In the end, I think agents will stream output actions continously. Think @thinkymachines interaction models but not only streaming speech and vision, but also streaming output control actions.
This will also be end-to-end trained in the model weights, but I wonder how far you could get today by stitching something together with @livekit etc., with computer use models outputting high level actions and faster models outputting the micro-steps. This is kind of how we've done things in unity [https://t.co/pTyu36D86Z], but for now we only stream the speech and vision at the high-frequency conversational layer (not yet actions).
In the end more of the harness will move to end-to-end training, and harnesses are a point-in-time solution to what will inevitably become an end-to-end trained system with latent representations at the boundaries instead of text etc.
We’re excited to have @shirleyxiaoyic from @IndianaUniv, co-author of the paper "The Janus Interface: How Fine-Tuning in Large Language Models Amplifies Privacy Risks," joining us this Friday for our Paper Reading Session! 🤩
RSVP 👉 https://t.co/dc0BJHGDAM
The research introduces a novel attack, Janus, which exploits the fine-tuning interface to recover forgotten PIIs from the pre-training data in LLMs also formalizing the privacy leakage problem in LLMs, explaining why forgotten PIIs can be recovered through empirical analysis on open-source language models.🧠
Check out the Paper: https://t.co/hsU63vK7Kj
See you there!
We're thrilled to announce that @Vapi_AI will be joining us for our weekly Webinar Series tomorrow! (Wednesday) 🤩
RSVP here: https://t.co/Xt4NArf1UA
Join us as we welcome Sahil Suman, Solution Engineer at Vapi AI, to the session. Discover how VAPI enables the quick setup of high-quality voice agents and see the integration of @letsunifyai with VAPI for seamless access to various models and providers. See you there! 🧑💻
Explore Vapi:
⚡️https://t.co/Sg69g4RSfg
⚡️https://t.co/aSRX20yNQd
We are really excited to welcome @zlwang_cs from @ucsd_cse, who co-authored the paper "Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting". Happening Tomorrow!🤩
RSVP 👉 https://t.co/XW2dClf4UN
The research introduces SPECULATIVE RAG, a framework that leverages a larger generalist LM to efficiently verify multiple RAG drafts produced in parallel by a smaller, distilled specialist LM 🧠🤖
Check out the Paper👉https://t.co/lTeYmUEVR4
See you there!
We are really excited to announce that we will be joined by @llmware for our Webinar Series today! (Tuesday)🤩
RSVP👉 https://t.co/dWNWKhATHa
In this session, we're excited to welcome Darren Oberst and Namee Oberst from LLMware. We will explore how small specialized LLMs can compete with the larger models for specific use cases, especially for Financial, Legal, Compliance, and Regulatory-Intensive Industries. See you there! 🧑💻
Checkout LLMWare:
⚡️https://t.co/FVJA4kUYiq
⚡️https://t.co/vtC0TSfE2B
We are really excited to welcome Devichand Budagam
from @IITKgp, who co-authored the paper "Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models". Happening Friday! 🤩
RSVP👉 https://t.co/IkXvbO7G0z
The research introduces Hierarchical Prompting Taxonomy (HPT), a universal evaluation metric that can be used to evaluate both the datasets' complexity and LLMs' capabilities🧠
Check out the Paper👉 https://t.co/DPXJzFTrC7
See you there!
We are really excited to announce that we will be joined by @tavilyai for our Webinar Series this Tuesday!🤩
RSVP👉 https://t.co/A5DWx3v657
In this session, we'll explore how Tavily API makes search engine optimised for LLMs and RAG, to provide efficient, quick, and persistent search results. We'll also showcase Unify's SSO integration with Tavily 🧠🧑💻
Checkout Tavily:
⚡️https://t.co/09HUAktlpM
⚡️https://t.co/He5lk2TEae
We are really excited to welcome @sh_reya from @Berkeley_EECS, who co-authored the paper "Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences". Happening Tomorrow! 🤩
RSVP 👉https://t.co/7DERN45vZ3
The research introduces EvalGen, an interface that provides automated assistance in generating evaluation criteria and implementing assertions🧠👩💻
Check out the Paper👉 https://t.co/13yCWyIUjv
See you there!
We are really excited to announce that we will be joined by @CopilotKit for our Webinar Series this Thursday!🤩
RSVP 👉https://t.co/7xpLFcEWQS
In this session, we'll explore how CopilotKit makes integrating AI-powered Copilots into any product easy. We'll also showcase how the Unify Router can help you create Copilots that automatically select the best Large Language Model (LLM) for the task 🤖✨
Checkout CopilotKit:
⚡https://t.co/f09Lm93k97
⚡https://t.co/sF0PUhs3NK
See you there!
We are really excited to welcome
@yyzTodd from @ZJU_China, who co-authored the paper "Knowledge Circuits in Pretrained Transformers". This Friday! 🤩
RSVP 👉 https://t.co/NSHg5l091O
The research dives into the computation graph of language models to uncover the knowledge circuits that are instrumental in articulating specific knowledge 🤖🧠
Check out the Paper 👉 https://t.co/O1rNFGxsIL
See you there!
LLM Contributor Projects Week - LLM Resume Analyser 🔍
⚡️Try it out! - https://t.co/0uZYjyl6DQ
Oscar Arroyo Vega (@OscarArroyoVega), Sanjay Suthar (@Sanjay__Suthar), Jeyabalan Ganesh Nadar, and Maissa Rekik have been working on an LLM Resume Analyser. The app extracts and analyzes key skills from resumes, provides matching scores for job descriptions, and suggests resume improvements! 📚✨
Check out their presentation - https://t.co/LyutEQ20MX
Check out the repo here - https://t.co/uslQXQGcE4
We are super excited to welcome @felipemaiapolo from @UMich this Friday to our paper reading session. Felipe co-authored the paper "Efficient multi-prompt evaluation of LLMs" 🤩
⚡️RSVP - https://t.co/vADJhvqlge
His research introduces PromptEval, a new method for estimating performance across a large set of prompts, borrowing strength across prompts and examples to produce accurate estimates under practical evaluation budgets📈
📚Check out the paper - https://t.co/buAUUrGYZE
See you there!
LLM Contributor Projects Week - LlamaIndex RAG Playground🛝
Abhijeet Chintakunta has developed the LLamaIndex RAG Playground, an application that allows users to upload PDF documents and ask questions about them!⚡️
Try it out - https://t.co/XRaFCuVf2P
Abhijeet used LLamaIndex to create a RAG application for this project. The application's interface is built with Streamlit, making it user-friendly and easy to interact with 🤝🤖
Check out their presentation - https://t.co/PKwZ7KF92r
Check out the repo here -https://t.co/GgL3sML1Ye
LLM Contributor Projects Week - LLM Debate 📚
Ogban Ugot (@OgbanUgot) and Sanjay Suthar (@Sanjay__Suthar), have been working on LLM Debate.
Try it out! - https://t.co/eXZ5LGnMqu
In this project, they developed a web application that allows two LLMs to engage in a real-time conversation on a topic chosen by the user. Users can select any two models, input a query, and view the dialogue between the LLMs as it unfolds. This application, built using Unify and deployed with Streamlit, offers a platform for users to observe AI-generated debates and explore the capabilities of different language models⚡️ ⚔️
Check out their presentation - https://t.co/htwDazrOuQ
Check out the repo here - https://t.co/PKuNAugZEm