arxiv:2601.05242
LIU Shih-yang
sliuau
AI & ML interests
None yet
Recent Activity
liked
a Space
37 minutes ago
dylan-marimo-io/Reward-Policy-Intuition
upvoted
a
paper
about 1 hour ago
Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
authored
a paper
6 days ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Organizations
models
11
sliuau/llama-3.2-3b_4bits_128group_size_eora_rank128_mmlu_c4
Updated
sliuau/llama-3.2-3b_4bits_128group_size_eora_rank64_mmlu_c4
Updated
sliuau/Llama-3.2-3B_4bits_128group_size
Text Generation
•
3B
•
Updated
•
406
sliuau/llama3.2-1b-4bit-group128-eora-rank128-arc-v2
Updated
sliuau/llama3.2-1b-4bit-group128
1B
•
Updated
•
58
sliuau/llama3.2-1b-4bit-group128-eora-rank128-arc
Updated
sliuau/llama3_8b_gptq_w4_eora_arc
Updated
sliuau/llama3_8b_gptq_4bits
Updated
sliuau/llama3_8b_gptq_w3_eora_arc
Updated
sliuau/llama3_8b_gptq_3bits
Updated
•
2
datasets
8
sliuau/DeepScaleR-Preview-Dataset-verl-format
Viewer
•
Updated
•
40.8k
•
15
sliuau/FULL-MATH
Viewer
•
Updated
•
7.5k
•
9
sliuau/c4-val
Viewer
•
Updated
•
45.6k
•
8
sliuau/c4-train
Viewer
•
Updated
•
356k
•
65
sliuau/gsm9k_reasoning_openr1_eval_format
Viewer
•
Updated
•
1.32k
•
5
sliuau/truncated_openr1_math_0.1k
Viewer
•
Updated
•
100
•
3
sliuau/truncated_openr1_math_1k
Viewer
•
Updated
•
1k
•
2
sliuau/c4
Updated
•
1