Ziheng Li's picture

Ziheng Li

ChillingDream

·

ChillingDream

AI & ML interests

Natural Language Processing

Recent Activity

authored a paper about 8 hours ago

To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models

authored a paper about 8 hours ago

LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks

authored a paper about 8 hours ago

Trust Region On-Policy Distillation

View all activity

Organizations

None yet

Papers 7

arxiv:2606.03197

arxiv:2606.01249

arxiv:2604.13072

arxiv:2602.12566

models 4

ChillingDream/sft-3B

3B • Updated Mar 25 • 3

ChillingDream/sft-Math-7B

8B • Updated Mar 25 • 4

ChillingDream/dap-xlm-roberta-base

Feature Extraction • 0.3B • Updated Jan 12, 2025 • 9

ChillingDream/dap-mbert-base

Feature Extraction • 0.2B • Updated Jan 12, 2025 • 6

datasets 0

None public yet