Dehai Min

ZhishanQ's activity

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

upvoted a paper 1 day ago

ALoDLM: Adaptively Looped Diffusion Language Models

Paper • 2610.04198 • Published 5 days ago • 62

upvoted 2 papers 5 days ago

Decoding Looped Transformers Better for (Almost) Free

Paper • 2610.02185 • Published 7 days ago • 45

X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization

Paper • 2609.32993 • Published 12 days ago • 76

upvoted 3 papers 9 days ago

TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent

Paper • 2609.27277 • Published 15 days ago • 33

LastOPD: Taming Collapse in Latent On-Policy Distillation

Paper • 2609.28845 • Published 15 days ago • 30

TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces

Paper • 2609.33295 • Published 11 days ago • 72

upvoted a paper 22 days ago

RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments

Paper • 2609.15364 • Published 24 days ago • 84

upvoted a paper about 2 months ago

LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers

Paper • 2608.06867 • Published Aug 7 • 114

upvoted an article about 2 months ago

view article

Article

FineBooks: are open OCR models good enough to unlock historical knowledge?

• 

finebooks

•

Aug 10

• 26

upvoted a paper 2 months ago

Weak-to-Strong On-Policy Distillation

Paper • 2607.26246 • Published Jul 28 • 59

upvoted a collection 3 months 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 • 2

upvoted a paper 4 months ago

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

Paper • 2605.29648 • Published May 28 • 8

upvoted 2 papers 5 months 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

upvoted a collection 5 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 • 13 items • Updated Aug 11 • 108

upvoted a paper 7 months ago

Arcee Trinity Large Technical Report

Paper • 2602.17004 • Published Feb 19 • 22

upvoted 2 collections 8 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 20 days ago • 42

Qwen3

Collection

84 items • Updated Dec 31, 2025 • 1.87k

upvoted 2 papers 8 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