Diyi Yang
- Papers
- 42
Cite
Notes
Only stored in your browser.
Authored papers
42Towards Execution-Grounded Automated AI Research
arXiv 2026
CooperBench: Why Coding Agents Cannot be Your Teammates Yet
arXiv 2026
SWE-smith: Scaling Data for Software Engineering Agents
arXiv 2025
SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs
arXiv 2025
Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors
arXiv 2025
AutoLibra: Agent Metric Induction from Open-Ended Feedback
arXiv 2025
The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas
arXiv 2025
ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?
arXiv 2025
GEM: A Gym for Agentic LLMs
arXiv 2025
Real-Time Reasoning Agents in Evolving Environments
arXiv 2025
OpenCUA: Open Foundations for Computer-Use Agents
arXiv 2025
EgoNormia: Benchmarking Physical Social Norm Understanding
arXiv 2025
PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
arXiv 2024
Are Large Language Models Consistent over Value-laden Questions?
arXiv 2024
Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering
arXiv 2024
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
arXiv 2024
Aligning Language Models with Demonstrated Feedback
arXiv 2024
Attacking Vision-Language Computer Agents via Pop-ups
arXiv 2024
Towards Bidirectional Human-AI Alignment: A Systematic Review for Clarifications, Framework, and Future Directions
arXiv 2024
Unintended Impacts of LLM Alignment on Global Representation
arXiv 2024
Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors
arXiv 2024
A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration
arXiv 2023
Training Socially Aligned Language Models on Simulated Social Interactions
arXiv 2023
LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding
arXiv 2023
Task-Agnostic Low-Rank Adapters for Unseen English Dialects
arXiv 2023
TADA: Task-Agnostic Dialect Adapters for English
arXiv 2023
A Cheaper and Better Diffusion Language Model with Soft-Masked Noise
arXiv 2023
NormBank: A Knowledge Bank of Situational Social Norms
arXiv 2023
Can Large Language Models Transform Computational Social Science?
arXiv 2023
CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation
arXiv 2023
DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules
arXiv 2023
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TMLR
Inducing Positive Perspectives with Text Reframing
ACL 2022 5
Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension
arXiv 2022
On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning
arXiv 2022
TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding
NAACL 2022 7
VALUE: Understanding Dialect Disparity in NLU
ACL 2022 5
DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue
arXiv 2022
A Search Engine for Discovery of Scientific Challenges and Directions
NeurIPS Workshop AI4Scien 2021 12
Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering
Findings (ACL) 2021 8
Evaluating Graph Vulnerability and Robustness using TIGER
arXiv 2020
Automatically Neutralizing Subjective Bias in Text
arXiv 2019
Affiliations
Frequent co-authors
10from 42 papers