Stephen Z. Lu

Hi! My name is Stephen (pronounced STEH-fən) and I am a Ph.D. student in computer science at UC Berkeley supervised by Prof. Yun S. Song. I completed my undergraduate studies at McGill University in my hometown of Montreal, Canada 🇨🇦.

My research focuses on machine learning approaches for protein sequence and structure. I am broadly interested in developing deep probabilistic models of protein evolution and dynamics. Recently, my work has centered on learning representations of antibody selection during affinity maturation [1], and building generative models for protein conformation sampling [2], [3].

Previously, I dabbled in small molecule generative models [4], [5] and agentic benchmarking for autonomous scientific discovery [6].

In my free time, I love playing pickup basketball, composing some funky songs on the piano, discovering new hiking trails, and spending time with my family and friends.

Feel free to reach out at stephen.lu@berkeley.edu if you’d like to chat about research or meet for coffee in the Bay Area!

selected publications

2026

Conditionally Site-Independent Neural Evolution of Antibody Sequences

ICML, 2026 · * equal contribution

Stephen Zhewen Lu^*, Aakarsh Vermani^*, Kohei Sanno, and 4 more authors

We introduce CoSiNE, a neural CTMC model of antibody affinity maturation that provably approximates the sequential point mutation process while disentangling selection from somatic hypermutation to enable inference-time affinity optimization.

Paper

Common deep learning approaches for antibody engineering focus on modeling the marginal distribution of sequences. By treating sequences as independent samples, however, these methods overlook affinity maturation as a rich and largely untapped source of information about the evolutionary process by which antibodies explore the underlying fitness landscape. In contrast, classical phylogenetic models explicitly represent evolutionary dynamics but lack the expressivity to capture complex epistatic interactions. We bridge this gap with CoSiNE, a continuous-time Markov chain parameterized by a deep neural network. Mathematically, we prove that CoSiNE provides a first-order approximation to the intractable sequential point mutation process, capturing epistatic effects with an error bound that is quadratic in branch length. Empirically, CoSiNE outperforms stateof-the-art language models in zero-shot variant effect prediction by explicitly disentangling selection from context-dependent somatic hypermutation. Finally, we introduce Guided Gillespie, a classifier-guided sampling scheme that steers CoSiNE at inference time, enabling efficient optimization of antibody binding affinity toward specific antigens.

2025

Aligning Protein Conformation Ensemble Generation with Physical Feedback

ICML, 2025

Jiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu, and 4 more authors

We introduce Energy-based Alignment (EBA), calibrating protein conformation generative models with molecular energy feedback to thermodynamically weight conformational states at state-of-the-art accuracy on MD ensemble benchmarks.

Paper

Protein dynamics play a crucial role in protein biological functions and properties, and their traditional study typically relies on time-consuming molecular dynamics (MD) simulations conducted in silico. Recent advances in generative modeling, particularly denoising diffusion models, have enabled efficient accurate protein structure prediction and conformation sampling by learning distributions over crystallographic structures. However, effectively integrating physical supervision into these data-driven approaches remains challenging, as standard energy-based objectives often lead to intractable optimization. In this paper, we introduce Energy-based Alignment (EBA), a method that aligns generative models with feedback from physical models, efficiently calibrating them to appropriately balance conformational states based on their energy differences. Experimental results on the MD ensemble benchmark demonstrate that EBA achieves state-of-the-art performance in generating high-quality protein ensembles. By improving the physical plausibility of generated structures, our approach enhances model predictions and holds promise for applications in structural biology and drug discovery.
Structure Language Models for Protein Conformation Generation

ICLR, 2025

Jiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu, and 4 more authors

We introduce Structure Language Modeling (SLM), encoding protein structures as discrete tokens for autoregressive conformation generation that achieves a 20–100× speedup over diffusion-based methods while covering diverse ensemble modes.

Paper

Proteins adopt multiple structural conformations to perform their diverse biological functions, and understanding these conformations is crucial for advancing drug discovery. Traditional physics-based simulation methods often struggle with sampling equilibrium conformations and are computationally expensive. Recently, deep generative models have shown promise in generating protein conformations as a more efficient alternative. However, these methods predominantly rely on the diffusion process within a 3D geometric space, which typically centers around the vicinity of metastable states and is often inefficient in terms of runtime. In this paper, we introduce Structure Language Modeling (SLM) as a novel framework for efficient protein conformation generation. Specifically, the protein structures are first encoded into a compact latent space using a discrete variational auto-encoder, followed by conditional language modeling that effectively captures sequence-specific conformation distributions. This enables a more efficient and interpretable exploration of diverse ensemble modes compared to existing methods. Based on this general framework, we instantiate SLM with various popular LM architectures as well as proposing the ESMDiff, a novel BERT-like structure language model fine-tuned from ESM3 with masked diffusion. We verify our approach in various scenarios, including the equilibrium dynamics of BPTI, conformational change pairs, and intrinsically disordered proteins. SLM provides a highly efficient solution, offering a 20-100x speedup than existing methods in generating diverse conformations, shedding light on promising avenues for future research.