Shichao Song

Ki-Seki's activity

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

updated a dataset about 10 hours ago

Sculpt-AI/GIMBench-cv-parse

Viewer • Updated about 10 hours ago • 43

published a dataset about 10 hours ago

Sculpt-AI/GIMBench-cv-parse

Viewer • Updated about 10 hours ago • 43

New activity in Qwen/Qwen3-1.7B 4 days ago

Qwen3-1.7B does not reliably enter assistant role without explicit generation prompt, unlike Qwen3-4B

👀 1

#17 opened 4 days ago by

Ki-Seki

updated a dataset 2 months ago

Sculpt-AI/random-articles

Viewer • Updated Nov 17, 2025 • 3.75k • 6

published a dataset 2 months ago

Sculpt-AI/random-articles

Viewer • Updated Nov 17, 2025 • 3.75k • 6

upvoted a paper 3 months ago

HaluMem: Evaluating Hallucinations in Memory Systems of Agents

Paper • 2511.03506 • Published Nov 5, 2025 • 94

updated a dataset 4 months ago

Ki-Seki/GAIR_lima

Viewer • Updated Sep 18, 2025 • 1.33k • 8

published a dataset 4 months ago

Ki-Seki/GAIR_lima

Viewer • Updated Sep 18, 2025 • 1.33k • 8

authored 3 papers 6 months ago

SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model

Paper • 2501.18636 • Published Jan 28, 2025 • 31

MemOS: A Memory OS for AI System

Paper • 2507.03724 • Published Jul 4, 2025 • 159

MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models

Paper • 2505.22101 • Published May 28, 2025

upvoted a paper 7 months ago

MemOS: A Memory OS for AI System

Paper • 2507.03724 • Published Jul 4, 2025 • 159

liked a dataset 7 months ago

wdndev/webnovel-chinese

Viewer • Updated Apr 4, 2024 • 601k • 132 • 28

updated a dataset 8 months ago

Ki-Seki/mem_cube_2

Viewer • Updated Jun 13, 2025 • 2 • 23

published a dataset 8 months ago

Ki-Seki/mem_cube_2

Viewer • Updated Jun 13, 2025 • 2 • 23

liked a dataset 9 months ago

stochastic/random_streetview_images_pano_v0.0.2

Viewer • Updated Oct 14, 2022 • 11.1k • 305 • 23

upvoted a paper 10 months ago

xVerify: Efficient Answer Verifier for Reasoning Model Evaluations

Paper • 2504.10481 • Published Apr 14, 2025 • 85

updated a Space 10 months ago

Running

6

FineWeb：大规模提炼网页以获取优质文本数据

🍷

6

upvoted a collection 10 months ago

xVerify

Collection

15 items • Updated Dec 3, 2025 • 13

authored a paper 11 months ago

SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models

Paper • 2503.07605 • Published Mar 10, 2025 • 66