AI Papers of the Week
Every paper worth reading in AI, hand-picked one week at a time.
Generative AI for Programming Education
Evaluates GPT-4 and ChatGPT on programming education scenarios versus human tutors.
DragDiffusion
Extends interactive point-based image editing to diffusion models.
Understanding Theory-of-Mind in LLMs with LLMs
A framework for procedurally generating ToM evaluations using LLMs themselves.
Evaluations with No Labels
Self-supervised evaluation of LLMs via sensitivity/invariance to input transformations.
Long-range Language Modeling with Self-Retrieval
Jointly trains a retrieval-augmented LM from scratch for long-range modeling.
Scaling MLPs: A Tale of Inductive Bias
Shows MLPs scale with compute despite their lack of inductive bias.
Textbooks Are All You Need (phi-1)
Introduces a 1.3B parameter code LLM trained on textbook-quality data.
RoboCat
DeepMind's self-improving foundation agent that operates different robotic arms from as few as 100 demonstrations.
ClinicalGPT
A language model optimized through extensive and diverse medical data and multi-turn dialogue.
An Overview of Catastrophic AI Risks
Dan Hendrycks' comprehensive overview of catastrophic AI risk categories.
LOMO
A memory-efficient optimizer that combines gradient computation and parameter update in one step.
SequenceMatch
Formulates sequence generation as imitation learning, enabling backtracking via a backspace action.
LMFlow
An extensible and lightweight toolkit for fine-tuning and inference of large foundation models.
MotionGPT
Generates consecutive human motions from multimodal control signals via LLM instructions.
Wanda
A simple, effective pruning approach for LLMs requiring no retraining.
AudioPaLM
Fuses PaLM-2 and AudioLM into a multimodal architecture supporting speech understanding and generation.
Voicebox
Meta's all-in-one generative speech model supporting 6 languages and many speech tasks in-context.
FinGPT
An open-source LLM for the finance sector with a data-centric approach.
Crowd Workers Widely Use LLMs for Text Production
Empirical evidence that 33-46% of MTurk crowd workers used LLMs on text tasks.
Reliability of Watermarks for LLMs
Studies whether watermarks survive human rewriting and LLM paraphrasing.
Applications of Transformers
A new survey highlighting major applications of Transformers across deep learning.
Benchmarking NN Training Algorithms (AlgoPerf)
A new benchmark for rigorously evaluating optimizers using realistic workloads.
Unifying LLMs & Knowledge Graphs
A roadmap for combining LLMs with knowledge graphs for stronger reasoning.
Augmenting LLMs with Long-term Memory (LongMem)
Enables LLMs to memorize long history via memory-augmented adaptation.