shiyang's picture

1 9 4

shiyang

sY713

·

AI & ML interests

None yet

Recent Activity

upvoted a collection 13 days ago

upvoted a paper 13 days ago

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

new activity 17 days ago

openai/frontierscience:Questions about Olympiad evaluation averaging and a possible duplicate task in the Research subset

View all activity

Organizations

upvoted a collection 13 days ago

SGI-Bench

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows • 9 items • Updated 12 days ago • 30

upvoted a paper 13 days ago

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Paper • 2512.16969 • Published 17 days ago • 109

upvoted a paper 5 months ago

CellForge: Agentic Design of Virtual Cell Models

Paper • 2508.02276 • Published Aug 4, 2025 • 39

upvoted 2 papers 7 months ago

Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning

Paper • 2506.10521 • Published Jun 12, 2025 • 73

MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs

Paper • 2505.21327 • Published May 27, 2025 • 83

upvoted a paper 8 months ago

NovelSeek: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification

Paper • 2505.16938 • Published May 22, 2025 • 120

upvoted a paper 10 months ago

SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing

Paper • 2503.04629 • Published Mar 6, 2025 • 19

upvoted a paper 12 months ago

Dolphin: Closed-loop Open-ended Auto-research through Thinking, Practice, and Feedback

Paper • 2501.03916 • Published Jan 7, 2025 • 16

upvoted a collection about 1 year ago

OpenScholar_V1

The set of models, index, data associated with the paper "OpenScholar: Synthesizing Scientific Literature with Retrieval-Augmented LMs". • 8 items • Updated Nov 22, 2024 • 43