yuyijiong

yuyijiong's activity

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

upvoted a paper about 23 hours ago

EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?

Paper • 2610.04184 • Published 10 days ago • 22

upvoted a collection about 2 months ago

🤏 Smol-Data

Collection

Tried and tested mixes for strong pretraining. Inspired by https://huggingface.co/blog/codelion/optimal-dataset-mixing • 14 items • Updated Mar 2 • 21

upvoted 2 papers 5 months ago

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs

Paper • 2605.24202 • Published May 22 • 19

MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning

Paper • 2605.14212 • Published May 14 • 20

upvoted 2 papers 7 months ago

Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms

Paper • 2603.28489 • Published Mar 30 • 28

Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio

Paper • 2603.25926 • Published Mar 26 • 6

upvoted a paper 10 months ago

mHC: Manifold-Constrained Hyper-Connections

Paper • 2512.24880 • Published Dec 31, 2025 • 340

upvoted 2 collections 10 months ago

Qualcomm NPU

Collection

Latest SOTA models supported on Qualcomm NPU. • 32 items • Updated Mar 2 • 15

Sliding Window Attention Adaptation

Collection

3 items • Updated Dec 15, 2025 • 1

upvoted a paper 10 months ago

Sliding Window Attention Adaptation

Paper • 2512.10411 • Published Dec 11, 2025 • 21

upvoted a paper over 1 year ago

Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence

Paper • 2503.20533 • Published Mar 26, 2025 • 12

upvoted a paper almost 2 years ago

OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training

Paper • 2501.08197 • Published Jan 14, 2025 • 9

upvoted a collection almost 2 years ago

high-quality Chinese training datasets

Collection

a suite of high-quality Chinese datasets, used for pretraining, fine-tuning or preference alignment. And the models trained on these datasets. • 13 items • Updated May 22, 2025 • 24

upvoted 2 papers almost 2 years ago

Qwen2.5 Technical Report

Paper • 2412.15115 • Published Dec 19, 2024 • 381

LLMs Do Not Think Step-by-step In Implicit Reasoning

Paper • 2411.15862 • Published Nov 24, 2024 • 9

upvoted a collection almost 2 years ago

Chinese pretrain datasets

Collection

3 items • Updated Nov 26, 2024 • 1

upvoted a paper almost 2 years ago

Patience Is The Key to Large Language Model Reasoning

Paper • 2411.13082 • Published Nov 20, 2024 • 7

upvoted a paper about 2 years ago

Hyper-multi-step: The Truth Behind Difficult Long-context Tasks

Paper • 2410.04422 • Published Oct 6, 2024 • 7

upvoted a collection about 2 years ago

Qwen2-Math

Collection

Math-specific model series based on Qwen2 • 7 items • Updated Mar 2 • 53

upvoted a collection over 2 years ago

MAmmoTH

Collection

The datasets and models for the MAmmoTH project • 9 items • Updated Apr 19, 2024 • 3