December 11, 2024 at 1:51 AM
🚀 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/
andrehuang.github.io/renovate/
February 26, 2025 at 2:45 PM
🚀 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/
andrehuang.github.io/renovate/
🚗💡 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
github.com/OpenDriveLab...
With @hongyang.bsky.social @kashyap7x.bsky.social
February 27, 2025 at 8:03 AM
🚗💡 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
github.com/OpenDriveLab...
With @hongyang.bsky.social @kashyap7x.bsky.social
Excited that our multi-agent LLM agent work, “Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents,” will be presented at #NeurIPS24 -- reach out if you want to meet up in Vancouver!
December 5, 2024 at 5:03 PM
Excited that our multi-agent LLM agent work, “Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents,” will be presented at #NeurIPS24 -- reach out if you want to meet up in Vancouver!
from the wonders of @neuripsconf.bsky.social #NeurIPS24
part 31/101
the #coffe truck outside the Convention center with its effective #advertisment strategy
part 31/101
the #coffe truck outside the Convention center with its effective #advertisment strategy
December 13, 2024 at 1:11 PM
from the wonders of @neuripsconf.bsky.social #NeurIPS24
part 31/101
the #coffe truck outside the Convention center with its effective #advertisment strategy
part 31/101
the #coffe truck outside the Convention center with its effective #advertisment strategy
Just came across this interesting blog post on the job market for new PhD grads in AI: kyunghyuncho.me/i-sensed-anxiety-and-frustration-at-neurips24
The argument feels pretty reasonable. Here is my take: (1/6)
#MLSky #NeuroAI 🧠📈
The argument feels pretty reasonable. Here is my take: (1/6)
#MLSky #NeuroAI 🧠📈
January 3, 2025 at 4:02 PM
Just came across this interesting blog post on the job market for new PhD grads in AI: kyunghyuncho.me/i-sensed-anxiety-and-frustration-at-neurips24
The argument feels pretty reasonable. Here is my take: (1/6)
#MLSky #NeuroAI 🧠📈
The argument feels pretty reasonable. Here is my take: (1/6)
#MLSky #NeuroAI 🧠📈
This will be fun the next coming days! #neurips24
December 11, 2024 at 4:00 AM
This will be fun the next coming days! #neurips24
What are your biggest takes from attending #NeurIPS24? Where do you think the field is moving/should move?
December 15, 2024 at 5:50 PM
What are your biggest takes from attending #NeurIPS24? Where do you think the field is moving/should move?
the Sepp Hochreiter on stage at #NeurIPS24 for the Posner lecture
on the different stages in science, engineering and industrialization
(early, 8.30am, but very nice to start the day)
on the different stages in science, engineering and industrialization
(early, 8.30am, but very nice to start the day)
December 11, 2024 at 4:42 PM
the Sepp Hochreiter on stage at #NeurIPS24 for the Posner lecture
on the different stages in science, engineering and industrialization
(early, 8.30am, but very nice to start the day)
on the different stages in science, engineering and industrialization
(early, 8.30am, but very nice to start the day)
Anyone I know going to Neurips24?
November 27, 2024 at 4:45 AM
Anyone I know going to Neurips24?
Interested in predicting transcriptomic effects of perturbations? Check out our @NeurIPS24 D&B spotlight living perturbation prediction benchmark & new drug perturbation dataset:
- paper: openreview.net/forum?id=WTI... !
- benchmarking platform: openproblems.bio/results/pert...
🧵1/8
- paper: openreview.net/forum?id=WTI... !
- benchmarking platform: openproblems.bio/results/pert...
🧵1/8
A benchmark for prediction of transcriptomic responses to chemical...
Single-cell transcriptomics has revolutionized our understanding of cellular heterogeneity and drug perturbation effects. However, its high cost and the vast chemical space of potential drugs...
openreview.net
November 15, 2024 at 10:37 PM
Interested in predicting transcriptomic effects of perturbations? Check out our @NeurIPS24 D&B spotlight living perturbation prediction benchmark & new drug perturbation dataset:
- paper: openreview.net/forum?id=WTI... !
- benchmarking platform: openproblems.bio/results/pert...
🧵1/8
- paper: openreview.net/forum?id=WTI... !
- benchmarking platform: openproblems.bio/results/pert...
🧵1/8
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...
February 28, 2025 at 7:22 AM
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...
I am deeply troubled and shocked by MIT professor Rosalind Picard’s keynote speech at NeurIPS24 that included a racist comment about Chinese students. This type of implicit bias has no place in academia.
NeurIPS acknowledges that the cultural generalization made by the keynote speaker today reinforces implicit biases by making generalisations about Chinese scholars. This is not what NeurIPS stands for. NeurIPS is dedicated to being a safe space for all of us. 1/3
December 17, 2024 at 5:31 PM
I am deeply troubled and shocked by MIT professor Rosalind Picard’s keynote speech at NeurIPS24 that included a racist comment about Chinese students. This type of implicit bias has no place in academia.
Hey, #chemsky tweeps. If you are at #Neurips next week, visit our poster on ‘Applications of Modular Co-Design for De Novo 3D Molecule Generation’. neurips.cc/virtual/2024... Drop me a line if you want to chat about #ML4Scince #compchem and #GenAI #NeurIPS24
a 3d model of a chemical compound with a red and blue capsule
ALT: a 3d model of a chemical compound with a red and blue capsule
media.tenor.com
December 3, 2024 at 9:29 PM
Hey, #chemsky tweeps. If you are at #Neurips next week, visit our poster on ‘Applications of Modular Co-Design for De Novo 3D Molecule Generation’. neurips.cc/virtual/2024... Drop me a line if you want to chat about #ML4Scince #compchem and #GenAI #NeurIPS24
neural nets are so good... at finding #shortcuts to your downstream tasks!
how can you measure if they learned the right labels for the right reasons?
here is a cool dataset with labeled intermediate #concepts that you can use for concept-bottlenecks and #neurosymbolic #AI
at #NeurIPS24
how can you measure if they learned the right labels for the right reasons?
here is a cool dataset with labeled intermediate #concepts that you can use for concept-bottlenecks and #neurosymbolic #AI
at #NeurIPS24
📣 Does your model learn high-quality #concepts, or does it learn a #shortcut?
Test it with our #NeurIPS2024 dataset & benchmark track paper!
rsbench: A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
What's the deal with rsbench? 🧵
Test it with our #NeurIPS2024 dataset & benchmark track paper!
rsbench: A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
What's the deal with rsbench? 🧵
December 10, 2024 at 10:25 PM
neural nets are so good... at finding #shortcuts to your downstream tasks!
how can you measure if they learned the right labels for the right reasons?
here is a cool dataset with labeled intermediate #concepts that you can use for concept-bottlenecks and #neurosymbolic #AI
at #NeurIPS24
how can you measure if they learned the right labels for the right reasons?
here is a cool dataset with labeled intermediate #concepts that you can use for concept-bottlenecks and #neurosymbolic #AI
at #NeurIPS24
Workshop days are always the most engaging and rewarding. Here are my two picks for this weekend:
Saturday
Video-language
video-and-language-workshop-2024.webflow.io
Sunday
Multimodal algorithmic reasoning
marworkshop.github.io/neurips24/
Do you have other recommendations?
#NeurIPS #NeurIPS2024
Saturday
Video-language
video-and-language-workshop-2024.webflow.io
Sunday
Multimodal algorithmic reasoning
marworkshop.github.io/neurips24/
Do you have other recommendations?
#NeurIPS #NeurIPS2024
December 14, 2024 at 1:39 AM
Workshop days are always the most engaging and rewarding. Here are my two picks for this weekend:
Saturday
Video-language
video-and-language-workshop-2024.webflow.io
Sunday
Multimodal algorithmic reasoning
marworkshop.github.io/neurips24/
Do you have other recommendations?
#NeurIPS #NeurIPS2024
Saturday
Video-language
video-and-language-workshop-2024.webflow.io
Sunday
Multimodal algorithmic reasoning
marworkshop.github.io/neurips24/
Do you have other recommendations?
#NeurIPS #NeurIPS2024
Missed out on #Swift tickets? No worries—swing by our #SVFT poster at #NeurIPS2024 and catch *real* headliners! 🎤💃🕺
📌Where: East Exhibit Hall A-C #2207, Poster Session 4 East
⏲️When: Thu 12 Dec, 4:30 PM - 7:30 PM PST
#AI #MachineLearning #PEFT #NeurIPS24
📌Where: East Exhibit Hall A-C #2207, Poster Session 4 East
⏲️When: Thu 12 Dec, 4:30 PM - 7:30 PM PST
#AI #MachineLearning #PEFT #NeurIPS24
December 9, 2024 at 5:55 AM
Missed out on #Swift tickets? No worries—swing by our #SVFT poster at #NeurIPS2024 and catch *real* headliners! 🎤💃🕺
📌Where: East Exhibit Hall A-C #2207, Poster Session 4 East
⏲️When: Thu 12 Dec, 4:30 PM - 7:30 PM PST
#AI #MachineLearning #PEFT #NeurIPS24
📌Where: East Exhibit Hall A-C #2207, Poster Session 4 East
⏲️When: Thu 12 Dec, 4:30 PM - 7:30 PM PST
#AI #MachineLearning #PEFT #NeurIPS24
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
To complete the swirl, we visited @loicaroyer.bsky.social at @cziscience.bsky.social in downtown SF. What an inspiring day! @helmholtzai.bsky.social
December 18, 2024 at 5:46 AM
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
To complete the swirl, we visited @loicaroyer.bsky.social at @cziscience.bsky.social in downtown SF. What an inspiring day! @helmholtzai.bsky.social
🚀 #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
👉 Come to our poster #2600 (East) today at 11am
📎Paper: t.co/92UJBKn4WZ
December 13, 2024 at 5:51 PM
🚀 #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
👉 Come to our poster #2600 (East) today at 11am
📎Paper: t.co/92UJBKn4WZ
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
Putting the H Back in RLHF: Challenging assumptions of human behaviour for AI alignment — #behavioralml workshop at #neurips2024 #neurips #neurips24 behavioralml.org
December 15, 2024 at 12:24 AM
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
Putting the H Back in RLHF: Challenging assumptions of human behaviour for AI alignment — #behavioralml workshop at #neurips2024 #neurips #neurips24 behavioralml.org
Looking for a good workshop today?
#NeurIPS #NeurIPS2024
Multimodal Algorithmic Reasoning
(MAR)
📍West Exhibition Hall A
marworkshop.github.io/neurips24/
#NeurIPS #NeurIPS2024
Multimodal Algorithmic Reasoning
(MAR)
📍West Exhibition Hall A
marworkshop.github.io/neurips24/
December 15, 2024 at 4:09 PM
Looking for a good workshop today?
#NeurIPS #NeurIPS2024
Multimodal Algorithmic Reasoning
(MAR)
📍West Exhibition Hall A
marworkshop.github.io/neurips24/
#NeurIPS #NeurIPS2024
Multimodal Algorithmic Reasoning
(MAR)
📍West Exhibition Hall A
marworkshop.github.io/neurips24/
Attending NeurIPS 2024? Learn about simulating users for embodied agents!
Catch our work, "Simulating User Agents for Embodied Conversational AI," at the Open World Agents Workshop on Dec 15.
Poster: tinyurl.com/yc42h4ud
Audio: tinyurl.com/mr2hd35a
@dilekh.bsky.social @gokhantur.bsky.social
Catch our work, "Simulating User Agents for Embodied Conversational AI," at the Open World Agents Workshop on Dec 15.
Poster: tinyurl.com/yc42h4ud
Audio: tinyurl.com/mr2hd35a
@dilekh.bsky.social @gokhantur.bsky.social
Neurips24 Simulating Users.pptx
1 Acknowledgements Approach Results Motivation Introduction Simulating User Agents for Embodied Conversational AI Daniel Philipov, Vardhan Dongre, Gokhan Tur, Dilek Hakkani-Tür University of Illinois,...
tinyurl.com
November 18, 2024 at 10:19 PM
Attending NeurIPS 2024? Learn about simulating users for embodied agents!
Catch our work, "Simulating User Agents for Embodied Conversational AI," at the Open World Agents Workshop on Dec 15.
Poster: tinyurl.com/yc42h4ud
Audio: tinyurl.com/mr2hd35a
@dilekh.bsky.social @gokhantur.bsky.social
Catch our work, "Simulating User Agents for Embodied Conversational AI," at the Open World Agents Workshop on Dec 15.
Poster: tinyurl.com/yc42h4ud
Audio: tinyurl.com/mr2hd35a
@dilekh.bsky.social @gokhantur.bsky.social
I am totally in the FOMO mode, seeing #NeurIPS24 messages. I’m not there :( this year.
However, I recommend chatting with my co-authors and students :) @bartoszpiotrowski.bsky.social @albertqjiang.bsky.social @michalnauman @mateuszostaszewski.bsky.social
2 papers on the main track and spotlight
However, I recommend chatting with my co-authors and students :) @bartoszpiotrowski.bsky.social @albertqjiang.bsky.social @michalnauman @mateuszostaszewski.bsky.social
2 papers on the main track and spotlight
December 12, 2024 at 2:37 PM
I am totally in the FOMO mode, seeing #NeurIPS24 messages. I’m not there :( this year.
However, I recommend chatting with my co-authors and students :) @bartoszpiotrowski.bsky.social @albertqjiang.bsky.social @michalnauman @mateuszostaszewski.bsky.social
2 papers on the main track and spotlight
However, I recommend chatting with my co-authors and students :) @bartoszpiotrowski.bsky.social @albertqjiang.bsky.social @michalnauman @mateuszostaszewski.bsky.social
2 papers on the main track and spotlight
An excellent work comparing MAE- and JEPA-type SSL dynamics (the latter is commonly called non-contrastive). They get a closed-form ODE of i-th feature importance.
"How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks" (NeurIPS24)
arxiv.org/abs/2407.03475
"How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks" (NeurIPS24)
arxiv.org/abs/2407.03475
February 28, 2025 at 11:42 PM
An excellent work comparing MAE- and JEPA-type SSL dynamics (the latter is commonly called non-contrastive). They get a closed-form ODE of i-th feature importance.
"How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks" (NeurIPS24)
arxiv.org/abs/2407.03475
"How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks" (NeurIPS24)
arxiv.org/abs/2407.03475
I’m @neurips24! Let’s chat😁
December 10, 2024 at 6:28 PM
I’m @neurips24! Let’s chat😁