Deep Learning
Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning
When Spot tries to walk across a sandy beach or on ice, the challenges multiply, and her once-steady walk becomes erratic.
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
This raises a challenging research question: How can we keep improving the systems when their capabilities have surpassed the levels of humans?
dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans
Key attributes (cf. Figure 1) include the challenging task of classifying doppelganger animals,
HEPrune: Fast Private Training of Deep Neural Networks With Encrypted Data Pruning
However, FHE-based private training is significantly hindered by its substantial execution time.
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering John Y ang Carlos E. Jimenez
SWE-bench test instances (SWE-bench Lite) to analyze our ACI design choices.
Selective Generation for Controllable Language Models
Trustworthiness of generative language models (GLMs) is crucial in their deployment to critical decision making systems.
