This work led by JIACHEN LIAN and collaborators at ALBA Language Neurobiology laboratory will be presented at #NeurIPS2024

Catch us at poster #242 on Thursday at 4:30 PM! More details here: 🔗 Website: tinglok.netlify.app/files/avsounds… 📄 arXiv: arxiv.org/abs/2409.14340 w/ Ren Wang , Bernie Huang, Andrew Owens , and Gopala Anumanchipalli .

If you are at #SfN2024, check out our poster in section F9 from 8 AM to 12 PM on Sunday! We present a streamable framework to restore a naturalistic voice to a person with paralysis. We will also show demos of voice synthesis, incremental TTS, and generalization to unseen words.

``Sylber: Syllabic Embedding Representation of Speech from Raw Audio,'' Cheol Jun Cho, Nicholas Lee, Akshat Gupta, Dhruv Agarwal, Ethan Chen, Alan W Black, Gopala K. Anumanchipalli, ift.tt/5PWQXna

Please checkout the following works on LLM editing and characterization next week at #EMNLP2024

I will be attending #NeurIPS2024 presenting our work SSDM: Scalable Speech Dysfluency Modeling (lnkd.in/gP9VvKdk), East Exhibit Hall A-C #3207, on Thursday, December 12th, 4:30-7:30 PM PST. Hope to meet with old and new friends!

Self-Supervised Syllabic Representation Learning from speech. With unsupervised syllable discovery & linear time tokenization of speech at the syllabic rate (~4 Hz) !! Work from my group Cheol Jun Cho, Nick Lee and Akshat Gupta Berkeley AI Research to be presented at #ICLR2025

Thrilled to share that our paper on "Norm Growth and Stability Challenges in Sequential Knowledge Editing" has been accepted for an Oral Presentation at the KnowFM workshop @ #AAAI2025 w/ Tom Hartvigsen Ahmed Alaa Gopala Anumanchipalli More details below (1/n)

Our work on knowledge editing got an "Outstanding Paper Award"🏆🏆 at the AAAI KnowFM Workshop!! #AAAI2025 🥳🥳🥳 Congratulations to my amazing co-authors Tom Hartvigsen Ahmed Alaa Gopala Anumanchipalli

(1/5) Introducing Full-Duplex-Bench: A Benchmark for Full-Duplex Spoken Dialogue Models We’re excited to present Full-Duplex-Bench, the first benchmark designed to evaluate turn-taking capabilities in full-duplex spoken dialogue models (SDMs)! arxiv.org/abs/2503.04721 Details👇

1/n) Our latest work is out today in Nature Neuroscience! We developed a streaming “brain-to-voice” neuroprosthesis which restores naturalistic, fluent, intelligible speech to a person who has paralysis. nature.com/articles/s4159…

Today in Nature Neuroscience, @ChangLabUCSF and Berkeley Engineering’s Gopala Anumanchipalli show that their new AI-based method for decoding neural data synthesizes audible speech from neural data in real-time: l8r.it/G2KC

A paper in Nature Neuroscience presents a new device capable of translating speech activity in the brain into spoken words in real-time. This technology could help people with speech loss to regain their ability to communicate more fluently in real time. go.nature.com/444kW0k

Scientists have developed a device that can translate thoughts about speech into spoken words in real time. Although it’s still experimental, they hope the brain-computer interface could someday help give voice to those unable to speak.

This thread is an excellent and accurate summary of our work ! Thank you vittorio !

Work led by BAIR students Kaylo Littlejohn and Cheol Jun Cho advised by BAIR faculty Gopala Anumanchipalli "...made it possible to synthesize brain signals into speech in close to real-time." dailycal.org/news/campus/re… via The Daily Californian

#ICLR25 Our work on characterizing alignment between MLP matrices in LLMs and Linear Associative Memories has been accepted for an Oral Presentation at the NFAM workshop. Location : Hall 4 #5 Time : 11 AM (April 27) Gopala Anumanchipalli Berkeley AI Research

🚀 Excited to share that our paper on Plan-and-Act has been accepted to ICML 2025. Below is a TLDR: 🔎 Problem: • LLM agents struggle on complex, multi-step web tasks (or API calls for that matter). • Why not add planning for complex tasks and decouple planning and execution?

Excited to have two paper accepted at #ACL2025 !🎉🎉 1 Main track and 1 Findings. Papers out on arxiv soon. Big thank you to all my collaborators!

Just did a major revision to our paper on Lifelong Knowledge Editing!🔍 Key takeaway (+ our new title) - "Lifelong Knowledge Editing requires Better Regularization" Fixing this leads to consistent downstream performance! Tom Hartvigsen Ahmed Alaa Gopala Anumanchipalli Berkeley AI Research