2 citations · 2 across the 9 of their papers we have counts for
10 papers
TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal Rate
Erica Zhang, Fangzhao Zhang, Aneesh Pappu +5
Negotiation is a central mechanism of economic exchange, shaping markets, procurement, labor agreements, and resource allocation. It is also a canonical testbed for agentic languag…
Optimizer-Induced Mode Connectivity: From AdamW to Muon
Fangzhao Zhang, Sungyoon Kim, Erica Zhang +2
Mode connectivity has been widely studied, yet the role of the optimizer remains underexplored. We revisit it through optimizer-induced implicit regularization, asking how connecti…
Learning When to Trust LLM Priors: A Validated Framework for Semantic Prior Integration
Erica Zhang, Naomi Sagan, Danny Tse +3
Large language models (LLMs) encode rich semantic knowledge that can be useful for supervised learning, but their outputs are unreliable as statistical priors: they may be noisy, m…
AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?
Ori Press, Brandon Amos, Haoyu Zhao +21
Despite progress in language model (LM) capabilities, evaluations have thus far focused on models' performance on tasks that humans have previously solved, including in programming…
Solving Large Multicommodity Network Flow Problems on GPUs
Fangzhao Zhang, Stephen Boyd
We consider the all-pairs multicommodity network flow problem on a network with capacitated edges. The usual treatment keeps track of a separate flow for each source-destination pa…
Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing
Elad Romanov, Fangzhao Zhang, Mert Pilanci
Motivated by recent advances in serverless cloud computing, in particular the "function as a service" (FaaS) model, we consider the problem of minimizing a convex function in a mas…
Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes
Erica Zhang, Fangzhao Zhang, Mert Pilanci
Active learning methods aim to improve sample complexity in machine learning. In this work, we investigate an active learning scheme via a novel gradient-free cutting-plane trainin…
Spectral Adapter: Fine-Tuning in Spectral Space
Fangzhao Zhang, Mert Pilanci
Recent developments in Parameter-Efficient Fine-Tuning (PEFT) methods for pretrained deep neural networks have captured widespread interest. In this work, we study the enhancement…
Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models
Fangzhao Zhang, Mert Pilanci
Low-Rank Adaptation (LoRA) emerges as a popular parameter-efficient fine-tuning (PEFT) method, which proposes to freeze pretrained model weights and update an additive low-rank tra…
Analyzing Neural Network-Based Generative Diffusion Models through Convex Optimization
Fangzhao Zhang, Mert Pilanci
Diffusion models are gaining widespread use in cutting-edge image, video, and audio generation. Score-based diffusion models stand out among these methods, necessitating the estima…