Junxiao Yang

yangjunxiao2021's activity

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

authored a paper 2 days ago

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

Paper • 2604.12710 • Published 6 days ago • 5

upvoted a paper 3 days ago

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

Paper • 2604.12710 • Published 6 days ago • 5

submitted a paper to Daily Papers 3 days ago

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

Paper • 2604.12710 • Published 6 days ago • 5

upvoted an article 12 days ago

view article

Article

Uncensor any LLM with abliteration

• 

Jun 13, 2024

•

844

upvoted a paper about 2 months ago

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

Paper • 2602.24286 • Published Feb 27 • 98

liked a dataset 2 months ago

ronantakizawa/moltbook

Viewer • Updated Feb 2 • 6.23k • 353 • 55

updated a model 3 months ago

yangjunxiao2021/safe_unlearning

Updated Jan 23

published a model 3 months ago

yangjunxiao2021/safe_unlearning

Updated Jan 23

liked a dataset 3 months ago

simon123905/ICLR

Updated Jan 17 • 190 • 4

updated a model 3 months ago

yangjunxiao2021/LASA_Models

Updated Jan 18

published a model 3 months ago

yangjunxiao2021/LASA_Models

Updated Jan 18

upvoted a paper 5 months ago

HaluMem: Evaluating Hallucinations in Memory Systems of Agents

Paper • 2511.03506 • Published Nov 5, 2025 • 95

upvoted 3 papers 6 months ago

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Paper • 2510.25726 • Published Oct 29, 2025 • 46

DeepAgent: A General Reasoning Agent with Scalable Toolsets

Paper • 2510.21618 • Published Oct 24, 2025 • 103

The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

Paper • 2509.09677 • Published Sep 11, 2025 • 37

upvoted an article 6 months ago

view article

Article

DABStep: Data Agent Benchmark for Multi-step Reasoning

• 
• 
• +5

Feb 4, 2025

•

128

upvoted a paper 6 months ago

It Takes Two: Your GRPO Is Secretly DPO

Paper • 2510.00977 • Published Oct 1, 2025 • 32

upvoted a collection 6 months ago

Agent & RL

Collection

55 items • Updated Nov 27, 2025 • 21

upvoted 2 papers 6 months ago

Glyph: Scaling Context Windows via Visual-Text Compression

Paper • 2510.17800 • Published Oct 20, 2025 • 69

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning

Paper • 2510.15444 • Published Oct 17, 2025 • 151