In NAVSIM #NeurIPS24, we use simulation metrics for end-to-end driving by unrolling BEV abstractions of scenes for a few seconds. The result? Open-loop evaluation that is better aligned with closed-loop evaluation compared to traditional open loop metrics. github.com/autonomousvi...
🚗💡 Smarter driving starts with better world models! Vista predicts high-fidelity driving scenarios with versatile control. #AI #AutonomousVehicles #NeurIPS24
github.com/OpenDriveLab...
With @hongyang.bsky.social @kashyap7x.bsky.social
🚀 Names matter! We show that better class names in open-vocabulary segmentation benchmarks greatly improve dataset quality and boost model performance. RENOVATE your dataset labels with our automatic framework! #AI #ComputerVision #NeurIPS24
andrehuang.github.io/renovate/
The @turingpost.bsky.social send out a survey to its readers. Starting the thing, I already felt excluded a bit 👇👇👇
But hey, being at #Neurips24 already gave be impression that being in academia and working on #AI is a niche profession these days. 🤷
Subsequent to #neurips24, we had the chance to give a seminar at #LBNL. @lbnlcs.bsky.social It was great seeing old friends @axccl.bsky.social.
To complete the swirl, we visited @loicaroyer.bsky.social at @cziscience.bsky.social in downtown SF. What an inspiring day! @helmholtzai.bsky.social
What are your biggest takes from attending #NeurIPS24? Where do you think the field is moving/should move?
Final Invited talk: Hannah Rose Kirk (Oxford)
Putting the H Back in RLHF: Challenging assumptions of human behaviour for AI alignment — #behavioralml workshop at #neurips2024 #neurips #neurips24 behavioralml.org
3:45-4:15pm: Invited talk: Hoda Heidari (CMU)
Examining large language models as qualitative research participants — really relevant work for LLM human behavior simulation. #neurips2024 #neurips #neurips24
Understanding how algorithms “misunderstand” us and vice versa. Dr. Sendhil Mullainathan (MIT) #neurips2024 #neurips24 #neurips #behavioralml behavioral.org
“Choices does not equal preferences” “clicks are not preferences” Dr. Sendhil Mullainathan (MIT) #neurips2024 #neurips24 #neurips at the #behavioralml workshop behavioralml.org
Photos from the #behavioralml
Workshop invited talk on theory and data for prediction. #neurips #neurips2024 #neurips24
Invited talk: Sendhil Mullainathan (MIT) on
Misunderstandings for the #behavioralml workshop. The understandings between human and algorithm. The room is packed! #neurips2024 #neurips #neurips24 behavioral.org
Standing room only at #BehavioralML workshop! 1:00-1:30pm: Invited talk: Tom Griffiths (Princeton)
Combining theory and data to predict and explain human decisions #neurips2024 #neurips24 #neurips behavioralml.org
Catch my talk at the CZI virtual cells AI workshop at #NeurIPS24 to gain insight into how we develop the foundational elements of AI for biology at @Bioptimus and how we apply them at @Owkin to add value throughout the entire drug development process:
Behavioral ML workshop expert panel (behavioralml.org) 10:45-11:45am: Panel (Michael Bernstein, Andreea Bobu, Tom Griffiths, Hoda Heidari, Hannah Rose Kirk, Jon Kleinberg, Sendhil Mullainathan, moderated by Katie Collins) #neurips2024 #neurips #neurips24 #behavioralml
Learning to Cooperate with Humans using Generative Agents (Yancheng Liang, Daphne Chen, Abhishek Gupta, Simon Shaolei Du, Natasha Jaques) — looking at performance in the Overcooked multi agent game! @natashajaques.bsky.social #neurips2024 #neurips24 #neurips #behavioralml
Words that work: Using language to generate hypotheses (Rafael M. Batista, James Ross) #neurips2024 #neurips #neurips24 #behavioralml workshop behavrioralml.org
Superficial Alignment, Subtle Divergence, and Nudge Sensitivity in LLM Decision-Making (Manuel Cherep, Nikhil Singh, Patricia Maes) #neurips2024 #neurips #neurips24 #behavioralml workshop
The Double-Edged Sword of Behavioral Responses in Strategic Classification (Raman Ebrahimi, Kristen Vaccaro, Parinaz Naghizadeh) #neurips2024 #neurips24 #neurips #behavioralml
Spotlight talks for #behavioralml #neurips2024 #neurips24 #neurips behavioral.org PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences (Daiwei Chen, Yi Chen, Aniket Rege, Ramya Korlakai Vinayak)
“Can we create general purpose computational human behavior across domains?” “behavioral simulation empowers science and design.” From the Sims to LLMs. Dr. Michael Berstein (Stanford) #neurips24 #behavioralml #neurips behavioralml.org
“Structure learning by learning representations.” Design to represent human cognition enables more efficient human aligned robot learning. From Dr. Andreea Bobu (MIT) #behavioralml #neurips24 #neurips behavioralml.org
🚀 #NeurIPS24: Excited to share UniGuide! We've developed a new approach for molecular diffusion models that enables flexible geometric conditioning across tasks—no retraining required.
👉 Come to our poster #2600 (East) today at 11am
📎Paper: t.co/92UJBKn4WZ
from the wonders of @neuripsconf.bsky.social #NeurIPS24
part 31/101
the #coffe truck outside the Convention center with its effective #advertisment strategy
Anyone else feeling extremely overwhelmed by the sheer amount of information, connections, ideas and opportunities at NeurIPS? So hard to pause for a second and process. Will need to digest this for weeks to come. #NeurIPS24
If you're attending #NeurIPS2024, don't miss our spotlight poster on multicriteria benchmarking TODAY 11am in West Ballroom A-D
Talk: neurips.cc/virtual/2024...
Paper: openreview.net/pdf?id=jXxvS...
Where? West Ballroom A-D #6501
When? Thu 12 Dec 11 a.m. - 2 p.m. local time
#neurips #neurips24
