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 2 days ago
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight upvoted a paper 6 days ago
ALoDLM: Adaptively Looped Diffusion Language Models upvoted a paper 9 days ago
Decoding Looped Transformers Better for (Almost) FreeOrganizations
models 6
ZhishanQ/qwen3-embedding-redundancy-detector-0.6B
Sentence Similarity • 0.6B • Updated • 445
ZhishanQ/QuCo-extractor-0.5B
Text Generation • 0.5B • Updated • 41
ZhishanQ/UniHGKR-7B
Feature Extraction • 7B • Updated • 10
ZhishanQ/UniHGKR-base-beir
Sentence Similarity • 0.1B • Updated • 68
ZhishanQ/UniHGKR-base
Sentence Similarity • 0.1B • Updated • 81
ZhishanQ/UniHGKR-7B-pretrained
Feature Extraction • 7B • Updated • 11
datasets 6
ZhishanQ/puma-rd-training-data
Viewer • Updated • 484k • 66 • 1
ZhishanQ/QuCo-RAG-es-data-archive
Updated • 50
ZhishanQ/UniHGKR_eval_data
Updated • 16
ZhishanQ/UniHGKR_training_data
Preview • Updated • 42
ZhishanQ/UniHGKR_Date_Text_Pairs
Viewer • Updated • 4.33M • 14 • 1
ZhishanQ/CompMix-IR
Updated • 7