How LoRA Remembers? A Parametric Memory Law for LLM Finetuning Paper • 2605.30260 • Published 13 days ago • 42
AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery Paper • 2605.23204 • Published 19 days ago • 29
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards Paper • 2605.10899 • Published 30 days ago • 78
WTF GENIUS PAPERS Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 168 items • Updated about 22 hours ago • 35
δ-mem: Efficient Online Memory for Large Language Models Paper • 2605.12357 • Published 29 days ago • 128
Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling Paper • 2605.13301 • Published 28 days ago • 159
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation Paper • 2605.10813 • Published 30 days ago • 16
MinT: Managed Infrastructure for Training and Serving Millions of LLMs Paper • 2605.13779 • Published 28 days ago • 219
Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning Paper • 2605.00347 • Published May 1 • 16
Hallucinations Undermine Trust; Metacognition is a Way Forward Paper • 2605.01428 • Published May 2 • 24
The Last Human-Written Paper: Agent-Native Research Artifacts Paper • 2604.24658 • Published Apr 29 • 21
Efficient Training on Multiple Consumer GPUs with RoundPipe Paper • 2604.27085 • Published Apr 29 • 46
Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction Paper • 2604.27221 • Published Apr 29 • 39
Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists Paper • 2604.28158 • Published Apr 30 • 49
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration Paper • 2605.03042 • Published May 4 • 130
From Context to Skills: Can Language Models Learn from Context Skillfully? Paper • 2604.27660 • Published May 3 • 166