Emre Can Acikgoz @acl2025
@emrecanacikgoz
PhD Student at @convai_uiuc, @IllinoisCDS | Intern @AmazonScience Alexa AI | #ConversationalAgents
🎉 Thrilled to share that two of our Agent papers are accepted to ACL 2025! 1️⃣ CoALM: arxiv.org/abs/2502.08820 2️⃣ SMART: arxiv.org/abs/2502.11435 Looking forward to presenting these and exchanging ideas on Agents at #ACL2025 @aclmeeting! 🚀 Additionally, I am also excited to be…
I'll be @aclmeeting in Vienna to present our recent agent papers SMART and CoALM! 🇦🇹🤖 #acl2025 Feel free to stop by our posters to exchange ideas and discuss agents together!
Happy to share that 🔄TD-Eval is accepted to #SIGDIAL2025 as an oral presentation! Hope to see you there at @sigdial and chat more on TOD Agent evaluation, which will definitely play a big role in next generation conversational agents.
🚀Excited to share our new evaluation paper "TD-Eval: Revisiting Task-Oriented Dialogue Evaluation by Combining Turn-Level Precision with Dialogue-Level Comparisons"! 🔄 🤖⚔️TOD systems have rapidly evolved thanks to LLMs, but traditional metrics remain insufficient in…
In a galaxy not so far away... engineers are the real Jedi. 🛠️🪐💡 May the 4th be with you from Illinois Grainger Engineering! #MayThe4th #ForceOfInnovation #IllinoisGraingerEngineering
Congratulations to Mila members Ada Tur, Gaurav Kamath and @sivareddyg for their SAC award at #NAACL2025! Check out Ada's talk in Session I: Oral/Poster 6. Paper: arxiv.org/abs/2502.05670
Given its promising results in reasoning-oriented tasks, how can we leverage RL with tool-specific reward functions for improved tool learning? How is the performance of smart rewards compared to SFT? Does it also lead to better thinking skills in tool-calling tasks? Introducing…
🚀 ToolRL unlocks LLMs' true tool mastery! The secret? Smart rewards > more data. 📖 Introducing newest paper: ToolRL: Reward is all Tool Learning Needs Paper Link: arxiv.org/pdf/2504.13958 Github Link: github.com/qiancheng0/Too…