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/
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)
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”
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.
llama.com
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/
Dissecting Adversarial Robustness of Multimodal LM Agents
Dissecting Adversarial Robustness of Multimodal LM Agents
chenwu.io
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
GenAI Summit 2025
#GenAIUCSD25
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...
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
blog.ml.cmu.edu/2025/01/08/o...
Optimizing LLM Test-Time Compute Involves Solving a Meta-RL Problem
Figure 1: Training models to optimize test-time compute and learn "how to discover" correct responses, as opposed to the traditional learning paradigm of learning "what answer" to output. The major...
blog.ml.cmu.edu
blog.ml.cmu.edu/2025/01/02/i...
Inductive biases of neural network modularity in spatial navigation
TL;DR: The brain may have evolved a modular architecture for daily tasks, with circuits featuring functionally specialized modules that match the task structure. We hypothesize that this architecture ...
blog.ml.cmu.edu
🌲 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
🎉 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!
blog.ml.cmu.edu/2024/12/06/s...
ScribeAgent: Fine-Tuning Open-Source LLMs for Enhanced Web Navigation
TL;DR: LLM web agents are designed to predict a sequence of actions to complete a user-specified task. Most existing agents are built on top of general-purpose, proprietary models like GPT-4 and rely ...
blog.ml.cmu.edu
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 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
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.
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
