Arthur LAGACHERIE

Arthur-LAGACHERIE's activity

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

upvoted a paper 1 day ago

Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models

Paper • 2511.08577 • Published 9 days ago • 85

upvoted a paper 3 days ago

Virtual Width Networks

Paper • 2511.11238 • Published 6 days ago • 31

upvoted a paper 4 days ago

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

Paper • 2511.06221 • Published 11 days ago • 109

upvoted a collection 6 days ago

Pre-training Dataset Samples

Collection

A collection of pre-training datasets samples of sizes 10M, 100M and 1B tokens. Ideal for use in quick experimentation and ablations. • 19 items • Updated 9 days ago • 13

upvoted a paper 7 days ago

TiDAR: Think in Diffusion, Talk in Autoregression

Paper • 2511.08923 • Published 8 days ago • 92

upvoted a paper 14 days ago

Diffusion Language Models are Super Data Learners

Paper • 2511.03276 • Published 15 days ago • 116

upvoted 4 papers 19 days ago

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

Paper • 2510.11696 • Published Oct 13 • 173

Scaling Latent Reasoning via Looped Language Models

Paper • 2510.25741 • Published 22 days ago • 213

Kimi Linear: An Expressive, Efficient Attention Architecture

Paper • 2510.26692 • Published 21 days ago • 107

The End of Manual Decoding: Towards Truly End-to-End Language Models

Paper • 2510.26697 • Published 21 days ago • 113

upvoted a paper about 1 month ago

BitNet Distillation

Paper • 2510.13998 • Published Oct 15 • 53

upvoted a paper about 2 months ago

Model Merging in Pre-training of Large Language Models

Paper • 2505.12082 • Published May 17 • 40

upvoted a paper 2 months ago

Energy-Based Transformers are Scalable Learners and Thinkers

Paper • 2507.02092 • Published Jul 2 • 69

upvoted 4 papers 3 months ago

Transition Models: Rethinking the Generative Learning Objective

Paper • 2509.04394 • Published Sep 4 • 28

AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs

Paper • 2508.16153 • Published Aug 22 • 154

CRISP: Persistent Concept Unlearning via Sparse Autoencoders

Paper • 2508.13650 • Published Aug 19 • 15

On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

Paper • 2508.05629 • Published Aug 7 • 178

upvoted a paper 5 months ago

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

Paper • 2506.16406 • Published Jun 19 • 126

upvoted 2 articles 5 months ago

view article

Article

🐯 Liger GRPO meets TRL

• 

May 25

•

51

view article

Article

Tiny Agents in Python: a MCP-powered agent in ~70 lines of code

• 

May 23

•

170