Daniela Rus

MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents

ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment

Learning to Dissipate Energy in Oscillatory State-Space Models

High Performance Differentially Private Fine-Tuning using Dataset Distillation

The Curious Case of In-Training Compression of State Space Models

Neural Low-Discrepancy Sequences

Provably Sample-Efficient Active Preference Data Collection

DataS3: Dataset Subset Selection for Specialization

Quantifying Memory Use in Reinforcement Learning with Temporal Range

Oscillatory State-Space Models

Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples

ReasonIR: Training Retrievers for Reasoning Tasks

SafeDiffuser: Safe Planning with Diffusion Probabilistic Models

The Quest for Universal Master Key Filters in DS-CNNs

ABNet: Adaptive explicit-Barrier Net for Safe and Scalable Robot Learning

Data Value Estimation on Private Gradients

ReGen: Generative Robot Simulation via Inverse Design

Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models

Flex: End-to-End Text-Instructed Visual Navigation with Foundation Models

ABNet: Attention BarrierNet for Safe and Scalable Robot Learning