Mar 16
Review request:
As usual for the time of year, I'll be looking for #IROS2026 reviewers. Highly interesting stack of papers on #ReinforcementLearning #Sim2Real #RewardLearning #LLMs #DataEfficiency #RoboticManipulation
Reach out with your ID or papercept registered mail address and background. Looking forward to working together!
7
6
54
9,754
19 Aug 2025
📢 Blockchain in EdTech: Changing How We Recognize & Reward Learning 🎓✨
1️⃣ Learn-to-Earn in Action
2️⃣ DID/VC-Based Credentials
3️⃣ Trends Worth Watching 👀
4️⃣ Why It Matters 🚀
👉 More info: bit.ly/4lCsHzX
#XIIID #AItutor #Web3AI #Education #L2E #EdTech #RewardLearning
🌐 Join Our Official Channels:
• Website: xiiid.ai
• X: x.com/xiiid_official
• Telegram: t.me/xiiid_channel
1
5
6
2,514
28 Oct 2024
Happy to share our latest #CoRL2024 paper, "Learning Transparent #Reward Models via Unsupervised Feature Selection". @GokhanAlcan_ Kevin Sebastian Luck @VKyrki
Website: sites.google.com/view/transp…
#inversereinforcementlearning #rewardlearning #robotics #CoRL2024
5
197
12 Dec 2023
#DPO instilled a lot of interesting conversations and research discussions around #RLHF #rewardlearning
Great to see it being recognized and Congratulations to @rm_rafailov @ericmitchellai @architsharma @chelseabfinn and team.
P.S .: #Alignment of #LLMs #GenAI is is crucial
12 Dec 2023
DPO is a runner up for NeurIPS outstanding paper. 🙌
Big congrats especially to the students @rm_rafailov @archit_sharma97 @ericmitchellai & the other awardees.
If you haven't learned about DPO already, check out the oral & poster 👇 on Thurs afternoon.
ALT Poster for the DPO paper, including an overview of how DPO optimizes the same objective as RLHF without RL, a description of the RLHF process, a description of the DPO objective, and an overview of the results on sentiment generation, summarization, and single-turn dialogue problems.
1
8
1,341
It's the final day of #SfN2023 , but the sessions are still in full swing! Having great chats with researchers this a.m. about their work in #rewardlearning, #tbi, and #neuroprotection - among many more! #neuroscience
1,692
📢Welcome to project 5! 💡Today, we delve into the fascinating world of dopamine, sex hormones, and mood. Meet Zsofia @zsoffzsoff, a dedicated PhD candidate from @neuromadlab, focusing on women’s mental health and positive valence in her research. 🌟 1/7 #RewardLearning #Dopamine
1
3
10
884
14 Jun 2023
Wonderful memories made with @rewardlearning, @ChrissiKru & Lauren before they left the EVAlabs 💔❤️
14 Jun 2023
Sadly we don't only have people join the lab...they also leave. We don't let them leave empthy handed though! We laughed, we cried, and all three of you will be missed!
3
184
12 Feb 2023
Missed the #CNSnightcap?
👉👉 Watch it's Premiere on Monday 13th February at 4 pm: youtu.be/5KAFlBty4Sk 👈👈
#ChatGPT - What role will text-generating AI play in #teaching and #research?
#innovation #ai #techinnovation #chatgpt #ethics #rewardlearning #publishing
ALT ChatGPT (Chat Generative Pre-trained Transformer) has caused a stir across many professions and has been a hot topic of debate across universities and publishing houses. The tool has exceeded expectations and even passed academic exams raising several ethical considerations about ownership, authorship, and plagiarism. We discuss these considerations and how the model was trained to be effective and politically correct, which also raised further critiques on potential biases and the method of training.
1
2
4
1,529
24 Nov 2022
PyTorch provides open-source implementations of imitation and rewardlearning algorithms in PyTorch.
📄 arxiv.org/abs/2211.11972v1
2
22 Aug 2022
@rewardlearning Yes! Kind of alarming to know that room is there. Definitely ups the castle's 'spook' factor 😂
2
31 Jul 2022
A Recent Research From @Harvard and #KeioUniversity Researchers Present A New Link
Between Dopamine-Based #RewardLearning And #MachineLearning
marktechpost.com/2022/07/30/… #fintech #AI #ArtificialIntelligence @asifrazzaq1988 @MarkTechPost
6
10
10 Jun 2022
How did #covid19 lockdown measures affect our mood? So many things happened since 2020 that this is difficult to say. Our #preregistered study with @rewardlearning contributes another piece to the puzzle and just got published #openaccess in @FrontPsychol: frontiersin.org/articles/10.…
1
1
4
22 Mar 2022
Meet the team!
Remember our group pic? it was taken by our post-doc Chris Valuch @rewardlearning! At the EVAlab, he collaborates with partners from the smartphone industry to develop a model of the aesthetic quality of photos, overlapping with his own passion for photography.
7
9 Mar 2022
looks like a big happy family... love how @Dr_D_J managed to still squeeze in a tiny bit of red in the black pic :-)
2
9 Mar 2022
A lab can be like a family, on the left we have a classic awkward family photo on the right the party pic. Which of our sides do you like better?
Both pics of the EVA-labs with @ARTIS_H2020 team were made by our lovely team member Chris Valuch @rewardlearning!
3
3
27
20 Jan 2022
Check out this awesome #postdoc program @umichmedicine! & I am still looking for a #postdoc to join the @Flagel_Lab in the coming months. If interested in #behavioralneuroscience, #deepphenotyping, #motivation, #rewardlearning, #neuralcircuits, #individualdifferences, reach out!
19 Jan 2022
The Michigan Postdoctoral Pioneer Program is accepting applications from entering and first year postdocs! The MP3 program provides a generous stipend and mentoring for motivated and accomplished post-doc fellows interested in a career in research. RT umichpioneerprogram.org/
6
16
9 Dec 2021
This is my general concern with the use of density plots. The parameters in density plots are really unintuitive. Whereas with histograms, bin_width is pretty straight forward to understand.
1
2
17 Sep 2021
@NadineGogolla @triciajanak, Brigitte Kieffer, PhD
Leon Coleman, MD, PhD, Véronique Deroche-Gamonet, PhD, Peter Kalivas, PhD, Huib Mansvelder, PhD #Neurobiology #Addiction #rewardlearning @AddictionNeuro @worldwideneuro
CHECK IT OUT👉world-wide.org/Neuro/Neurobi…
1
4
18 Feb 2021
Thanks! I def think it's a possibility that "seeing shapes in the noise" may be influencing preference (see table attached of labels given to 1/f noise movies from Billock 2001 JOSA A)... I didn't address this in my paper, but def food for thought in future work!
ALT https://doi.org/10.1364/JOSAA.18.002404
2
5 Jan 2021
Great to be starting the year with the virtual #BCCCD21 conference! Our presentation on “Development and relation of predictive context processing and Theory of Mind” with @rewardlearning will take place today at 8pm and tomorrow at 8am. Looking forward to seeing you!
1
7