arxiv:2504.17192
minju
iaminju
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
16 days ago
Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for
MLLMs
upvoted
a
paper
21 days ago
When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs
upvoted
a
paper
29 days ago
ACON: Optimizing Context Compression for Long-horizon LLM Agents
Organizations
models
13
iaminju/rlpvr_pref_only
2B
•
Updated
iaminju/rlpvr_math_only
2B
•
Updated
•
2
iaminju/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_sample_83k_3
Updated
iaminju/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_sample_83k_2
2B
•
Updated
•
1
iaminju/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_sample_83k
2B
•
Updated
iaminju/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_sample_10k
Text Generation
•
2B
•
Updated
iaminju/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_sample_1k
Text Generation
•
2B
•
Updated
iaminju/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_nq_s_pref
Text Generation
•
2B
•
Updated
iaminju/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_pref
Text Generation
•
2B
•
Updated
iaminju/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_math_nq_s
Updated