J Li

jiazhengli's activity

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

upvoted a paper 17 days ago

Where does output diversity collapse in post-training?

Paper • 2604.16027 • Published 24 days ago • 22

upvoted 2 papers 3 months ago

Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation

Paper • 2602.02007 • Published Feb 2 • 19

Chain Of Thought Compression: A Theoritical Analysis

Paper • 2601.21576 • Published Jan 29 • 20

commented a paper 6 months ago

SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space

Paper • 2511.20102 • Published Nov 25, 2025 • 28 •

3

authored a paper 6 months ago

SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space

Paper • 2511.20102 • Published Nov 25, 2025 • 28

upvoted a paper 6 months ago

SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space

Paper • 2511.20102 • Published Nov 25, 2025 • 28

liked a Space 6 months ago

Running on CPU Upgrade

Featured

3.16k

The Smol Training Playbook

📚

3.16k

The secrets to building world-class LLMs

updated a dataset 7 months ago

jiazhengli/DARS_synthethsis_reflection

Viewer • Updated Oct 22, 2025 • 43.5k • 38

authored 2 papers 7 months ago

Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time

Paper • 2502.19230 • Published Feb 26, 2025 • 2

EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States

Paper • 2503.03340 • Published Mar 5, 2025 • 1

updated a model 7 months ago

jiazhengli/Qwen2.5-3B-Instruct-Critic

3B • Updated Oct 20, 2025 • 2

updated a collection 7 months ago

DARS

Collection

Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time • 4 items • Updated Oct 22, 2025

updated a model 7 months ago

jiazhengli/Qwen2.5-3B-Instruct-Reasoner

3B • Updated Oct 20, 2025 • 3

published 2 models 7 months ago

jiazhengli/Qwen2.5-3B-Instruct-Critic

3B • Updated Oct 20, 2025 • 2

jiazhengli/Qwen2.5-3B-Instruct-Reasoner

3B • Updated Oct 20, 2025 • 3

updated a collection 7 months ago

DARS

Collection

Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time • 4 items • Updated Oct 22, 2025

published a dataset 7 months ago

jiazhengli/DARS_synthethsis_reflection

Viewer • Updated Oct 22, 2025 • 43.5k • 38

upvoted a paper 7 months ago

Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States

Paper • 2510.11052 • Published Oct 13, 2025 • 52