Conventional AI benchmarks typically focus on the content of responses, for example checking factual (e.g. MMLU) or mathematical correctness (e.g. GSM8k).
-
17Jun
-
17Jun
This talk presents the first comprehensive security evaluation of Internet voting systems used in U.S. federal elections. We find that all systems suffer from critical flaws that allow attackers to expose a voter’s private ballot, change votes, or otherwise control an election’s outcome.
-
18Jun
Recently, the field of Machine Learning has seen renewed interest in communication-efficient training over slow, unreliable, and heterogeneous networks.
-
19Jun
=== Hybrid talk ===
Join Zoom Meeting
https://cam-ac-uk.zoom.us/j/89856091954?pwd=Bba77QB2KuTideTlH6PjAmbXLO8HbY.1Meeting ID: 898 5609 1954
Passcode: ITPtalk -
20Jun
Abstract not available
-
24Jun
Abstract not available
-
26Jun
*Abstract*
Stay tuned!
*Bio*
Stay tuned!
-
03Jul
*Abstract*
Stay tuned!
*Bio*
Orlando is a second-year PhD student with the AI4ER CDT. Supervised by Oscar Branson (Earth Sciences), he is interested in the opportunities and limitations for modelling marine ecosystems – particularly coral reefs – posed by the data available today.
-
17Jul
*Abstract*
Stay tuned!
*Bio*
Stay tuned!
-
04Aug
In both federated learning (FL) and large language model (LLMs) optimization, a central challenge is effective learning under constraints, ranging from data heterogeneity and personalization to limited communication and black-box access.