Dehai Min

ZhishanQ's activity

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

authored a paper 25 days ago

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models

Paper • 2605.17672 • Published May 17 • 23

upvoted a paper 28 days ago

Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering

Paper • 2605.29648 • Published 29 days ago • 10

submitted a paper to Daily Papers 28 days ago

Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering

Paper • 2605.29648 • Published 29 days ago • 10

updated a collection about 1 month ago

PUMA

Collection

The official repository of the paper: Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models • 3 items • Updated May 25 • 1

published a dataset about 1 month ago

ZhishanQ/puma-rd-training-data

Viewer • Updated May 25 • 484k • 92 • 1

updated a dataset about 1 month ago

ZhishanQ/puma-rd-training-data

Viewer • Updated May 25 • 484k • 92 • 1

updated a model about 1 month ago

ZhishanQ/qwen3-embedding-redundancy-detector-0.6B

Sentence Similarity • 0.6B • Updated May 25 • 18

published a model about 1 month ago

ZhishanQ/qwen3-embedding-redundancy-detector-0.6B

Sentence Similarity • 0.6B • Updated May 25 • 18

upvoted 2 papers about 1 month ago

Lance: Unified Multimodal Modeling by Multi-Task Synergy

Paper • 2605.18678 • Published May 18 • 79

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models

Paper • 2605.17672 • Published May 17 • 23

submitted a paper to Daily Papers about 1 month ago

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models

Paper • 2605.17672 • Published May 17 • 23

upvoted a collection about 2 months ago

Nemotron RAG

Collection

Set of tools to build retrieval-augmented generation (RAG) systems, improve search and ranking accuracy, and extract structured data from complex docs • 11 items • Updated 14 days ago • 93

upvoted a paper 3 months ago

Arcee Trinity Large Technical Report

Paper • 2602.17004 • Published Feb 19 • 21

liked a model 3 months ago

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8

Text Generation • 124B • Updated Apr 29 • 380k • 262

upvoted 2 collections 4 months ago

jina-embeddings-v5-text

Collection

Our 5th-gen embeddings: two lightweight multilingual models with SOTA performance in retrieval, matching, clustering, and classification. • 29 items • Updated Feb 27 • 40

Qwen3

Collection

84 items • Updated Dec 31, 2025 • 1.82k

upvoted 2 papers 4 months ago

When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning

Paper • 2602.10560 • Published Feb 11 • 31

TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning

Paper • 2601.21135 • Published Jan 29 • 8