Jack
codeplay
·
AI & ML interests
None yet
Organizations
None yet
papers
-
Statistical Rejection Sampling Improves Preference Optimization
Paper • 2309.06657 • Published • 15 -
In-Context Learning Creates Task Vectors
Paper • 2310.15916 • Published • 42 -
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 66 -
Make Your LLM Fully Utilize the Context
Paper • 2404.16811 • Published • 54
diffusion
leader_boards
- Running on CPU UpgradeAgentsFeatured1.53k
Open ASR Leaderboard
🏆1.53kExplore speech‑recognition model performance across datasets
- Running on CPU UpgradeFeatured991
TTS Arena V2
🗣991Rank text‑to‑speech voices via blind A/B listening
-
lj1995/VoiceConversionWebUI
Updated • 1.24k - Build errorAgents294
GenAI Arena
📈294Realtime Image/Video Gen AI Arena
video
text-to-video
dataset
llm
voice
-
lj1995/VoiceConversionWebUI
Updated • 1.24k - Running on ZeroAgents3.82k
Live Portrait
🤪3.82kApply the motion of a video on a portrait
-
hexgrad/Kokoro-82M
Text-to-Speech • Updated • 12.5M • • 7.39k - Running109
MiniMax Speech Tech Report
🎙109Generate natural speech in any voice and language instantly
img-to-3d
text-to-video
papers
-
Statistical Rejection Sampling Improves Preference Optimization
Paper • 2309.06657 • Published • 15 -
In-Context Learning Creates Task Vectors
Paper • 2310.15916 • Published • 42 -
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 66 -
Make Your LLM Fully Utilize the Context
Paper • 2404.16811 • Published • 54
dataset
diffusion
llm
leader_boards
- Running on CPU UpgradeAgentsFeatured1.53k
Open ASR Leaderboard
🏆1.53kExplore speech‑recognition model performance across datasets
- Running on CPU UpgradeFeatured991
TTS Arena V2
🗣991Rank text‑to‑speech voices via blind A/B listening
-
lj1995/VoiceConversionWebUI
Updated • 1.24k - Build errorAgents294
GenAI Arena
📈294Realtime Image/Video Gen AI Arena
voice
-
lj1995/VoiceConversionWebUI
Updated • 1.24k - Running on ZeroAgents3.82k
Live Portrait
🤪3.82kApply the motion of a video on a portrait
-
hexgrad/Kokoro-82M
Text-to-Speech • Updated • 12.5M • • 7.39k - Running109
MiniMax Speech Tech Report
🎙109Generate natural speech in any voice and language instantly
video