80 citations · 174 across the 31 of their papers we have counts for
36 papers
Longitudinal Brain Aging in Covariance Space: Temporally Calibrated Bayesian Inference for Adaptive Covariance Operators
Montserrat Fuentes, Yi Zhao
Functional brain aging is often characterized by differences between people of different ages, although aging unfolds within individuals. This distinction is especially important f…
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng +3
Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent exper…
Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods
Michal Moshkovitz, Suraj Srinivas, Lesia Semenova +7
Despite the proliferation of Explainable AI (XAI) techniques -- from feature attributions to sparse autoencoders -- explanations rarely influence real-world workflows. In practice,…
On the Generalization Gap in Self-Evolving Language Model Reasoning
Zhenting Qi, Susanna Maria Baby, Stefanie Anna Baby +5
Recent work suggests that large language models (LLMs) can improve through self-evolution (SE), using supervision signals generated by the model itself. In this work, we ask: under…
Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time Methods
Avrim Blum, Daniel Hsu, Cyrus Rashtchian +1
Test-time augmentation, such as Retrieval-Augmented Generation (RAG) or tool use, critically depends on an interplay between a model's parametric knowledge and externally retrieved…
Latent Concept Disentanglement in Transformer-based Language Models
Guan Zhe Hong, Bhavya Vasudeva, Vatsal Sharan +3
When large language models (LLMs) use in-context learning (ICL) to solve a new task, they must infer latent concepts from demonstration examples. This raises the question of whethe…
Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
Hailey Joren, Jianyi Zhang, Chun-Sung Ferng +3
Augmenting LLMs with context leads to improved performance across many applications. Despite much research on Retrieval Augmented Generation (RAG) systems, an open question is whet…
A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning
Guan Zhe Hong, Nishanth Dikkala, Enming Luo +3
Due to the size and complexity of modern large language models (LLMs), it has proven challenging to uncover the underlying mechanisms that models use to solve reasoning problems. F…
SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models
Jianyi Zhang, Da-Cheng Juan, Cyrus Rashtchian +3
Large language models (LLMs) have demonstrated remarkable capabilities, but their outputs can sometimes be unreliable or factually incorrect. To address this, we introduce Self Log…
Imagen 3
Imagen-Team-Google, :, Jason Baldridge +257
We introduce Imagen 3, a latent diffusion model that generates high quality images from text prompts. We describe our quality and responsibility evaluations. Imagen 3 is preferred…
Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings
Olivia Wiles, Chuhan Zhang, Isabela Albuquerque +11
While text-to-image (T2I) generative models have become ubiquitous, they do not necessarily generate images that align with a given prompt. While previous work has evaluated T2I al…
DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback
Jiao Sun, Deqing Fu, Yushi Hu +8
Despite their wide-spread success, Text-to-Image models (T2I) still struggle to produce images that are both aesthetically pleasing and faithful to the user's input text. We introd…
Substance or Style: What Does Your Image Embedding Know?
Cyrus Rashtchian, Charles Herrmann, Chun-Sung Ferng +5
Probes are small networks that predict properties of underlying data from embeddings, and they provide a targeted, effective way to illuminate the information contained in embeddin…
Benchmarking Robustness to Adversarial Image Obfuscations
Florian Stimberg, Ayan Chakrabarti, Chun-Ta Lu +9
Automated content filtering and moderation is an important tool that allows online platforms to build striving user communities that facilitate cooperation and prevent abuse. Unfor…
A Theoretical View on Sparsely Activated Networks
Cenk Baykal, Nishanth Dikkala, Rina Panigrahy +2
Deep and wide neural networks successfully fit very complex functions today, but dense models are starting to be prohibitively expensive for inference. To mitigate this, one promis…
Multivariate Analytic Combinatorics for Cost Constrained Channels
Andreas Lenz, Stephen Melczer, Cyrus Rashtchian +1
Analytic combinatorics in several variables is a branch of mathematics that deals with deriving the asymptotic behavior of combinatorial quantities by analyzing multivariate genera…
Lower Bounds on the Total Variation Distance Between Mixtures of Two Gaussians
Sami Davies, Arya Mazumdar, Soumyabrata Pal +1
Mixtures of high dimensional Gaussian distributions have been studied extensively in statistics and learning theory. While the total variation distance appears naturally in the sam…
Average-Case Communication Complexity of Statistical Problems
Cyrus Rashtchian, David P. Woodruff, Peng Ye +1
We study statistical problems, such as planted clique, its variants, and sparse principal component analysis in the context of average-case communication complexity. Our motivation…
Approximate Trace Reconstruction
Sami Davies, Miklos Z. Racz, Cyrus Rashtchian +1
In the usual trace reconstruction problem, the goal is to exactly reconstruct an unknown string of length after it passes through a deletion channel many times independently, p…
Batch Optimization for DNA Synthesis
Konstantin Makarychev, Miklos Z. Racz, Cyrus Rashtchian +1
Large pools of synthetic DNA molecules have been recently used to reliably store significant volumes of digital data. While DNA as a storage medium has enormous potential because o…
Probing Predictions on OOD Images via Nearest Categories
Yao-Yuan Yang, Cyrus Rashtchian, Ruslan Salakhutdinov +1
We study out-of-distribution (OOD) prediction behavior of neural networks when they classify images from unseen classes or corrupted images. To probe the OOD behavior, we introduce…
Unsupervised Embedding of Hierarchical Structure in Euclidean Space
Jinyu Zhao, Yi Hao, Cyrus Rashtchian
Deep embedding methods have influenced many areas of unsupervised learning. However, the best methods for learning hierarchical structure use non-Euclidean representations, whereas…
Trace Reconstruction Problems in Computational Biology
Vinnu Bhardwaj, Pavel A. Pevzner, Cyrus Rashtchian +1
The problem of reconstructing a string from its error-prone copies, the trace reconstruction problem, was introduced by Vladimir Levenshtein two decades ago. While there has been c…
ExKMC: Expanding Explainable -Means Clustering
Nave Frost, Michal Moshkovitz, Cyrus Rashtchian
Despite the popularity of explainable AI, there is limited work on effective methods for unsupervised learning. We study algorithms for -means clustering, focusing on a trade-of…