-
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 225 -
MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU
Paper • 2604.05091 • Published • 44 -
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Paper • 2606.11926 • Published • 79
Malthe August Bordin Bresler
maltheaugust
AI & ML interests
None yet
Recent Activity
updated a collection 24 days ago
Architectures upvoted a paper 29 days ago
Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement updated a collection 29 days ago
ArchitecturesOrganizations
None yet
Architectures
-
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 520 -
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain
Paper • 2509.26507 • Published • 558 -
LightMem: Lightweight and Efficient Memory-Augmented Generation
Paper • 2510.18866 • Published • 116 -
The End of Manual Decoding: Towards Truly End-to-End Language Models
Paper • 2510.26697 • Published • 120
LLM_RL
-
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 520 -
Weak-to-Strong Generalization via Direct On-Policy Distillation
Paper • 2607.05394 • Published • 143 -
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement
Paper • 2607.23802 • Published • 96
Frameworks
-
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 225 -
MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU
Paper • 2604.05091 • Published • 44 -
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Paper • 2606.11926 • Published • 79
LLM_RL
-
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 520 -
Weak-to-Strong Generalization via Direct On-Policy Distillation
Paper • 2607.05394 • Published • 143 -
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement
Paper • 2607.23802 • Published • 96
Architectures
-
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 520 -
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain
Paper • 2509.26507 • Published • 558 -
LightMem: Lightweight and Efficient Memory-Augmented Generation
Paper • 2510.18866 • Published • 116 -
The End of Manual Decoding: Towards Truly End-to-End Language Models
Paper • 2510.26697 • Published • 120