Hengxiang Zhang

hxiang's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model 7 days ago

hxiang/olmo3-7b-GRPO-step-450

7B • Updated 7 days ago • 9

published a model 8 days ago

hxiang/olmo3-7b-GRPO-step-450

7B • Updated 7 days ago • 9

liked a Space 10 days ago

Running

Agents

21

ChineseSafe

🌍

21

Explore Chinese LLM safety benchmarks

upvoted a paper 10 months ago

Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense

Paper • 2510.07242 • Published Oct 8, 2025 • 30

upvoted 3 papers 11 months ago

Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding

Paper • 2509.23050 • Published Sep 27, 2025 • 15

Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment

Paper • 2509.23564 • Published Sep 28, 2025 • 8

LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals

Paper • 2509.21875 • Published Sep 26, 2025 • 10

updated a model 11 months ago

SUSTech/Reasoner

Updated Sep 15, 2025

updated a Space about 1 year ago

Running

Agents

21

ChineseSafe

🌍

21

Explore Chinese LLM safety benchmarks

published a model about 1 year ago

SUSTech/Reasoner

Updated Sep 15, 2025

published a dataset about 1 year ago

hxiang/PrivacySafety

Updated Jul 15, 2025 • 11

New activity in SUSTech/ChineseSafe-Benchmark about 1 year ago

hongfu_test_20250701

#18 opened about 1 year ago by

hxiang

feat: update new models

#15 opened about 1 year ago by

Jerry0723

hongfu_update_20250701

#19 opened about 1 year ago by

Jerry0723

hongfu_update_20250701

#11 opened about 1 year ago by

Jerry0723

update_LLM_20250701_hongfu

#8 opened about 1 year ago by

Jerry0723

Updata_LLMs_Hongfu

#7 opened about 1 year ago by

Jerry0723

test

#12 opened about 1 year ago by

Jerry0723

Upload chinese_benchmark_gen.csv

#13 opened about 1 year ago by

Jerry0723

Upload 2 files

#14 opened about 1 year ago by

Jerry0723