2024 – Page 14 – Andrew Fairless, Ph.D.

What I Read: Type Checking

By Andrew Fairless on February 26, 2024January 25, 2024

https://vickiboykis.com/2023/12/11/why-if-type_checking/ Why if TYPE_CHECKING?Vicki BoykisDec 11 2023 “Typechecking by mypy is more meticulous than the checking that happens at runtime, so we have to do hacks in order to getContinue readingWhat I Read: Type Checking

What I Read: Inducing hierarchy for multi-class classification

By Andrew Fairless on February 22, 2024January 7, 2024

https://arxiv.org/abs/2102.10263 Inducing a hierarchy for multi-class classification problemsHayden S. Helm, Weiwei Yang, Sujeeth Bharadwaj, Kate Lytvynets, Oriana Riva, Christopher White, Ali Geisa, Carey E. Priebe “In applications where categorical labelsContinue readingWhat I Read: Inducing hierarchy for multi-class classification

What I Read: Research Directions

By Andrew Fairless on February 21, 2024January 7, 2024

https://nlpnewsletter.substack.com/p/nlp-research-in-the-era-of-llms NLP Research in the Era of LLMs5 Key Research Directions Without Much ComputeSebastian RuderDec 19, 2023 “In an era where running state-of-the-art models requires a garrison of expensive GPUs,Continue readingWhat I Read: Research Directions

What I Read: Instruction Tuning

By Andrew Fairless on February 19, 2024December 19, 2023

https://gaotianyu.xyz/blog/2023/11/30/instruction-tuning/ Teach Llamas to Talk: Recent Progress in Instruction TuningTianyu Gao30 November 2023 “…open-ended instruction tuning… fine-tunes an LLM such that it can follow user instructions…. there have been numerousContinue readingWhat I Read: Instruction Tuning

What I Read: Will Scaling Solve Robotics?

By Andrew Fairless on February 15, 2024December 19, 2023

https://nishanthjkumar.com/Will-Scaling-Solve-Robotics-Perspectives-from-CoRL-2023/ Will Scaling Solve Robotics?: Perspectives From Corl 2023Nishanth J. Kumar “…is training a large neural network on a very large dataset a feasible way to solve robotics?”

What I Read: 3D human pose estimation

By Andrew Fairless on February 14, 2024December 19, 2023

https://perceiving-systems.blog/en/news/third-wave-3d-human-pose-and-shape-estimation Third wave 3D human pose and shape estimationPerceiving Systems Blog04 December 2023 “…PoseGPT looks at the whole image and can reason about people in context…. we can now relateContinue readingWhat I Read: 3D human pose estimation

What I Read: Limits of Transformers on Compositionality

By Andrew Fairless on February 13, 2024December 19, 2023

https://arxiv.org/abs/2305.18654 Faith and Fate: Limits of Transformers on CompositionalityNouha Dziri, Ximing Lu, Melanie Sclar, Xiang Lorraine Li, Liwei Jiang, Bill Yuchen Lin, Peter West, Chandra Bhagavatula, Ronan Le Bras, JenaContinue readingWhat I Read: Limits of Transformers on Compositionality

What I Read: survey LLM tooling

By Andrew Fairless on February 8, 2024February 5, 2024

https://ericmjl.github.io/blog/2024/2/1/an-incomplete-and-opinionated-survey-of-llm-tooling/ An (incomplete and opinionated) survey of LLM toolingEric J. Ma1/31/24 7:00 PM “More critical than specifying specific tools, my goal with this blog post is to outline a frameworkContinue readingWhat I Read: survey LLM tooling

What I Read: Multi-Modal Retrieval-Augmented Generation

By Andrew Fairless on February 7, 2024December 19, 2023

https://blog.llamaindex.ai/evaluating-multi-modal-retrieval-augmented-generation-db3ca824d428?gi=45acebfc0a3a Evaluating Multi-Modal Retrieval-Augmented GenerationLlamaIndexNov 16 “A natural starting point is to consider how evaluation was done in traditional, text-only RAG and then ask ourselves how this ought to beContinue readingWhat I Read: Multi-Modal Retrieval-Augmented Generation

What I Read: Adversarial Attacks on LLMs

By Andrew Fairless on February 6, 2024December 19, 2023

https://lilianweng.github.io/posts/2023-10-25-adv-attack-llm/ Adversarial Attacks on LLMsLilian WengOctober 25, 2023 “Adversarial attacks are inputs that trigger the model to output something undesired.”

Year: 2024