Alane Suhr
UC Berkeley assistant professor working on grounded language understanding, instruction following, and LLM agents.
- Role
- professor
- Currently at
- University of California, Berkeley
- twitter.com/alsuhr
- GitHub
- github.com/alsuhr-c
- Scholar
- scholar.google.com/citations
- Papers
- 14
Cite
Notes
Only stored in your browser.
Authored papers
14V_1: Unifying Generation and Self-Verification for Parallel Reasoners
arXiv 2026
Learning Adaptive Parallel Reasoning with Language Models
arXiv 2025
TULIP: Towards Unified Language-Image Pretraining
arXiv 2025
AutoPresent: Designing Structured Visuals from Scratch
CVPR 2025 1
Visually Prompted Benchmarks Are Surprisingly Fragile
arXiv 2025
SWE-Gym: An Open Environment for Training Software Engineering Agents and Verifiers
preprint
Autonomous Evaluation and Refinement of Digital Agents
arXiv 2024
Grounding Language in Multi-Perspective Referential Communication
arXiv 2024
Evaluating Model Perception of Color Illusions in Photorealistic Scenes
CVPR 2025 1
Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
arXiv 2023
What's In My Big Data?
arXiv 2023
We're Afraid Language Models Aren't Modeling Ambiguity
arXiv 2023
Continual Learning for Instruction Following from Realtime Feedback
continual-learning-for-instruction-following
A Corpus for Reasoning About Natural Language Grounded in Photographs
a-corpus-for-reasoning-about-natural-language-1
Tool contributions
1Affiliations
Frequent co-authors
10from 14 papers