Perouz Taslakian

I am an AI Research Scientist at Service Now. I am also an Adjunct Professor at McGill University & an industry member at MILA.

[Perouz Taslakian @PerouzT]

🚀 Internship Opportunities in AI Agents!
At @ServiceNowRSRCH, we have 4 internship positions on AI Agents — exploring robustness, privacy & collaboration.

🧠 Applicants must be registered students at a Canadian university.

👇 Thread with details & links to apply:

[Perouz Taslakian @PerouzT]

🔬👁️ Looking for an AI intern to work on eye disease detection!

Build models that combine high-res images with clinical data to automate diagnosis.

🇨🇦 Mitacs internship (8 months, full-time, ASAP)
(Must be enrolled at a Canadian university)

📩 https://t.co/xP4f93br7E

#McGill

[Alexandre Drouin @alexandredrouin]

The NeurIPS Datasets & Benchmarks Track is now the Evaluations & Datasets (ED) Track. It now treats evaluation as a scientific object of study in its own right. Datasets/benchmarks still fully in scope.

👉Details: https://t.co/MN75FwQ8Ow

We look forward to your submissions!

[Siva Reddy @sivareddyg]

Thoughtology paper -- the study of reasoning chains of thinking models -- is now published at TMLR. Since we wrote the paper, a lot has changed. Many more models have been released with open-weights.

1. These models are no longer thinking verbosely. GPT-OSS has crisper thoughts than Qwen3/R1.

2. GPT-OSS almost never self-verifies or tries alternate solutions.

3. Qwen3 has a large bloom step (initial solution) than R1.

Among commonalities:
4. All of them still have a problem-specific sweet spot (i.e., overthinking doesn't help)

5. Incorrect problems still have a longer chain length.

On another note, thanks to @TmlrOrg for allowing us to submit a ridiculously long paper :). 135 pages in total. We thank reviewers and AE for their time.

This is the first paper where every member of the group contributed to it! Special thanks to @saraveramarjano and @arkil_patel.

We have a documentary around it taken by @CBCNews and @binhanv, hopefully you will get to see it one day.

Thanks to @SimonsInstitute for letting us work on this during their LLM2 semester program. @IVADO_Qc for the funding, and @Mila_Quebec members for the feedback.

Full paper: https://t.co/kaTNGCv6rk

[Alexandre Drouin @alexandredrouin]

Excited to speak at the AAAI-26 Workshop on Agentic AI Benchmarks & Enterprise Tasks (Jan 26, Singapore) 🇸🇬

As agents are rapidly productized, realistic enterprise benchmarks for capabilities and reliability are essential!

Submit: https://t.co/NYWO6Xv89b
🗓️ Oct 29

cc @gneubig

[Perouz Taslakian @PerouzT]

4️⃣ Agent Memory Poisoning Attacks

Detecting and defending against corrupted memories.

Apply 👉 https://t.co/28UMVXJS9r

[Perouz Taslakian @PerouzT]

🚀 Internship Opportunities in AI Agents!
At @ServiceNowRSRCH, we have 4 internship positions on AI Agents — exploring robustness, privacy & collaboration.

🧠 Applicants must be registered students at a Canadian university.

👇 Thread with details & links to apply:

[Perouz Taslakian @PerouzT]

3️⃣ BlackBox Whisperer

Tuning smaller open models to collaborate effectively with large black-box LLMs.

Apply👉 https://t.co/rkj7vTE2VO

[Christos Tsirigotis @tsirigoc]

A big shoutout to amazing collaborators @vaibhav_adlakha @joaomonteirof @AaronCourville @PerouzT

Come find us at poster 55, 11am-1pm, on Tuesday to learn more!

https://t.co/4rePyb50jj

#COLM2025 #informationretrieval #denseencoders

[ServiceNow AI Research @ServiceNowRSRCH]

SLAM Labs presents Apriel-1.5-15B-Thinker 🚀

An open-weights multimodal reasoning model that hits frontier-level performance with just a fraction of the compute.

[Massimo Caccia @MassCaccia]

See you in San Diego 🚀
#NeurIPS2025

[Perouz Taslakian @PerouzT]

🎉Congratulations to all the authors for this great work -- specially to @Ahmed_Masry97 for his perseverance through the highs and lows of this project 😀

Excited to see AlignVLM accepted to #NeurIPS2025!
@ServiceNowRSRCH

[Ahmed Masry @Ahmed_Masry97]

Excited to announce that AlignVLM got accepted to NeurIPS! 🎉🥳

We’ll be releasing the code and sharing an updated version of the paper with reviewer feedback soon.
#NeurIPS2025

[Rabiul Awal @_rabiulawal]

🚨Exciting news! Our paper “WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation” is accepted for an oral presentation at EMNLP 2025! 🎉 WebMMU addresses a critical gap in AI evaluation: how well can models understand and build websites? 🧵1/n

[Ahmed Masry @Ahmed_Masry97]

UI-Vision vs GPT-5: Still holding the crown 👑 and far from saturation.

GPT-5 has strengths in coding and reasoning, but when it comes to computer-use tasks, it’s still awkward to rely on it alone. And our team's UI-Vision (ICML 2025) remains a key and still unbeaten multimodal eval framework for screen understanding and grounding.

What we continue to see: focused training is essential to beat our evals, and this is exactly where open-source models have been shining.

A big thanks to research teams at Microsoft, OpenCUA, and UI-Tars for actively using UI-Vision to push the limits of visual screen understanding. If you are working on VLMs or screen grounding applications for ICLR submissions, UI-Vision is the place to measure and improve your systems.

And we are only getting started: our next, UI-Vision-Grounding, is on the way🚀. It brings a larger dataset that the community can make use of, harder grounding tasks, and new training recipes to help models level up in grounding abilities.

🔗https://t.co/ObaK1zjD0p
📜https://t.co/NoKK387FLd

Big kudos to all our partners and collaborators who made this possible! @ServiceNowRSRCH, @turingcom, @Mila_Quebec, @PShravannayak, @EdwardJian2, @aarashfeizi, @gspandana, @PerouzT, Qinghong Lin, @chrisjpal, @_rabiulawal, @dvazquezcv, @joanrod_ai, @RajeswarSai

[Perouz Taslakian @PerouzT]

🚀 We just released the final test split of #RepLiQA —our dataset for evaluating QA on truly unseen content!

📚 Dataset: https://t.co/VTgESfBqv2
📝 NeurIPS ’24: https://t.co/9JKgGxdWSo

Big thanks to my amazing co-authors @ @ServiceNowRSRCH ! 🙌

#RAG #LLMs #NLP #QA

[NewInML @ NeurIPS 2025 @NewInML]

New to ML research? Never published at ICML? Don't miss this!

Check out the New in ML workshop at ICML 2025 — no rejections, detailed feedback, awards, and ICML tickets for selected authors.

Deadline: June 10 (AoE)
Submit: https://t.co/xNiccKTelq
Info: https://t.co/1dBY6bnGji

[Joan Rodriguez @joanrod_ai]

Thanks @_akhaliq for sharing our work! Excited to present our next generation of SVG models, now using Reinforcement Learning from Rendering Feedback (RLRF).

🧠 We think we cracked SVG generalization with this one.

Go read the paper! https://t.co/EnSbizvWOQ

More details on the demo, code, and models coming soon! Stay tuned 💫

[Patrice Bechard @patricebechard]

🚀 New paper from our team at @ServiceNowRSRCH!⁣
⁣
💫𝐒𝐭𝐚𝐫𝐅𝐥𝐨𝐰: 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐧𝐠 𝐒𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐞𝐝 𝐖𝐨𝐫𝐤𝐟𝐥𝐨𝐰 𝐎𝐮𝐭𝐩𝐮𝐭𝐬 𝐅𝐫𝐨𝐦 𝐒𝐤𝐞𝐭𝐜𝐡 𝐈𝐦𝐚𝐠𝐞𝐬⁣
We use VLMs to turn 𝘩𝘢𝘯𝘥-𝘥𝘳𝘢𝘸𝘯 𝘴𝘬𝘦𝘵𝘤𝘩𝘦𝘴 and diagrams into executable workflows. ����️→⚙️⁣
⁣
🔗https://t.co/HRU22oXQsT⁣
📝https://t.co/2Rpp9Nwuiz⁣
#Sketch2Flow #AI #VLM

[Perouz Taslakian @PerouzT]

Our team has released the UI-Vision benchmark (accepted at #ICML2025) for testing GUI agent visual grounding and action prediction! 🚀🚀🚀

🤗 Dataset: https://t.co/EWOTL0nVVF

Special thanks to the students to lead this effort, @PShravannayak and @EdwardJian2

@ServiceNowRSRCH

[P Shravan Nayak @PShravannayak]

🚀 Excited to share that UI-Vision has been accepted at ICML 2025! 🎉

We have also released the UI-Vision grounding datasets. Test your agents on it now! 🚀

🤗 Dataset: https://t.co/GhZSHI0uVO

#ICML2025 #AI #DatasetRelease #Agents