Theory of Machine Learning, EPFL
Popular repositories Loading
-
llm-adaptive-attacks
llm-adaptive-attacks PublicJailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]
-
understanding-fast-adv-training
understanding-fast-adv-training PublicUnderstanding and Improving Fast Adversarial Training [NeurIPS 2020]
-
llm-past-tense
llm-past-tense PublicDoes Refusal Training in LLMs Generalize to the Past Tense? [ICLR 2025]
-
why-weight-decay
why-weight-decay PublicWhy Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
-
sharpness-vs-generalization
sharpness-vs-generalization PublicA modern look at the relationship between sharpness and generalization [ICML 2023]
Repositories
- sparse-attention-dynamics Public
The code for "Incremental Learning of Sparse Attention Patterns in Transformers"
- sub-n-grams-are-stationary Public
- coconut Public Forked from facebookresearch/coconut
Training Large Language Model to Reason in a Continuous Latent Space
- softmax Public
Official code for the paper "Gradient Flow Polarizes Softmax Outputs towards Low-Entropy Solutions"
- axlearn-mod Public Forked from apple/axlearn
AXLearn framework slightly modified to extract the attention sinks metrics.
- os-harm Public
OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]
- learning-parametric-distributions-from-samples-and-preferences Public
Learning Parametric Distributions from Samples and Preferences [ICML 2025]
- llm-adaptive-attacks Public
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]
Top languages
Loading…
Most used topics
Loading…