Elias Stengel-Eskin

8

Papers

45

Total Citations

3

Affiliations

Affiliations

UT AustinJohns Hopkins UniversityUNC Chapel Hill

Papers (8)

CAPTURE: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting

Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models

DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback

LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits

ReGAL: Refactoring Programs to Discover Generalizable Abstractions

MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models

Language-guided Skill Learning with Temporal Variational Inference

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos