Seunghyuk Oh
JakeOh
AI & ML interests
None yet
Recent Activity
authored a paper 2 days ago
AsyncOPD: How Stale Can On-Policy Distillation Be? authored a paper 2 days ago
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts authored a paper 2 days ago
ParallelBench: Understanding the Trade-offs of Parallel Decoding in
Diffusion LLMsOrganizations
models 47
JakeOh/research-template-models
Updated
JakeOh/llada-1.0-s1
Updated • 5
JakeOh/LLaDA-8B-Instruct-fixed
Feature Extraction • 8B • Updated • 5
JakeOh/llada-1.0-sft-gsm8k
Text Generation • Updated • 5
JakeOh/llada10sft
Updated
JakeOh/LLaDA-Tiny
Feature Extraction • 17.7M • Updated • 11
JakeOh/LLaDA-1.5-fixed
Feature Extraction • 8B • Updated • 6
JakeOh/llada_1.5-addition
Updated
JakeOh/gpt2-tokenizer-bert-processing
Updated
JakeOh/llada-70m
Updated • 1
datasets 39
JakeOh/research-template-datasets
Updated • 14
JakeOh/proj-dllm-sft-lm-eval-results-private
Viewer • Updated • 2 • 16
JakeOh/lm-eval-results-private
Updated • 13
JakeOh/proj-dllm-sft
Viewer • Updated • 6.83M • 286
JakeOh/MetaMathQA
Viewer • Updated • 334k • 63
JakeOh/rejection-sampling-llada-1.0-sft-gsm8k
Viewer • Updated • 5.59k • 236
JakeOh/addition-dataset
Viewer • Updated • 3M • 1.49k
JakeOh/dllm-bench
Viewer • Updated • 326k • 250
JakeOh/debug
Updated • 6
JakeOh/fineweb-edu-10BT
Viewer • Updated • 52 • 11