Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction
Paper • 2512.15605 • Published
Mathieu Blondel
mblondel
AI & ML interests
None yet
Recent Activity
authored a paper 5 days ago
Gemma 4 Technical ReportOrganizations
None yet
authored 4
papers 5 days ago
Gemma 4 Technical Report
Paper • 2607.02770 • Published • 83
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Paper • 2507.06261 • Published • 69
API design for machine learning software: experiences from the scikit-learn project
Paper • 1309.0238 • Published
updated a
model about 1 year ago
published a
model about 1 year ago
authored 7
papers over 1 year ago
Scikit-learn: Machine Learning in Python
Paper • 1201.0490 • Published • 1
Efficient and Modular Implicit Differentiation
Paper • 2105.15183 • Published
Sinkformers: Transformers with Doubly Stochastic Attention
Paper • 2110.11773 • Published
Routers in Vision Mixture of Experts: An Empirical Study
Paper • 2401.15969 • Published • 2
Implicit Diffusion: Efficient Optimization through Stochastic Sampling
Paper • 2402.05468 • Published • 6
Sparsity-Constrained Optimal Transport
Paper • 2209.15466 • Published • 1
On Teacher Hacking in Language Model Distillation
Paper • 2502.02671 • Published • 19
authored a
paper about 2 years ago