web/
π§βπ«πVideo-MMLU requires strong reasoning capabilities and world knowledge compared to the previous benchmarks for video LMMs.
Each video comes with two tasks:
π Take Notes β detailed captioning of multi-discipline lectures
π§ Do Quiz β open-ended QA to test reasoning over visuals & proofs
We evaluated 90+ models, including vision-blind baselines, open-source models and proprietary ones.
π We find that existing models generally perform poorly, with accuracy ranging from only 10% to 50%.
πWe also explore how the number of visual tokens and the base LLMs influence performance, offering insights into the interplay between multimodal perception and reasoning in lecture comprehension.
For more details, please check belowοΌ
π Paper: https://arxiv.org/abs/2504.14693
π» Code: https://github.com/Espere-1119-Song/Video-MMLU
π§ Data: Enxin/Video-MMLU
π Website: https://enxinsong.com/Video-MMLU-web/
LXTΒ
authored
a
paper
about 2 months ago
QingyuShiΒ
authored
a
paper
about 2 months ago