5/ RAG for AI-Generated Content Provides an overview of RAG used in different generation scenarios like code, image, and audio, including a taxonomy of RAG enhancements with reference to key papers.
@dair_ai
-
Benchmark Evaluation Reveals Significant Reasoning Gap in LLMs
By
–
2/ Robust Evaluation of Reasoning Proposes functional benchmarks for the evaluation of the reasoning capabilities of LLMs; finds that there is a reasoning gap with current models from 58.35% to 80.31%.
-
Claude 3 family outperforms GPT-4 on key benchmarks
By
–
1/ Claude 3 Consists of a family of three models (Claude 3 Haiku, Claude 3 Sonnet, and Claude 3 Opus); Claude 3 Opus (the strongest model) seems to outperform GPT-4 on common benchmarks like MMLU and HumanEval.
-
Top ML Papers of the Week: Claude 3, KnowAgent, Design2Code
By
–
The Top ML Papers of the Week (March 4 – March 10): • Claude 3
• KnowAgent
• LLM for Law
• Design2Code
• RAG Enhancements Overview
• Robust Evaluation of Reasoning
… -
PlanGPT: Multi-Approach Framework for Spatial Planning AI
By
–
10/ PlanGPT – combines multiple approaches like retrieval augmentation, fine-tuning, tool usage, and more; the proposed framework is applied to urban and spatial planning but there are a lot of insights and practical tips that apply to other domains.
-
LLMs for Tabular Data: Techniques, Models and Research Directions
By
–
9/ LLMs on Tabular Data – an overview of LLMs for tabular data tasks including key techniques, metrics, datasets, models, and optimization approaches; it covers limitations and unexplored ideas with insights for future research directions.
-
Societal Impact of Open Foundation Models Position Paper
By
–
7/ On the Societal Impact of Open Foundation Models – a position paper with a focus on open foundation models and their impact, benefits, and risks.
-
EMO: Direct Audio-to-Video Synthesis Framework for Expressive Videos
By
–
6/ EMO – a new framework for generating expressive video by utilizing a direct audio-to-video synthesis approach; by leveraging an Audio2Video diffusion model it bypasses the need for intermediate 3D models or facial landmarks. https://
x.com/_akhaliq/statu
s/1762686465777999932?s=20
… -
StarCoder 2: Open LLM Family for Code Generation
By
–
8/ StarCoder 2 – a family of open LLMs for code with three different sizes (3B, 7B, and 15B); the 15B model was trained on 14 trillion tokens and 600+ programming languages with a context window of 16K token and employing a fill-in-the-middle objective.
-
LearnAct: Open-Action Learning Strategy for Language Agents
By
–
5/ LearnAct – explores open-action learning for language agents through an iterative learning strategy that creates and improves actions using Python functions.