Mingda Chen

AI Researcher @sjtu1896. Prev: @AIatMeta @GoogleAI

[Gargi Ghosh @gargighosh]

Last one of the year - EWE: https://t.co/D5y53ahtyX
Ewe (Explicit Working Memory), enhances factuality in long-form text generation by integrating a working memory that receives real-time feedback from external resources.

[Aran Komatsuzaki @arankomatsuzaki]

Meta presents Improving Factuality with Explicit Working Memory

Presents EWE, a novel approach that enhances factuality in long-form text generation by integrating a working memory that receives real-time feedback from external resources

EWE outperforms strong baselines on four fact-seeking long-form generation datasets, increasing the factuality metric, VeriScore, by 2 to 10 points absolute without sacrificing the helpfulness of the responses.

https://t.co/4alpBA45dv

[AI at Meta @AIatMeta]

Newly published work from FAIR, Chameleon: Mixed-Modal Early-Fusion Foundation Models.

This research presents a family of early-fusion token-based mixed-modal models capable of understanding & generating images & text in any arbitrary sequence.

Paper ➡️ https://t.co/6l4uICXr3b

[Victoria X Lin @VictoriaLinML]

Preview of our poster: #ICLR2024 #RAG #LLMs

[Victoria X Lin @VictoriaLinML]

🌐 Retrieval-augmentation is becoming increasingly popular for enriching LLMs with long-tail knowledge and keeping them up-to-date.
💫 Introducing RA-DIT: Retrieval-Augmented Dual Instruction Tuning (https://t.co/IS7Vo9OYzr), a fine-tuning process that enhances LM and retrieval integration in RALM, leading to better performance on knowledge-rich downstream tasks.

[Sierra Boggess @sierraboggess]

Yep, I'm back in Phantom #BruisesRus

[LA Clippers @LAClippers]

SMH