arxiv:2610.08430
🤝 Open to Collab
Songlin Jiang
HollowMan6
P(doom) 10%
AI & ML interests
AI Infrastructure, Reinforcement Learning
Recent Activity
upvoted a paper about 6 hours ago
Learning Discriminative Geometry for Drifting Models authored a paper about 10 hours ago
NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale upvoted a paper about 11 hours ago
NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter ScaleOrganizations
None yet
models 15
HollowMan6/GLM-5-NOOP-LoRA
Text Generation • Updated • 12
HollowMan6/CodeLlama-34B-HF-RM-Mixture2_and_Safe_PKU
13B • Updated • 6
HollowMan6/CodeLlama-34B-HF-SFT-Model-Ocra-500k
34B • Updated • 6
HollowMan6/CodeLlama-13B-HF-RM-Mixture2_and_Safe_PKU
13B • Updated • 2
HollowMan6/CodeLlama-13B-HF-SFT-Model-Ocra-500k
13B • Updated • 6
HollowMan6/Llama-3.2-3B-RM-Mixture2_and_Safe_PKU
3B • Updated • 6
HollowMan6/Llama-3.2-1B-RM-Mixture2_and_Safe_PKU
1B • Updated • 5
HollowMan6/Llama-3-70B-RM-Mixture2_and_Safe_PKU
70B • Updated • 4
HollowMan6/Llama-3.1-70B-RM-Mixture2_and_Safe_PKU
70B • Updated • 6
HollowMan6/Llama-3.2-1B-SFT-Model-Ocra-500k
1B • Updated • 5
datasets 0
None public yet