🚀NEW COURSEVibe Coding AI Apps with Claude Code 🤖✨Enroll now
← All papersIssue 36 of 176

The week of Dec 4 – Dec 10, 2023

10 papers, hand-picked and summarised.

Gemini 1.0

Gemini 1.0

Google launches Gemini 1.0, a multimodal family natively designed to reason across text, images, video, audio, and code from the ground up.

01Multimodal
EfficientSAM

EfficientSAM

Meta's EfficientSAM is a lightweight Segment Anything variant that preserves most of SAM's zero-shot quality at a fraction of the compute.

02Training
Magicoder

Magicoder

Magicoder is a fully open-source code LLM that closes the gap with top commercial code models at only 7B parameters via high-quality synthetic instruction data.

03Code
LLMs on Graphs

LLMs on Graphs

A comprehensive overview of the many ways LLMs can be applied to graph-structured data and when each pattern is useful.

04Reasoning
Llama Guard

Llama Guard

Meta's Llama Guard is a compact, instruction-tuned safety classifier built on Llama 2-7B for input/output moderation in conversational AI.

05Safety
KTO (Kahneman-Tversky Optimization)

KTO (Kahneman-Tversky Optimization)

Contextual AI introduces KTO, an alignment objective derived from prospect theory that works with binary "good/bad" signals instead of preference pairs.

06Reinforcement Learning
Chain of Code

Chain of Code

DeepMind's Chain of Code extends CoT by encouraging LMs to write pseudocode that mixes real code with LM-simulated sub-routines.

07Reasoning
Data Management for LLMs

Data Management for LLMs

A survey of data-management research for LLM pretraining and supervised fine-tuning stages.

08Training
RankZephyr

RankZephyr

RankZephyr is an open-source LLM for listwise zero-shot reranking that bridges the effectiveness gap with GPT-4.

09Evaluation
The Efficiency Spectrum of LLMs

The Efficiency Spectrum of LLMs

A comprehensive review of algorithmic advancements for improving LLM efficiency across the full training-to-inference stack.

10Efficiency
Every Monday
Get next week’s papers.

The same picks and the same summaries, in your inbox. Free, and 176 issues deep.

Subscribe on Substack