ConvAI@UIUC

166 posts

ConvAI@UIUC banner
ConvAI@UIUC

ConvAI@UIUC

@convai_uiuc

Conversational AI | NLP | @dilekhakkanitur @tur_gokhan | @IllinoisCDS @uiuc_nlp

Urbana, IL Katılım Eylül 2024
825 Takip Edilen391 Takipçiler
Sabitlenmiş Tweet
ConvAI@UIUC
ConvAI@UIUC@convai_uiuc·
Welcome to the official page of ConvAI@UIUC! 🤖 Based in the cornfields of UIUC, and led by @dilekhakkanitur and @tur_gokhan, we do cool research on chatbots, dialogue, embodied agents, and everything in between!
English
3
10
46
12.2K
ConvAI@UIUC retweetledi
Shuhaib Mehri
Shuhaib Mehri@ShuhaibMehri·
Interdisciplinary research has driven major scientific breakthroughs. We show that LLMs can identify interdisciplinary insights that present fresh perspectives and improve creative research ideation.
Priyanka Kargupta@priyanka_karg

Breakthroughs don’t come from one big “aha.” They come from creatively connecting ideas across fields. Instead of automating incremental discovery, we introduce Idea-Catalyst to augment your scientific creativity: find insights from other domains to tackle gaps in your research.

English
0
3
7
574
ConvAI@UIUC retweetledi
Dan McAteer
Dan McAteer@daniel_mac8·
researchers from U of Illinois created: > Idea-Catalyst unlike an ai scientist that runs experiments and tries to reach a scientific conclusion Idea-Catalyst analyzes cross-disciplinary ideas and tries to help scientists discover novel angles for their research code below 👇
Dan McAteer tweet media
English
4
34
151
9.4K
ConvAI@UIUC retweetledi
ConvAI@UIUC retweetledi
Emre Can Acikgoz
Emre Can Acikgoz@emrecanacikgoz·
English
0
2
11
763
ConvAI@UIUC retweetledi
Emre Can Acikgoz
Emre Can Acikgoz@emrecanacikgoz·
Can LLMs self-evolve into general-purpose tool-calling agents without any external data? Yes. Introducing "Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data"! ♾️ Initialized from the same LLM, Tool-R0 co-evolves a Generator and Solver through self-play RL; training general-purpose tool-calling agents entirely from scratch with zero data. (1/n)
Emre Can Acikgoz tweet media
English
11
49
288
24.8K
ConvAI@UIUC
ConvAI@UIUC@convai_uiuc·
Join us in Urbana-Champaign 🌽 this year for the Midwest Speech and Language Days (MSLD 2026). Abstracts are due on March 2nd, everyone is welcome to attend!
ConvAI@UIUC tweet media
English
1
9
14
3.2K
ConvAI@UIUC retweetledi
Shuhaib Mehri
Shuhaib Mehri@ShuhaibMehri·
Excited to give a talk @GoogleResearch tomorrow on user-centered conversational agents!👩‍💻🔄🤖 I'll cover two directions: (1) LLMs that reliably simulate users during multi-turn conversations (2) Agents that continuously learn user preferences & improve collaboration across multiple sessions Really grateful for the opportunity to share our research, huge thanks to @maximillianc_ for the invite!🚀
English
1
1
10
430
ConvAI@UIUC retweetledi
Emre Can Acikgoz
Emre Can Acikgoz@emrecanacikgoz·
Just a reminder that the deadline for our Lifelong Agent Workshop at #ICLR2026 (@iclr_conf) is coming up in 10 days! We’re still finalizing parts of our program and putting together a few new exciting updates behind the scenes, can’t wait to share more soon... 👀 👉 For now, make sure you don’t miss the deadline: February 15—updates coming shortly!
Cheng Qian@qiancheng1231

📢 We are now releasing our second call for paper! 🚀 10 days to go for the submission DDL of Lifelong Agent Workshop@ICLR 2026! Website: lifelongagent.github.io Submission: openreview.net/group?id=ICLR.… More partners onboard! More excitiment ahead!

English
0
3
7
957
ConvAI@UIUC
ConvAI@UIUC@convai_uiuc·
Can games help AI understand the physical world? We're hosting a special session at the 2026 IEEE Conference on Games (@ieee_cog) — Evaluating and Advancing Spatial Intelligence through Games. Submit your work and join us in Madrid this September! 🇪🇸
Vardhan Dongre@Vardhan_Dongre

We’re excited to announce a special session at the 2026 IEEE Conference on Games (CoG): Evaluating and Advancing Spatial Intelligence through Games. Submit your research and join us in Madrid this September! 🇪🇸 📝 Key Information 📄 Call for Papers: lnkd.in/gqSK4xSD 📅 Submission Deadline: 17 March 2026 🗓️ Conference Dates: September 1–4, 2026 @ieee_cog @siebelschool

English
1
0
2
135
ConvAI@UIUC retweetledi
Shuhaib Mehri
Shuhaib Mehri@ShuhaibMehri·
ChatGPT remembers my birthday but not that I prefer an academic tone for writing assistance😮‍💨 I will present our work on agents that continuously learn and improve human-AI collaboration over time at the Assistive and Inclusive Technology workshop tomorrow. Join if you can!
Shuhaib Mehri tweet media
English
1
1
4
205
ConvAI@UIUC retweetledi
Vardhan Dongre
Vardhan Dongre@Vardhan_Dongre·
We’re excited to announce a special session at the 2026 IEEE Conference on Games (CoG): Evaluating and Advancing Spatial Intelligence through Games. Submit your research and join us in Madrid this September! 🇪🇸 📝 Key Information 📄 Call for Papers: lnkd.in/gqSK4xSD 📅 Submission Deadline: 17 March 2026 🗓️ Conference Dates: September 1–4, 2026 @ieee_cog @siebelschool
Prashant Jayannavar@p_jayannavar

🎮🤖 Can games teach AI to understand the physical world? Excited to announce a special session at the 2026 IEEE Conference on Games (@ieee_cog): Evaluating and Advancing Spatial Intelligence through Games. Submit your research and join us in Madrid this September! 🇪🇸 🧵👇 (1/5)

English
0
4
7
530
ConvAI@UIUC
ConvAI@UIUC@convai_uiuc·
Our OpenReview is live! #tab-recent-activity" target="_blank" rel="nofollow noopener">openreview.net/group?id=MSLD/…
English
0
1
1
112
ConvAI@UIUC retweetledi
Selin Yildirim
Selin Yildirim@seliny_uiuc·
Thrilled to share that I’m serving as Co-Chair of the ML track at the CSLSC 2026 conference at UIUC on Feb 24, 2–5 PM CST. Join us to explore deep learning theory, LLMs, multimodal learning, vision & signal processing research. More info & abstracts here: emails.illinois.edu/newsletter/75/…
English
1
2
4
1.2K
ConvAI@UIUC retweetledi
Ishika Agarwal
Ishika Agarwal@wonderingishika·
Excited to announce our newest work🎉 Idioms like "let sleeping dogs lie" need semantic translation, not literal ones. We use MTQE models to reward LLMs during training, improving both idiomatic and general translation quality—even for languages not in our training data.
Ishika Agarwal tweet media
English
1
6
21
558