TimeGPT-1 Foundation Model For Time Series; Merge LLMs; Fusilli - Python Lib for Multi-Modal Data Fusion; and More

Editor's Paper Recommendations

TimeGPT-1 : In this paper, we introduce TimeGPT, the first foundation model for time series capable of generating accurate predictions for diverse datasets not seen during training. We evaluate our pre-trained model against established statistical, machine learning, and deep learning methods, demonstrating that TimeGPT zero-shot inference excels in performance, efficiency, and simplicity. Our study provides compelling evidence that insights from other domains of artificial intelligence can be effectively applied to time series analysis. We conclude that large-scale time series models offer an exciting opportunity to democratize access to precise predictions and reduce uncertainty by leveraging the capabilities of contemporary advancements in deep learning.

Copy Suppression: Comprehensively Understanding an Attention Head : ??? We present a single attention head in GPT-2 Small with one main role across the entire training distribution. If components in earlier layers predict a certain token appearing earlier in the context, the head suppresses it: we call this copy suppression. Attention Head 10.7 (L10H7) suppresses naive copying behavior, improving overall model calibration. This explains why multiple prior works studying certain narrow tasks found negative heads that systematically favored the wrong answer. We uncover the mechanism that the Negative Heads use for copy suppression with weights-based evidence and can explain 76.9% of the impact of L10H7 in GPT-2 Small. To the best of our knowledge, this is the most comprehensive description of the complete role of a component in a language model to date. One major effect of copy suppression is its role in self-repair. Self-repair refers to how ablating crucial model components results in downstream neural network parts compensating for this ablation. Copy suppression leads to self-repair: if an initial overconfident copier is ablated, there is nothing to suppress. We show that self-repair is implemented by several mechanisms, including copy suppression, which explains 39% of the behavior in a narrow task. Interactive visualizations of the copy suppression phenomena may be seen at our web app https://copy-suppression.streamlit.app/

ALCUNA: Large Language Models Meet New Knowledge : With the rapid development of NLP, large-scale language models (LLMs) excel in various tasks across multiple domains now. However, existing benchmarks may not adequately measure these models’ capabilities, especially when faced with new knowledge. This paper addresses the lack of benchmarks to evaluate LLMs’ ability to handle new knowledge, an important and challenging aspect in the rapidly evolving world. We propose a KnowGen approach that generates new knowledge by altering existing entity attributes and relationships, resulting in artificial entities distinct from real-world entities. With KnowGen, we introduce a benchmark named ALCUNA to assess LLMs’ abilities in knowledge understanding, differentiation, and association. We benchmark several LLMs, revealing that their performance in the face of new knowledge is unsatisfactory, particularly in reasoning between new and internal knowledge. We also explore the impact of entity similarity on the model’s understanding of entity knowledge and the influence of contextual entities. We appeal to the need for caution when using LLMs in new scenarios or with new knowledge and hope that our benchmarks can help drive the development of LLMs in the face of new knowledge.

OpenAgents: An Open Platform for Language Agents in the Wild : Language agents show potential in being capable of utilizing natural language for varied and intricate tasks in diverse environments, particularly when built upon large language models (LLMs). Current language agent frameworks aim to facilitate the construction of proof-of-concept language agents while neglecting the non-expert user access to agents and paying little attention to application-level designs. We present OpenAgents, an open platform for using and hosting language agents in the wild of everyday life. OpenAgents includes three agents: (1) Data Agent for data analysis with Python/SQL and data tools; (2) Plugins Agent with 200+ daily API tools; (3) Web Agent for autonomous web browsing. OpenAgents enables general users to interact with agent functionalities through a web user interface optimized for swift responses and common failures while offering developers and researchers a seamless deployment experience on local setups, providing a foundation for crafting innovative language agents and facilitating real-world evaluations. We elucidate the challenges and opportunities, aspiring to set a foundation for future research and development of real-world language agents.

Meet SingleStore Pro Max, the Powerhouse Edition

In the rapidly changing landscape of AI and real-time analytics, the foundation of your applications—the data platform—is no longer an optional frill but a must-have. It's the springboard for innovation, the hidden force behind every breakthrough application.

Why Pro Max? Because it's not just a product update; it's a quantum leap. Power-packed with features like 1,000x faster vector search, an on-demand compute service for GPUs/ CPUs, and a new forever free tier, Pro Max stands for the sheer volume of advancements and their transformative impact on building modern applications.

Registration link

?--

Are you looking to advertise a product, job opening, or event to an audience of over 40,000 AI researchers and engineers? Please contact us on?LinkedIn? to explore your options.

Enjoy the newsletter? Help us make it bigger and better by sharing it with colleagues and friends.

--

Industry Insights

• Merge Large Language Models with mergekit
• Meet Fusilli: A Python Library for Multi-Modal Data Fusion in Machine Learning
• Data Science Better Practices, Part 2 — Work Together
• Meet LLama.cpp: An Open-Source Machine Learning Library to Run the LLaMA Model Using 4-bit Integer Quantization on a MacBook
• Researchers from Google Propose a New Neural Network Model Called 'Boundary Attention' that Explicitly Models Image Boundaries Using Differentiable Geometric Primitives like Edges, Corners, and Junctions

Growth Zone

4 Reasons Good Employees Lose Their Motivation

Expert Advice