Ongoing Projects

Large language models (LLMs) often incorporate multiple text chunks in their inputs to provide the necessary contexts. To speed up the prefill of the long LLM inputs, one can pre-compute the KV cache of a text and re-use the KV cache when the context is reused as the prefix of another LLM input.

Retrieval Augmented Generation (RAG) is the recent state-of-the art paradigm which lets Large Language Models (LLMs) generalise to text generation tasks in new domains, for which they have not been trained.

Nowadays, not only can we chat with chatGPT, but we can also let it write and execute code to do more complex tasks (e.g. letting chatGPT plot the boundary of America using Python).

As large language models (LLMs) take on complex tasks, their inputs are supplemented with longer contexts that incorporate domain knowledge or user-specific information. Yet using long contexts poses a challenge for responsive LLM systems, as nothing can be generated until the whole context is processed by the LLM.

Satellite imagery is useful for a wide range of applications, from automatic road detection to forest monitoring. But did you know only 2% of satellite images can actually be downloaded to the ground?

In real-time video communication, retransmitting lost packets over high-latency networks is not viable due to strict latency requirements. To counter packet losses without retransmission, two primary strategies are employed -- encoder-based forward error correction (FEC) and decoder-based error concealment.