iiinova — where your digital self keeps evolving

Reposted by Mert İnan

Lorna Quandt @lornaquandt.bsky.social · 11/11/2025

👋 Researchers at Gallaudet University and Northeastern University are seeking participants for a study of ASL learning. Our study will ask you to sign about a few different topics. Participation takes about 30 minutes, and you will be paid $15. Part 1/

144

Mert İnan @merterm.bsky.social · 09/10/2025

I would like to thank my wonderful co-authors, Anthony Sicilia and @malihealikhani.bsky.social Only with their efforts and constant support, this paper could come together. 🧵n/n

011

Mert İnan @merterm.bsky.social · 09/10/2025

Code and checkpoints are open-source! ⚠️These LLMs are not perfect, and we will be updating as new libraries become available. Dive in and build with us the next generation of signing LLMs: 🔗 github.com/Merterm/sign... 🔗 huggingface.co/merterm/sign... 🧵7/n

github.com

GitHub - Merterm/signAlignLM

Contribute to Merterm/signAlignLM development by creating an account on GitHub.

110

Mert İnan @merterm.bsky.social · 09/10/2025

🛠️ In the paper, we also explored all avenues to teach LLMs to sign! We tested: 🌸In-Context Learning (Prompt-Tuning) 🌸Supervised Fine-Tuning (SFT) 🌸Multitasking Fine-Tuning 🧵6/n

100

Mert İnan @merterm.bsky.social · 09/10/2025

🛡️ Forget Forgetting! We solve the problem of catastrophic forgetting. When an LLM loses its original spoken language skills after learning a new task. Our Multitasking Fine-Tuning strategy (mixing DGS & spoken language data, OpenOrca) successfully mitigates this data shift.🧵5/n

100

Mert İnan @merterm.bsky.social · 09/10/2025

🚀 Our Core Contribution: We introduced new fine-tuning strategies to build the first text-based and multimodal LLMs capable of SLP. This includes: ✅ Video-Based Input capabilities via fine-tuned LLaVA (V2T task). ✅ Text-Based Models fine-tuned on LLaMA3. 🧵4/n

100

Mert İnan @merterm.bsky.social · 09/10/2025

Unlike other LLMs, our models are trained and tested on 6 additional SLP tasks: 🌿(G2T) DGS to German 🌿(T2G) German to DGS 🌿(V2T) DGS Videos to German 🌿(I-G2T) Intensified DGS to German 🌿(T2I-G) German to Intensified DGS 🌿(G2E) DGS to English 🧵 3/n

100

Mert İnan @merterm.bsky.social · 09/10/2025

🚀 We're proud to be among the first to bring multimodal and text-based SLP models to the open-source community. Our approach is uniquely comprehensive. 🧵 2/n

100

Mert İnan @merterm.bsky.social · 09/10/2025

🏃‍♀️💨While waiting for SignGemma to become available... You can check out our first text-based and multimodal LLMs capable of Sign Language Processing (SLP) called SignAlignLM! #SignLanguage #LLM #AIAccessibility @aclmeeting 📜Paper: aclanthology.org/2025.finding... 🧵1/n

110

Reposted by Mert İnan

Nikhil Krishnaswamy @nikhilkrishnaswamy.bsky.social · 09/05/2025

Yeah, there's a new pope but did you know there's also a new #NLP workshop at @colmweb.org? The First Workshop on Optimal Reliance and Accountability in Interactions with Generative LMs (ORIGen) will be held October 10 at the Palais des Congrès in Montreal!

121

Reposted by Mert İnan

Tejas Srinivasan @tejassrinivasan.bsky.social · 16/05/2025

LLMs are all around us, but how can we foster reliable and accountable interactions with them?? To discuss these problems, we will host the first ORIGen workshop at @colmweb.org! Submissions welcome from NLP, HCI, CogSci, and anything human-centered, due June 20 :) origen-workshop.github.io

origen-workshop.github.io

ORIGen 2025

Workshop on Optimal Reliance and Accountability in Interactions with Generative LMs

0104

Mert İnan @merterm.bsky.social · 08/02/2025

I would like to thank my wonderful co-authors, Anthony Sicilia, Suvodip Dey, @vardhandongre.bsky.social, @tejassrinivasan.bsky.social, @thomason.bsky.social, @gokhantur.bsky.social, @dilekh.bsky.social, @malihealikhani.bsky.social With their efforts and support, this paper beautifully came together.

010

Mert İnan @merterm.bsky.social · 08/02/2025

We present a taxonomy of different friction movements, and show that positive friction, 1⃣Extends Dialogue Acts 2⃣Helps Model User Mental States 3⃣Helps Accomplish User Goals

100

Mert İnan @merterm.bsky.social · 08/02/2025

We hypothesize that systems can improve goal alignment, modeling of user mental states, and task success by deliberately slowing down conversations in strategic moments to ask questions, reveal assumptions, or pause.

100

Mert İnan @merterm.bsky.social · 08/02/2025

‼️ Ever wish LLMs would just... slow down for a second? In our latest work, "Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems", we delve into how strategic delays can enhance dialogue systems. Paper Website: merterm.github.io/positive-fri...

1155