FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion
Paper
•
2405.04883
•
Published
ZiangZhang
Viglong
AI & ML interests
None yet
Recent Activity
liked
a Space
21 days ago
HuggingFaceFW/blogpost-fineweb-v1
liked
a Space
21 days ago
nanotron/ultrascale-playbook
liked
a model
21 days ago
HuggingFaceTB/SmolLM3-3B
Organizations
None yet
authored
8
papers
about 1 month ago
OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces
Paper
•
2407.11895
•
Published
•
7
WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling
Paper
•
2408.16532
•
Published
•
50
MuVi: Video-to-Music Generation with Semantic Alignment and Rhythmic Synchronization
Paper
•
2410.12957
•
Published
•
9
Depth Anything with Any Prior
Paper
•
2505.10565
•
Published
•
12
OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup
Paper
•
2410.21269
•
Published
APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization
Paper
•
2506.21655
•
Published
DSI-Bench: A Benchmark for Dynamic Spatial Intelligence
Paper
•
2510.18873
•
Published
•
8