The official repository of the paper: Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models
Dehai Min
ZhishanQ
AI & ML interests
PhD@UIC | NLP, LLM
Recent Activity
upvoted a paper about 2 hours ago
TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent upvoted a paper about 2 hours ago
LastOPD: Taming Collapse in Latent On-Policy Distillation upvoted a paper about 2 hours ago
TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment TracesOrganizations
models 6
ZhishanQ/qwen3-embedding-redundancy-detector-0.6B
Sentence Similarity • 0.6B • Updated • 401
ZhishanQ/QuCo-extractor-0.5B
Text Generation • 0.5B • Updated • 63
ZhishanQ/UniHGKR-7B
Feature Extraction • 7B • Updated • 9
ZhishanQ/UniHGKR-base-beir
Sentence Similarity • 0.1B • Updated • 96
ZhishanQ/UniHGKR-base
Sentence Similarity • 0.1B • Updated • 98
ZhishanQ/UniHGKR-7B-pretrained
Feature Extraction • 7B • Updated • 6
datasets 6
ZhishanQ/puma-rd-training-data
Viewer • Updated • 484k • 64 • 1
ZhishanQ/QuCo-RAG-es-data-archive
Updated • 14
ZhishanQ/UniHGKR_eval_data
Updated • 20
ZhishanQ/UniHGKR_training_data
Preview • Updated • 37
ZhishanQ/UniHGKR_Date_Text_Pairs
Viewer • Updated • 4.33M • 18 • 1
ZhishanQ/CompMix-IR
Updated • 15