papers

Publications (12)

cs.LG2024

Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents

Evgenii Kortukov, Alexander Rubinstein, Elisa Nguyen +1

Retrieval-augmented generation (RAG) mitigates many problems of fully parametric language models, such as temporal degradation, hallucinations, and lack of grounding. In RAG, the m…

cs.CV2023

Leveraging Diffusion Disentangled Representations to Mitigate Shortcuts in Underspecified Visual Tasks

Luca Scimeca, Alexander Rubinstein, Armand Mihai Nicolicioiu +2

Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to shortcut learning phenomena, where a model may rely on erroneous, easy-to-…

cs.LG2024

Scalable Ensemble Diversification for OOD Generalization and Detection

Alexander Rubinstein, Luca Scimeca, Damien Teney +1

Training a diverse ensemble of models has several practical applications such as providing candidates for model selection with better out-of-distribution (OOD) generalization, and…

cs.LG2026

DISCO: Diversifying Sample Condensation for Efficient Model Evaluation

Alexander Rubinstein, Benjamin Raible, Martin Gubri +1

Evaluating modern machine learning models has become prohibitively expensive. Benchmarks such as LMMs-Eval and HELM demand thousands of GPU hours per model. Costly evaluation reduc…

eess.SY2013

Correction of inertial navigation system's errors by the help of video-based navigator based on Digital Terrarium Map

Oleg Kupervasser, Alexander Rubinstein

This paper deals with the error analysis of a novel navigation algorithm that uses as input the sequence of images acquired from a moving camera and a Digital Terrain (or Elevation…

cs.LG2026

MEME: Multi-entity & Evolving Memory Evaluation

Seokwon Jung, Alexander Rubinstein, Arnas Uselis +2

LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. While prior benchmarks evaluate on…

cs.LG2023

Trustworthy Machine Learning

Bálint Mucsányi, Michael Kirchhof, Elisa Nguyen +2

As machine learning technology gets applied to actual products and solutions, new challenges have emerged. Models unexpectedly fail to generalize to small changes in the distributi…

cs.LG2025

Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles

Luca Scimeca, Alexander Rubinstein, Damien Teney +2

Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to a phenomenon known as shortcut learning, where a model relies on erroneous…

cs.AI2026

MASEval: Extending Multi-Agent Evaluation from Models to Systems

Cornelius Emde, Alexander Rubinstein, Anmol Goel +4

The rapid adoption of LLM-based agentic systems has produced a rich ecosystem of frameworks (smolagents, LangGraph, AutoGen, CAMEL, LlamaIndex, i.a.). Yet existing benchmarks are m…

cs.LG2024

Do Deep Neural Network Solutions Form a Star Domain?

Ankit Sonthalia, Alexander Rubinstein, Ehsan Abbasnejad +1

It has recently been conjectured that neural network solution sets reachable via stochastic gradient descent (SGD) are convex, considering permutation invariances (Entezari et al.,…

cs.CV2025

Are We Done with Object-Centric Learning?

Alexander Rubinstein, Ameya Prabhu, Matthias Bethge +1

Object-centric learning (OCL) seeks to learn representations that only encode an object, isolated from other objects or background cues in a scene. This approach underpins various…

cs.CV2018

Robust positioning of drones for land use monitoring in strong terrain relief using vision-based navigation

Oleg Kupervasser, Vitalii Sarychev, Alexander Rubinstein +1

For land use monitoring, the main problems are robust positioning in urban canyons and strong terrain reliefs with the use of GPS system only. Indeed, satellite signal reflection a…