47 citations · 78 across the 19 of their papers we have counts for
21 papers
Memorilla: Latent Semantic Memory for LLMs
Adibvafa Fallahpour, Parsa Idehpour, Vignesh Kothapalli +4
Memory enables large language models (LLMs) to use information beyond their parameters, such as past user conversations, long documents, or an agent's earlier actions. For a frozen…
Anchored Self-Play for Code Repair
Caroline Choi, Zeyneb Kaya, Shirley Wu +3
Code repair is an important capability for language models (LMs): given a buggy program and unit tests, an LM must produce a fixed program that passes the tests. Because code repai…
SWE-Together: Evaluating Coding Agents in Interactive User Sessions
Yifan Wu, Zhuokai Zhao, Songlin Li +8
Most coding-agent benchmarks are static: an agent receives a complete task description up front and is judged only by its final code. Real coding assistance is interactive, with us…
Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap
Tianlang Chen, Shirley Wu, Jure Leskovec
Large Language Model (LLM) interactions are typically underspecified, with users clarifying all necessary details across multiple conversational turns. Yet recent work shows that L…
Reflections and New Directions for Human-Centered Large Language Models
Caleb Ziems, Dora Zhao, Rose E. Wang +55
Large Language Models (LLMs) are increasingly shaping the private and professional lives of users, with numerous applications in business, education, finance, healthcare, law, and…
Poly-EPO: Training Exploratory Reasoning Models
Ifdita Hasan Orney, Jubayer Ibn Hamid, Shreya S Ramanujam +5
Exploration is a cornerstone of learning from experience: it enables agents to find solutions to complex problems, generalize to novel ones, and scale performance with test-time co…
SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving Scenarios
Tian Gao, Celine Tan, Catherine Glossop +8
A fundamental challenge in autonomous driving is the integration of high-level, semantic reasoning for long-tail events with low-level, reactive control for robust driving. While l…
HumanLM: Simulating Users with State Alignment Beats Response Imitation
Shirley Wu, Evelyn Choi, Arpandeep Khatua +7
Large Language Models (LLMs) are increasingly used to simulate how specific users respond to a given context, enabling more user-centric applications that rely on user feedback. Ho…
PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning
Wanjia Zhao, Qinwei Ma, Jingzhe Shi +7
Benchmarks for competition-style reasoning have advanced evaluation in mathematics and programming, yet physics remains comparatively explored. Most existing physics benchmarks eva…
Finance Agent Benchmark: Benchmarking LLMs on Real-world Financial Research Tasks
Antoine Bigeard, Langston Nashold, Rayan Krishnan +1
Artificial Intelligence (AI) technology has emerged as a transformative force in financial analysis and the finance industry, though significant questions remain about the full cap…
Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards
Shirley Wu, Parth Sarthi, Shiyu Zhao +10
Compound AI systems integrating multiple components, such as Large Language Models, specialized tools, and traditional machine learning models, are increasingly deployed to solve c…
SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
Wanjia Zhao, Mert Yuksekgonul, Shirley Wu +1
Multi-agent AI systems powered by large language models (LLMs) are increasingly applied to solve complex tasks. However, these systems often rely on fragile, manually designed prom…
CollabLLM: From Passive Responders to Active Collaborators
Shirley Wu, Michel Galley, Baolin Peng +7
Large Language Models are typically trained with next-turn rewards, limiting their ability to optimize for long-term interaction. As a result, they often respond passively to ambig…
AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning
Shirley Wu, Shiyu Zhao, Qian Huang +7
Large language model (LLM) agents have demonstrated impressive capabilities in utilizing external tools and knowledge to boost accuracy and reduce hallucinations. However, developi…
STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
Shirley Wu, Shiyu Zhao, Michihiro Yasunaga +7
Answering real-world complex queries, such as complex product search, often requires accurate retrieval from semi-structured knowledge bases that involve blend of unstructured (e.g…
GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts
Shirley Wu, Kaidi Cao, Bruno Ribeiro +2
Graph data are inherently complex and heterogeneous, leading to a high natural diversity of distributional shifts. However, it remains unclear how to build machine learning archite…
Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges
Chenhang Cui, Yiyang Zhou, Xinyu Yang +4
While GPT-4V(ision) impressively models both visual and textual information simultaneously, it's hallucination behavior has not been systematically assessed. To bridge this gap, we…
Communication-Free Distributed GNN Training with Vertex Cut
Kaidi Cao, Rui Deng, Shirley Wu +3
Training Graph Neural Networks (GNNs) on real-world graphs consisting of billions of nodes and edges is quite challenging, primarily due to the substantial memory needed to store t…
Med-Flamingo: a Multimodal Medical Few-shot Learner
Michael Moor, Qian Huang, Shirley Wu +6
Medicine, by its nature, is a multifaceted domain that requires the synthesis of information across various modalities. Medical generative vision-language models (VLMs) make a firs…
Discover and Cure: Concept-aware Mitigation of Spurious Correlation
Shirley Wu, Mert Yuksekgonul, Linjun Zhang +1
Deep neural networks often rely on spurious correlations to make predictions, which hinders generalization beyond training environments. For instance, models that associate cats wi…
Efficient Automatic Machine Learning via Design Graphs
Shirley Wu, Jiaxuan You, Jure Leskovec +1
Despite the success of automated machine learning (AutoML), which aims to find the best design, including the architecture of deep networks and hyper-parameters, conventional AutoM…