arxiv:2606.13603
📚 Learning new things
Gabriele Sarti
gsarti
AI & ML interests
Interpretability for generative language models
Recent Activity
liked a dataset about 9 hours ago
IntelligenceLab/Long-Horizon-Terminal-Bench liked a model 10 days ago
meta-models/Muse-Glimmer-30B authored a paper 24 days ago
Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning ModelsOrganizations
arxiv:2606.11172
arxiv:2603.05198
arxiv:2602.20021
arxiv:2602.08964
arxiv:2512.09730
arxiv:2507.07808
arxiv:2505.23183
arxiv:2505.16612
arxiv:2503.03044
arxiv:2408.00584
arxiv:2406.17563
arxiv:2406.13663
arxiv:2405.00208
arxiv:2310.03686
arxiv:2310.01188
arxiv:2305.17131
arxiv:2302.14220
arxiv:2302.13942
arxiv:2205.12215
arxiv:2203.03759
arxiv:2108.08688
arxiv:2008.10875
