-
DoPE: Denoising Rotary Position Embedding
Paper • 2511.09146 • Published • 98 -
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
Paper • 2511.19365 • Published • 66 -
Latent Collaboration in Multi-Agent Systems
Paper • 2511.20639 • Published • 130 -
Video Generation Models Are Good Latent Reward Models
Paper • 2511.21541 • Published • 50
JaehoHan
JaehoHan
AI & ML interests
None yet
Recent Activity
upvoted a paper 10 days ago
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs upvoted a paper 20 days ago
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling updated a collection 5 months ago
Interested paperOrganizations
None yet
-
DoPE: Denoising Rotary Position Embedding
Paper • 2511.09146 • Published • 98 -
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
Paper • 2511.19365 • Published • 66 -
Latent Collaboration in Multi-Agent Systems
Paper • 2511.20639 • Published • 130 -
Video Generation Models Are Good Latent Reward Models
Paper • 2511.21541 • Published • 50
models 37
JaehoHan/clip-resnet50-bert-tiny-kt2
Updated
JaehoHan/clip-resnet50-bert-tiny-kt3
Updated
JaehoHan/JaehoHan
Updated
JaehoHan/clip-resnet50-bert-tiny-kt
Updated
JaehoHan/clip-vit-base-12-resnet50
Updated
JaehoHan/clip-vit-base-9-layers-kt
0.1B • Updated • 3
JaehoHan/clip-vit-base-12-layers2
0.2B • Updated • 2
JaehoHan/clip-vit-base-6-layers-kt
89.8M • Updated • 3
JaehoHan/clip-vit-base-9-layers2
0.1B • Updated • 2
JaehoHan/clip-vit-base-3-layers-kt
59.1M • Updated • 2
datasets 0
None public yet