Russ Salakhutdinov
@rsalakhu.bsky.social
VP of Research, GenAI @ Meta (Multimodal LLMs, AI Agents), UPMC Professor of Computer Science at CMU, ex-Director of AI research at @Apple, co-founder Perceptual Machines (acquired by Apple)
New work on automated prompt engineering for personalized text-to-image generation:
PRISM: Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
Paper + Code: kellyyutonghe.github.io/prism/
PRISM: Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
Paper + Code: kellyyutonghe.github.io/prism/
April 28, 2025 at 10:51 PM
New work on automated prompt engineering for personalized text-to-image generation:
PRISM: Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
Paper + Code: kellyyutonghe.github.io/prism/
PRISM: Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
Paper + Code: kellyyutonghe.github.io/prism/
www.llama.com
Llama4 models are out! Open sourced! Check them out:
“Native multimodality, mixture-of-experts models, super long context windows, step changes in performance, and unparalleled efficiency. All in easy-to-deploy sizes custom fit for how you want to use it”
Llama4 models are out! Open sourced! Check them out:
“Native multimodality, mixture-of-experts models, super long context windows, step changes in performance, and unparalleled efficiency. All in easy-to-deploy sizes custom fit for how you want to use it”
Llama
The open-source AI models you can fine-tune, distill and deploy anywhere. Choose from our collection of models: Llama 4 Maverick and Llama 4 Scout.
www.llama.com
April 5, 2025 at 7:18 PM
www.llama.com
Llama4 models are out! Open sourced! Check them out:
“Native multimodality, mixture-of-experts models, super long context windows, step changes in performance, and unparalleled efficiency. All in easy-to-deploy sizes custom fit for how you want to use it”
Llama4 models are out! Open sourced! Check them out:
“Native multimodality, mixture-of-experts models, super long context windows, step changes in performance, and unparalleled efficiency. All in easy-to-deploy sizes custom fit for how you want to use it”
New work #ICLR2025 on “Dissecting Adversarial Robustness of Multimodal LM Agents” that shows that one can successfully break latest agents that use black-box frontier LLMs, including agents that perform reflection and tree search.
Paper + Code + Data: chenwu.io/attack-agent/
Paper + Code + Data: chenwu.io/attack-agent/
Dissecting Adversarial Robustness of Multimodal LM Agents
Dissecting Adversarial Robustness of Multimodal LM Agents
chenwu.io
February 19, 2025 at 10:16 PM
New work #ICLR2025 on “Dissecting Adversarial Robustness of Multimodal LM Agents” that shows that one can successfully break latest agents that use black-box frontier LLMs, including agents that perform reflection and tree search.
Paper + Code + Data: chenwu.io/attack-agent/
Paper + Code + Data: chenwu.io/attack-agent/
Excited to be at the GenAI Summit at UCSD!
I'll be sharing our latest work on VisualWebArena, inference-time tree search, and Internet-scale training of LLM Agents.
genaisummit2025.ucsd.edu
I'll be sharing our latest work on VisualWebArena, inference-time tree search, and Internet-scale training of LLM Agents.
genaisummit2025.ucsd.edu
GenAI Summit 2025
#GenAIUCSD25
genaisummit2025.ucsd.edu
February 19, 2025 at 5:19 PM
Excited to be at the GenAI Summit at UCSD!
I'll be sharing our latest work on VisualWebArena, inference-time tree search, and Internet-scale training of LLM Agents.
genaisummit2025.ucsd.edu
I'll be sharing our latest work on VisualWebArena, inference-time tree search, and Internet-scale training of LLM Agents.
genaisummit2025.ucsd.edu
1/4 New Work on InSTA: A pipeline for Internet-scale training of web agents across 150k diverse websites without human annotations.
Paper + Code: data-for-agents.github.io
Environment: github.com/data-for-age...
Paper + Code: data-for-agents.github.io
Environment: github.com/data-for-age...
February 12, 2025 at 2:21 AM
1/4 New Work on InSTA: A pipeline for Internet-scale training of web agents across 150k diverse websites without human annotations.
Paper + Code: data-for-agents.github.io
Environment: github.com/data-for-age...
Paper + Code: data-for-agents.github.io
Environment: github.com/data-for-age...
1/3 New work on Self-Regulation and Requesting Interventions: Enabling agents with a limited intervention budget to decide when to seek help:
Paper: soyeonm.github.io/self_reg/
We develop an offline framework that trains a helper policy to request interventions by combining LLM-based PRMs with RL
Paper: soyeonm.github.io/self_reg/
We develop an offline framework that trains a helper policy to request interventions by combining LLM-based PRMs with RL
February 10, 2025 at 10:28 PM
1/3 New work on Self-Regulation and Requesting Interventions: Enabling agents with a limited intervention budget to decide when to seek help:
Paper: soyeonm.github.io/self_reg/
We develop an offline framework that trains a helper policy to request interventions by combining LLM-based PRMs with RL
Paper: soyeonm.github.io/self_reg/
We develop an offline framework that trains a helper policy to request interventions by combining LLM-based PRMs with RL
Reposted by Russ Salakhutdinov
🌲 Ruslan Salakhutdinov (@rsalakhu.bsky.social) from CMU (@scsatcmu.bsky.social) opened the workshop with a talk on Tree Search for Language Model Agents.
Timestamp 36:20 in neurips.cc/virtual/2024...
📎 arxiv.org/abs/2407.01476
#NeurIPS2024 #AdaptiveFoundationModels
Timestamp 36:20 in neurips.cc/virtual/2024...
📎 arxiv.org/abs/2407.01476
#NeurIPS2024 #AdaptiveFoundationModels
December 19, 2024 at 4:59 AM
🌲 Ruslan Salakhutdinov (@rsalakhu.bsky.social) from CMU (@scsatcmu.bsky.social) opened the workshop with a talk on Tree Search for Language Model Agents.
Timestamp 36:20 in neurips.cc/virtual/2024...
📎 arxiv.org/abs/2407.01476
#NeurIPS2024 #AdaptiveFoundationModels
Timestamp 36:20 in neurips.cc/virtual/2024...
📎 arxiv.org/abs/2407.01476
#NeurIPS2024 #AdaptiveFoundationModels
Reposted by Russ Salakhutdinov
🎉 Had fun at #NeurIPS2024 Workshop on #AdaptiveFoundationModels!
🚀 Speakers: @rsalakhu.bsky.social @sedielem.bsky.social Kate Saenko, Matthias Bethge / @vishaalurao.bsky.social Minjoon Seo, Bing Liu, Tianqi Chen
🌐Posters: adaptive-foundation-models.org/papers
🎬 neurips.cc/virtual/2024...
🧵Recap!
🚀 Speakers: @rsalakhu.bsky.social @sedielem.bsky.social Kate Saenko, Matthias Bethge / @vishaalurao.bsky.social Minjoon Seo, Bing Liu, Tianqi Chen
🌐Posters: adaptive-foundation-models.org/papers
🎬 neurips.cc/virtual/2024...
🧵Recap!
December 19, 2024 at 4:59 AM
🎉 Had fun at #NeurIPS2024 Workshop on #AdaptiveFoundationModels!
🚀 Speakers: @rsalakhu.bsky.social @sedielem.bsky.social Kate Saenko, Matthias Bethge / @vishaalurao.bsky.social Minjoon Seo, Bing Liu, Tianqi Chen
🌐Posters: adaptive-foundation-models.org/papers
🎬 neurips.cc/virtual/2024...
🧵Recap!
🚀 Speakers: @rsalakhu.bsky.social @sedielem.bsky.social Kate Saenko, Matthias Bethge / @vishaalurao.bsky.social Minjoon Seo, Bing Liu, Tianqi Chen
🌐Posters: adaptive-foundation-models.org/papers
🎬 neurips.cc/virtual/2024...
🧵Recap!
With my amazing students and collaborators at @neuripsconf.bsky.social in Vancouver!
December 15, 2024 at 5:05 PM
With my amazing students and collaborators at @neuripsconf.bsky.social in Vancouver!
Carnegie Mellon University at NeurIPS 2024 – Machine Learning Blog | ML@CMU | Carnegie Mellon University
Carnegie Mellon University is proud to present 194 papers at the 38th conference on Neural Information Processing Systems (NeurIPS 2024)
blog.ml.cmu.edu/2024/12/02/c...
Carnegie Mellon University is proud to present 194 papers at the 38th conference on Neural Information Processing Systems (NeurIPS 2024)
blog.ml.cmu.edu/2024/12/02/c...
Carnegie Mellon University at NeurIPS 2024
Carnegie Mellon University is proud to present 194 papers at the 38th conference on Neural Information Processing Systems (NeurIPS 2024), held from December 10-15 at the Vancouver Convention Center. H...
blog.ml.cmu.edu
December 3, 2024 at 3:34 PM
Carnegie Mellon University at NeurIPS 2024 – Machine Learning Blog | ML@CMU | Carnegie Mellon University
Carnegie Mellon University is proud to present 194 papers at the 38th conference on Neural Information Processing Systems (NeurIPS 2024)
blog.ml.cmu.edu/2024/12/02/c...
Carnegie Mellon University is proud to present 194 papers at the 38th conference on Neural Information Processing Systems (NeurIPS 2024)
blog.ml.cmu.edu/2024/12/02/c...
1/2 New work on Evaluating Deep Unlearning in Large Language Models.
Paper: arxiv.org/abs/2410.15153
Unlearning specific facts in LLMs is challenging because the facts in LLMs can be deduced from each other. This work proposes a framework for deep unlearning of facts that are interrelated.
Paper: arxiv.org/abs/2410.15153
Unlearning specific facts in LLMs is challenging because the facts in LLMs can be deduced from each other. This work proposes a framework for deep unlearning of facts that are interrelated.
Evaluating Deep Unlearning in Large Language Models
Machine unlearning is a key requirement of many data protection regulations such as GDPR. Prior work on unlearning has mostly considered superficial unlearning tasks where a single or a few related pi...
arxiv.org
December 3, 2024 at 2:42 PM
1/2 New work on Evaluating Deep Unlearning in Large Language Models.
Paper: arxiv.org/abs/2410.15153
Unlearning specific facts in LLMs is challenging because the facts in LLMs can be deduced from each other. This work proposes a framework for deep unlearning of facts that are interrelated.
Paper: arxiv.org/abs/2410.15153
Unlearning specific facts in LLMs is challenging because the facts in LLMs can be deduced from each other. This work proposes a framework for deep unlearning of facts that are interrelated.
What is happening?! Who is this? 😆
November 24, 2024 at 12:22 AM
What is happening?! Who is this? 😆