arxiv:2506.07712
Jiaxi PRO
jxjessieli
·
AI & ML interests
None yet
Recent Activity
authored
a paper
about 10 hours ago
WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale
authored
a paper
about 10 hours ago
Through the Valley: Path to Effective Long CoT Training for Small
Language Models
upvoted
a
paper
16 days ago
SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware
Reinforcement Learning
Organizations
models
21
jxjessieli/llama-3.1_sp35-65-20k_5e-7
Text Generation
•
8B
•
Updated
•
42
jxjessieli/llama-3.1_sp35-65-20k_3e-7
Text Generation
•
8B
•
Updated
•
8
jxjessieli/llama-3.1_wildchat20k_5e-7
Text Generation
•
8B
•
Updated
•
34
jxjessieli/mistral_simple20k_1e-6
Text Generation
•
7B
•
Updated
•
11
jxjessieli/mistral_wildchat20k_1e-6
Text Generation
•
7B
•
Updated
•
7
jxjessieli/llama-3.1_single-graph20k_5e-7
Text Generation
•
8B
•
Updated
•
72
jxjessieli/llama-3.1_multi-graph20k_5e-7
Text Generation
•
8B
•
Updated
•
9
jxjessieli/llama-3.1_single-multi-graph20k_5e-7
Text Generation
•
8B
•
Updated
•
56
jxjessieli/mistral_single-graph20k_1e-6
Text Generation
•
7B
•
Updated
•
13
jxjessieli/mistral_longalign_1e-6
Text Generation
•
7B
•
Updated
•
8
datasets
0
None public yet