1 455 1061

jiakai

real-jiakai

https://blog.gujiakai.top

AI & ML interests

LLM && Smart QA

Recent Activity

liked a model 3 days ago

PokeeAI/pokee_research_7b

liked a model 3 days ago

mirth/chonky_mmbert_small_multilingual_1

upvoted a paper 4 days ago

LightMem: Lightweight and Efficient Memory-Augmented Generation

View all activity

Organizations

upvoted a paper 4 days ago

LightMem: Lightweight and Efficient Memory-Augmented Generation

Paper • 2510.18866 • Published 5 days ago • 101

upvoted a paper 5 days ago

DeepAnalyze: Agentic Large Language Models for Autonomous Data Science

Paper • 2510.16872 • Published 7 days ago • 83

upvoted a paper 6 days ago

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning

Paper • 2510.15444 • Published 10 days ago • 137

upvoted a paper 9 days ago

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Paper • 2510.04849 • Published 20 days ago • 108

upvoted a paper 12 days ago

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Paper • 2510.11696 • Published 13 days ago • 165

upvoted a paper 13 days ago

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Paper • 2510.04618 • Published 21 days ago • 105

upvoted a paper 16 days ago

Agent Learning via Early Experience

Paper • 2510.08558 • Published 17 days ago • 241

upvoted a paper 17 days ago

Cache-to-Cache: Direct Semantic Communication Between Large Language Models

Paper • 2510.03215 • Published 23 days ago • 92

upvoted a paper 19 days ago

Paper2Video: Automatic Video Generation from Scientific Papers

Paper • 2510.05096 • Published 20 days ago • 106

upvoted a paper 20 days ago

Efficient Multi-modal Large Language Models via Progressive Consistency Distillation

Paper • 2510.00515 • Published 26 days ago • 39

upvoted a paper 24 days ago

DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search

Paper • 2509.25454 • Published 27 days ago • 133

upvoted a paper 25 days ago

MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use

Paper • 2509.24002 • Published 28 days ago • 166

upvoted a paper 27 days ago

LongLive: Real-time Interactive Long Video Generation

Paper • 2509.22622 • Published about 1 month ago • 176

upvoted 2 papers 30 days ago

VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models

Paper • 2509.19803 • Published Sep 24 • 117

SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines

Paper • 2509.21320 • Published Sep 25 • 99

upvoted 2 papers about 1 month ago

SIM-CoT: Supervised Implicit Chain-of-Thought

Paper • 2509.20317 • Published Sep 24 • 40

Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR

Paper • 2509.18174 • Published Sep 17 • 124

upvoted a collection about 1 month ago

Qwen3Guard

Collection

7 items • Updated 26 days ago • 53

upvoted a paper about 1 month ago

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

Paper • 2509.16198 • Published Sep 19 • 126

upvoted an article about 1 month ago

Article

Smol2Operator: Post-Training GUI Agents for Computer Use

Sep 23

• 121

jiakai

AI & ML interests

Recent Activity

Organizations

real-jiakai's activity

Smol2Operator: Post-Training GUI Agents for Computer Use