Goto

Collaborating Authors

 Sweden


'It's survival of the fittest': the UK kebab chain seeking an edge with robot slicers

The Guardian

'People are being more discerning about spending money,' he says. 'People are being more discerning about spending money,' he says. T hey are already packing our groceries and delivering shopping. Now robots are coming to the kebab shop, alongside self-service screens and loyalty apps, as takeaways look for ways to tackle rising costs. German Doner Kebab (GDK), a perhaps surprisingly British-owned chain that has been springing up across the country, has turned to technology to keep its fast food business buzzing in the face of rising costs and tough times on the high street.


Russia-Ukraine war: List of key events, day 1,457

Al Jazeera

How the US left Ukraine exposed to Russia's winter war Will Europe use frozen Russian assets to fund war? How can Ukraine rebuild China ties? Russian forces launched 448 attacks on 34 settlements in Ukraine's front-line Zaporizhia region in a single day, injuring a six-year-old child and damaging homes, cars and other infrastructure, regional governor Ivan Fedorov wrote on the Telegram app. Russian drone, missile and artillery attacks on Ukraine's Kherson region injured five people and damaged homes, including seven high-rise buildings, the local military administration said on Telegram. Russian attacks also continued in Ukraine's Dnipropetrovsk and Sumy regions, but local officials there noted that "fortunately, no people were injured".


Align Y our Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization

Neural Information Processing Systems

TPT does not explicitly align the pre-trained CLIP to become aware of the test sample distribution. For the effective test-time adaptation of V -L foundation models, it is crucial to bridge the distribution gap between the pre-training dataset and the downstream evaluation set for high zero-shot generalization.




Debiasing Conditional Stochastic Optimization Lie He

Neural Information Processing Systems

The sample-averaged gradient of the CSO objective is biased due to its nested structure, and therefore requires a high sample complexity for convergence. We introduce a general stochastic extrapolation technique that effectively reduces the bias.