Ruslan Salakhutdinov
CMU professor and pioneer of deep learning; known for Boltzmann machines, dropout, and (more recently) WebArena, VisualWebArena, and agent benchmarks.
- Role
- professor
- Currently at
- Carnegie Mellon University
- Scholar
- scholar.google.com/citations
- Papers
- 32
Cite
Notes
Only stored in your browser.
Authored papers
32AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
arXiv 2025
Training a Generally Curious Agent
arXiv 2025
InSTA: Towards Internet-Scale Training For Agents
arXiv 2025
VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks
ACL
AgentKit: Structured LLM Reasoning with Dynamic Graphs
arXiv 2024
The BrowserGym Ecosystem for Web Agent Research
arXiv 2024
HEMM: Holistic Evaluation of Multimodal Foundation Models
arXiv 2024
Dissecting Adversarial Robustness of Multimodal LM Agents
arXiv 2024
Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference
arXiv 2024
Contrastive Difference Predictive Coding
arXiv 2023
Effective Data Augmentation With Diffusion Models
arXiv 2023
Grounding Language Models to Images for Multimodal Inputs and Outputs
arXiv 2023
Multimodal Graph Learning for Generative Tasks
arXiv 2023
Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data
arXiv 2023
Contrastive Example-Based Control
arXiv 2023
Generating Images with Multimodal Language Models
NeurIPS 2023 11
Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications
arXiv 2023
SPRING: Studying the Paper and Reasoning to Play Games
arXiv 2023
Confronting Reward Model Overoptimization with Constrained RLHF
arXiv 2023
MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts
arXiv 2023
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TMLR
Graph Generative Model for Benchmarking Graph Neural Networks
arXiv 2022
Conditional Contrastive Learning with Kernel
conditional-contrastive-learning-with-kernel
Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue
arXiv 2022
FILM: Following Instructions in Language with Modular Methods
film-following-instructions-in-language-with
ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers
ACL 2022 5
Towards Debiasing Sentence Representations
towards-debiasing-sentence-representations
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
transformer-xl-attentive-language-models-1
XLNet: Generalized Autoregressive Pretraining for Language Understanding
xlnet-generalized-autoregressive-pretraining-1
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
hotpotqa-a-dataset-for-diverse-explainable-1
Unsupervised Learning of Video Representations using LSTMs
arXiv 2015
Generating Images from Captions with Attention
arXiv 2015
Affiliations
Frequent co-authors
10from 32 papers
Louis-Philippe Morency
Jing Yu Koh
grad-student
Paul Pu Liang
Benjamin Eysenbach
Daniel Fried
professor
So Yeon Min
Yonatan Bisk
professor
Sergey Levine
professor
Yue Wu
Zhilin Yang