AI Papers of the Week
Every paper worth reading in AI, hand-picked one week at a time.
OPRO (LLMs as Optimizers)
DeepMind's OPRO uses LLMs as general-purpose optimizers over natural-language-described problems.
ImageBind-LLM
Shanghai AI Lab's ImageBind-LLM brings six-modality understanding to LLMs via the ImageBind joint embedding space.
Explaining Grokking
DeepMind advances our understanding of grokking, predicting and confirming two novel phenomena that test their theory.
Overview of AI Deception
A survey cataloguing empirical examples of AI systems exhibiting deceptive behavior.
FLM-101B
A 101B parameter open LLM trainable on a $100K budget through a growth-based training strategy.
Cognitive Architectures for Language Agents (CoALA)
Princeton proposes CoALA, a systematic framework for understanding and building language agents.
Q-Transformer
Google's Q-Transformer is a scalable RL method for training multi-task robotic policies from large offline datasets.
LLaSM (Large Language and Speech Model)
A combined language-and-speech model trained with cross-modal conversational abilities.
SAM-Med2D
Adapts the Segment Anything Model (SAM) to 2D medical imaging through large-scale medical fine-tuning.
Vector Search with OpenAI Embeddings
Argues, via empirical analysis, that dedicated vector databases aren't necessarily required for modern AI-stack search applications.
Graph of Thoughts (GoT)
Generalizes Chain-of-Thought and Tree-of-Thought by modeling LLM reasoning as an arbitrary graph.
MVDream
ByteDance's MVDream is a multi-view diffusion model that generates geometrically consistent images from multiple viewpoints given a text prompt.
Nougat
Meta's Nougat is a visual transformer for "Neural Optical Understanding for Academic documents" that converts PDFs to LaTeX/Markdown.
FacTool
A tool-augmented framework for detecting factual errors in LLM-generated text.
AnomalyGPT
Applies large vision-language models to industrial anomaly detection with synthetic data augmentation.
FaceChain
Alibaba's FaceChain is a personalized portrait generation framework that produces identity-preserving portraits from just a handful of input photos.
Qwen-VL
Alibaba's Qwen-VL is a large-scale vision-language model family with strong performance across captioning, VQA, and visual localization.
Code Llama
Meta releases Code Llama, a family of code-specialized LLMs built on top of Llama 2.
Survey on Instruction Tuning for LLMs
A comprehensive survey of instruction tuning covering methodology, dataset construction, and applications.
SeamlessM4T
Meta's SeamlessM4T is a unified multilingual and multimodal machine-translation system that handles five translation tasks in one model.
LLMs for Illicit Purposes
A survey cataloguing threats and vulnerabilities arising from LLM deployment.
Giraffe
A family of context-extended Llama and Llama 2 models, along with an empirical study of context-extension techniques.
IT3D
Improves Text-to-3D generation by leveraging explicitly synthesized multi-view images in the training loop.
LLM-Based Autonomous Agents Survey
A comprehensive survey of LLM-based autonomous agents covering construction and applications.