Iman Mirzadeh
@i_mirzadeh
Followers
1K
Following
441
Media
4
Statuses
38
Machine Learning Research Engineer @Apple | opinions are my own.
Seattle
Joined October 2024
RT @FartashFg: Is your AI keeping Up with the world?. Announcing #NeurIPS2025 CCFM Workshop: Continual and Compatible Foundation Model Upda….
0
10
0
RT @OncelTuzel: Come work with us! The Machine Learning Research (MLR) team at Apple is seeking a passionate AI researcher to work on Effic….
0
28
0
RT @EpochAIResearch: The biggest weakness was a lack of creativity and deep understanding. This is perhaps most aptly captured by a quote f….
0
15
0
RT @GaryMarcus: Healthy and unhealthy strategies for coping with the Apple paper:. - attack Apple for publishing it (which does nothing to….
0
10
0
RT @MFarajtabar: 🧵 1/8 The Illusion of Thinking: Are reasoning models like o1/o3, DeepSeek-R1, and Claude 3.7 Sonnet really "thinking"? 🤔 O….
0
588
0
I will be attending #ICLR this week to present our GSM-Symbolic paper, and we also have a full-time opening on our team! Let me know if you're interested in discussing reasoning and/or joining us!.
We are #hiring for a full time #research engineer/scientist position in our research team at #Apple on understanding and improving #reasoning capabilities of #LLMs. The ideal candidate: .- Has prior publications on LLM reasoning, planning, tool use, agentic LLMs, and related.
0
3
14
It was a pleasure joining @MLStreetTalk during the NeurIPS conference in December. While it might seem that a lot has changed over the past 3 months (e.g., with new models like o3/R1), I still believe the current models are not capable of reasoning :).
4
2
16
Exactly! I wish that at least academic people understood this. "All" models we have today are trained using cross-entropy to fit a distribution => By design, It is "impossible" for them to generate anything outside of that distribution.
It's unclear to me how these two ideas coexist in some people's minds:. 1) I train a model to copy its input, and I punish it if the copy is not exact. 2) I expect the model to design new algorithms, solve unsolved math problems, and do creative writing.
0
0
13
Amazing analysis! This has been THE question I was thinking about every single day in the past month. Although, I think if the model knows the algorithm (multiplication), we can only measure the accuracy of execution by the model and not necessarily their search/reasoning power.
To sum up, I'm still trying to wrap my head around this! why do recent frontier LLMs struggle on simple math if results on extremely hard math problems show some "signs of reasoning". Different hypotheses:.1⃣ CoT in data & RL are not enough to teach them proper search &.
0
0
10
RT @PierreAblin: 🍏🍏🍏 Come work with us at Apple Machine Learning Research! 🍏🍏🍏. Our team focuses on curiosity-based, open research. We wor….
0
36
0
We have open-sourced GSM-Symbolic templates and generated data! 🎉.- Github: .- Hugging Face: . I will be also attending #NeurIPS2024. If you are also attending and would like to discuss research ideas on reasoning, let's connect :).
8
4
41
RT @AtoosaChegini: 1/🔔Excited to share my internship work, SALSA: Soup-based Alignment Learning for Stronger Adaptation, (NeurIPS workshop….
0
4
0
RT @MFarajtabar: 1/ LLM inference is very expensive; and LLMs don't necessarily use their full capacity to respond to a specific prompt. Th….
0
56
0
RT @MFarajtabar: ** Intern position on LLM reasoning **. @mchorton1991, @i_mirzadeh, @KeivanAlizadeh2.and I are co-hosting an intern positi….
0
25
0
RT @sineadwilliamso: 📢Internships at Apple ML Research🍏. We’re looking for a PhD research intern with interests in uncertainty quantificati….
0
70
0
RT @MFarajtabar: 1/ Can Large Language Models (LLMs) truly reason? Or are they just sophisticated pattern matchers? In our latest preprint,….
0
1K
0
I was waiting and hoping the ML community on Twitter would move over to Mastodon so I wouldn't have to create an account here. But, well… here we are! :).
0
0
3