arxiv:2606.16285
Jiangze Yan
Kadins
·
AI & ML interests
Main areas of interest include large language models and multimodal models.
Recent Activity
authored a paper about 19 hours ago
DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models authored a paper about 21 hours ago
HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents authored a paper about 21 hours ago
HEAL: Hindsight Entropy-Assisted Learning for Reasoning DistillationOrganizations
models 8
Kadins/deepseek-r1-32b-dapo-0702
Text Generation • 33B • Updated • 1
Kadins/DeepSeek-R1-Distill-Qwen-7B-GRPO
Text Generation • 8B • Updated • 2
Kadins/Qwen-2.5-7B-Math-RL
Text Generation • 8B • Updated • 7
Kadins/Qwen-2.5-7B-Instruct-GRPO
Text Generation • 15B • Updated • 8
Kadins/Qwen-2.5-7B-Simple-RL
Text Generation • 8B • Updated • 4
Kadins/Llama-3.2-3B-LongCoT
Text Generation • 3B • Updated • 3
Kadins/Llama-3.2-Vision-chinese-lora
Image-Text-to-Text • Updated • 4 • 12
Kadins/BiliBot-7B-Q
1B • Updated • 5 • 3
datasets 0
None public yet