Speaker:

Dr. XU Yuzhi

Ph.D. Candidate, Department of Chemistry, New York University

Title:

Physics-Inspired Modeling for Molecular and Protein Structure: Prediction, Ranking, and Generation

Abstract:
As deep learning is increasingly deployed to molecular and protein systems, it must operate beyond the training distribution and respect the physical laws that govern real-world chemistry, calling for new algorithmic principles that integrate domain knowledge into AI pipelines. In this talk, I will present my research on physics-inspired deep learning methods for predicting, ranking, and generating molecular and protein structures.

This talk will highlight three representative lines of my work. The first work focuses on feature-level integration, where multi-level chemical priors are encoded into an E(3)-equivariant network, EnviroDetaNet, for infrared spectra prediction, yielding substantial gains in data efficiency and out-of-distribution generalization on molecules up to three times larger than those in the training set. The second work discusses how physics-inspired architecture-level design can capture the weak, accumulated interactions that shape protein interfaces, and introduces SAKE-PP, a kinetic graph network inspired by Langevin dynamics. SAKE-PP is an independent ranker that outperforms AlphaFold 3’s ranking score on protein–protein complex selection. The third work introduces inference-level guidance, where ProSteer injects a true atomic force field into diffusion sampling without retraining, enabling physically realistic and condition-dependent generation, such as pH-driven conformational transitions that AlphaFold 3 alone cannot capture. This talk will also discuss future directions in agentic molecular dynamics, closed-loop AI-driven materials discovery, and a broader vision for trustworthy, physics-grounded AI4Science.

Biography:

Yuzhi Xu is a final-year Ph.D. candidate at New York University, supervised by Prof. John Zhang, with a Ted Keusseff Fellowship nomination. He also serves as the AI Project Lead in a biology laboratory at the National University of Singapore and as a member of OpenADMET at Memorial Sloan Kettering Cancer Center. His research focuses on physics-inspired deep learning for molecular and protein modeling, spanning spectra prediction, protein complex ranking, and structure generation. He ranked Top-10 in the 6th CACHE Drug Discovery Challenge, and his AI4Science active-learning U.S. patent was featured by Xinhua News Agency.

Enquiries:

Ms. FUNG Wing Chi Mary (maryfung@cse.cuhk.edu.hk)

Mr. WONG O Bong (obong@cse.cuhk.edu.hk)

** ALL ARE WELCOME **

Speaker: Dr. LAI Yao Postdoctoral Research Associate, University of Cambridge Title: Towards Intelligent Chip Design via AI-Driven Approaches

Speaker: Dr. WAN Zishen
Postdoctoral Fellow, Harvard University

Title:
Architecting Physical Intelligence: Cross-Stack Co-Design from Systems to Silicon

Abstract:
Physical intelligence – where embodied agents perceive, reason, plan, and act in the physical world – is emerging as a new computing frontier spanning robotics, autonomous systems, and spatial AI. However, today’s physical intelligence systems remain constrained by high latency, energy cost, and fragile reliability, due to fundamental mismatch between their compositional nature and existing computing architectures. The core challenge extends beyond algorithms, to how we architect computing systems and silicon that natively support intelligence that reasons and adapts under real-world constraints.
In this talk, I will present a principled cross-stack system-architecture-silicon co-design approach to building the computational foundations for physical intelligence. I will first introduce REASON, a flexible hardware architecture culminating the first programmable SoC tapeout for efficient neuro-symbolic cognition. REASON integrates unified kernel abstractions, flexible dataflows, memory-centric computing, end-to-end compilation flow, and adaptive power management, enabling efficient cognition in silicon. Building on this foundation, I will present ReCA, an integrated hardware architecture that bridges high-level cognition and low-level autonomy under stringent power and latency constraints by leveraging spatial-aware runtimes, memory layout optimizations, and heterogeneous fabrics. Finally, I will highlight our agile SoC design flows that translate evolving physical intelligence workloads into efficient silicon implementations.
By bridging computer architecture, system software, and silicon validation, my research establishes adaptive, accelerator-rich computing substrates for physical intelligence. This work advances a vision in which AI and hardware are co-designed, co-reason, and co-adapt, architecting future computing systems as active enablers of intelligence in the physical world.

Biography:
Zishen Wan is a postdoctoral fellow at Harvard University, working with Prof. Vijay Janapa Reddi. He received his Ph.D. from Georgia Tech, advised by Profs. Arijit Raychowdhury and Tushar Krishna. His research focuses on computer architecture, with an emphasis on cross-stack co-design of systems, architectures, and silicon for physical intelligence. His work appears in venues including ASPLOS, MICRO, HPCA, JSSC, ISSCC, and DAC, and has been recognized with Best Paper Awards at DAC, CAL, and SRC JUMP2.0, First Place Awards in DAC PhD Forum and ACM Student Research Competition, and honorable mention in IEEE Micro Top Picks. He is a recipient of Qualcomm, Baidu, and CRNCH PhD Fellowships, and was named as ML and Systems Rising Star and Cyber-Physical Systems Rising Star. His research has been featured in MIT Technology Review and Fortune, and adopted by industry partners including Intel, IBM, and Google. For more information, please visit https://zishenwan.github.io/.

Enquiries:
Ms. FUNG Wing Chi Mary (maryfung@cse.cuhk.edu.hk)
Mr. WONG O Bong (obong@cse.cuhk.edu.hk)

** ALL ARE WELCOME **

Speaker: Prof. WANG Kangning, Assistant Professor, Computer Science, Rutgers University Title: How to Keep the Majority on Your Side

Speaker: Mr. CEN Ruoxu Ph.D. Candidate, Department of Computer Science, Duke University Title: Fast Algorithms for Network Connectivity and Reliability

Speaker: Prof. GUO Siyao Associate Professor, New York University (NYU) Shanghai Title: When Attackers Prepare: Backdoors, Preprocessing and Time-Space Tradeoffs

Speaker: Dr. HU Qinghao Postdoctoral Associate, Massachusetts Institute of Technology Title: Building Efficient and Scalable Machine Learning Systems

Speaker: Prof. WANG Binghui Assistant Professor, Department of Computer Science, Illinois Institute of Technology, Chicago, USA Co-PI of the Chicago-area Data Science Institute IDEAL IEEE Senior Member Title: Towards Provable Security and Privacy in Trustworthy Machine Learning

Speaker: Dr. MENG Ruijie Research Fellow, National University of Singapore Title: How to Test Reactive Systems?

Speaker: Ms. LIU Yuhan
Ph.D. Candidate, Department of Computer Science
The University of Chicago

Title:
Rethinking AI Systems Through Efficient Model Communication

Abstract:
For decades, AI models interacted with humans directly through human-centric inputs and outputs. Today, they are used much more ubiquitously and often interact through complex software systems, interacting with other models or software rather than directly with humans. This paradigm shift raises a natural question: can models interact with other models and software using model-native languages?
In this talk, I will present my work on facilitating model-native interactions among models and between models and software. To enable more efficient and practical model interactions using model-native states (i.e., KV cache) in LLM systems, my work CacheGen is the first system to share KV cache across different user queries by compressing it into compact bitstreams, and my work DroidSpeak is the first system to share KV cache across different models. My research has made real-world impacts via the open-source project, LMCache, widely used in production by top-tier AI companies. Together, these works make LLM inference 5–10× faster than state-of-the-art inference engines. To enable more accurate model-to-software communication, my work ChameleonAPI encodes software code structure into model-native loss functions, allowing models to be retrained for up to 43% higher application-level accuracy in vision applications.

Biography:
Yuhan Liu is a final-year PhD student at the University of Chicago, co-advised by Junchen Jiang and Shan Lu. Her research interest is in building efficient large-scale system and networking support for ML model inference. Her works appeared in top computer system/networking conferences, such as OSDI, SIGCOMM, NSDI. She received MIT EECS rising star, EuroSys best paper award, and UChicago’s Neubauer PhD fellowship for her research. She also leads two open-source projects that build large-scale KV caching layer for efficient LLM inference, and are used in over 30 companies in production, including Google Cloud, Amazon AWS, NVIDIA, IBM etc.

Enquiries:
Ms. FUNG Wing Chi Mary (maryfung@cse.cuhk.edu.hk)
Mr. WONG O Bong (obong@cse.cuhk.edu.hk)

** ALL ARE WELCOME **

Speaker: Professor YUAN Binhang Assistant Professor, Department of Computer Science and Engineering, The Hong Kong University of Science and Technology (HKUST) Title: Accommodating Comprehensive Foundation Model Services over Heterogeneous Computational Resources

Speaker: Prof. WANG Liwei Assistant Professor, Department of Computer Science and Engineering, The Chinese University of Hong Kong Title:Towards a Generalist Model That Can “See,” “Think,” and “Interact” in the 3D World

Speaker: Professor Wayne LUK Department of Computing, Imperial College London Title: JEDI-linear: Fast and Efficient Graph Neural Networks for Jet Tagging on FPGAs

Speaker: Dr. ZHANG Yuhui
Postdoctoral Scholar, Stanford University

Title:
Principled Multimodal Intelligence for Digital Twins of Science

Abstract:
Scientific discovery is increasingly bottlenecked by human effort and costly physical experiments. I envision a future with a “digital twin of science”, in which AI agents operate in virtual environments to accelerate discovery. In drug discovery, for example, such agents could autonomously retrieve knowledge, analyze data, propose candidate compounds, and validate them through a “virtual cell”.
Realizing this vision requires multimodal intelligence—models that can represent, reason over, and generate information across modalities such as language, vision, and biological data. While recent multimodal foundation models have demonstrated impressive capabilities, we still lack a principled understanding of their behaviour, leading to fundamental failures when they are applied to high-stakes scientific problems. For instance, CLIP exhibits modality gaps that introduce retrieval bias; GPT struggles to identify fine-grained biological features from images, limiting downstream interpretation; and diffusion models fail to generate statistically valid cellular images that reflect experimental variance.
My research advances “AI for science” through a “science of AI” approach: developing principled understanding of how these models work, when and why they fail, and how to improve them. For representation, I analyze the geometric origins of modality gaps and propose theoretically grounded methods to close them. For reasoning, I identify the sources of perceptual bottlenecks in multimodal language models and introduce data-centric solutions to enhance fine-grained interpretation. For generation, I show that standard diffusion models fail to capture data artifacts such as batch effects, and I propose distribution transformation via flow matching to enable faithful scientific simulation.
By bridging theoretical foundations and scientific application, my work paves the way toward digital twins that can fundamentally transform how science is conducted.

Biography:
Yuhui Zhang (https://cs.stanford.edu/~yuhuiz/) is a postdoctoral scholar at Stanford University, advised by Professors Serena Yeung-Levy, Ludwig Schmidt, and Emma Lundberg. He earned his Ph.D. in Computer Science from Stanford University and his B.E. from Tsinghua University. His research advances the foundations of multimodal machine learning to accelerate scientific discovery, with a focus on vision-language models and cell biology. His work has appeared at top-tier AI conferences (e.g., NeurIPS, CVPR, ACL) with multiple oral presentations, as well as in leading biomedical journals such as NEJM AI and npj Digital Medicine. He is a recipient of the Rising Stars in Data Science Award, the CVPR Doctoral Consortium Award, and the NeurIPS Scholar Award.

Enquiries:
Ms. FUNG Wing Chi Mary (maryfung@cse.cuhk.edu.hk)
Mr. WONG O Bong (obong@cse.cuhk.edu.hk)

Speaker: Yurong Chen is currently a postdoc at SIERRA-team, INRIA Paris, working with Michael I. Jordan, and was recently awarded a Marie Skłodowska-Curie Actions (MSCA) Postdoctoral Fellowship to be jointly hosted by Francis Bach and Michael I. Jordan. She earned her PhD in Computer Science at Peking University, where she was advised by Xiaotie Deng. Her research focuses on the intersection of learning, economics, and game theory, especially on how strategic agents exploit information advantage during interactions with learning agents. She is a recipient of the Best Student Paper Award at WINE 2022. Title: How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics

Speaker: Ms. YANG Kunhe
Ph.D. Candidate, Department of Electrical Engineering and Computer Science
University of California, Berkeley

Title:
Designing and Evaluating AI Algorithms in Human-Centered Environments

Abstract:
As AI models are increasingly deployed in real-world settings, they must operate in environments shaped by complex human behaviors, calling for new algorithmic principles for designing AI pipelines that account for human values and incentives. In this talk, I will present my research on the theoretical foundations of designing and evaluating AI algorithms in human-centered strategic environments, leveraging tools from algorithmic economics and learning theory.
I will highlight two representative lines of work. First, I will focus on incentive-aware evaluation, where evaluation metrics themselves become targets of optimization. In the context of sequential probability forecasting, I will present a framework for the truthfulness of calibration measures and introduce algorithmic principles for designing calibration metrics that automatically incentivize truthful reporting. Second, I will discuss how aligning AI with human preferences must account for preference heterogeneity, and introduce a framework called the distortion of AI alignment that characterizes information-theoretic limits of learning from heterogeneous human feedback and motivates robust, game-theoretic approaches to policy optimization. I conclude by discussing future directions and a broader vision for integrating these algorithmic principles into the design of trustworthy, human-centric AI.

Biography:
Kunhe Yang is a fifth-year PhD candidate in Electrical Engineering and Computer Sciences at the University of California, Berkeley, where she is advised by Professor Nika Haghtalab. Her research focuses on the theoretical foundations of AI in human-centered environments by drawing on tools from machine learning theory and algorithmic economics. Her work has been recognized by several awards, including EECS Rising Star, invited speaker at the Cornell Young Researchers workshop, finalist for the Meta Research PhD Fellowship in the Economics and Computation track, and a SIGMETRICS best paper award. Previously, she received her bachelor’s degree from Yao Class at Tsinghua University.

Enquiries:
Ms. FUNG Wing Chi Mary (maryfung@cse.cuhk.edu.hk)
Mr. WONG O Bong (obong@cse.cuhk.edu.hk)

Speaker: Prof. Cesare ALIPPI Professor, Università della Svizzera italiana (Switzerland) Professor, Politecnico di Milano (Italy) Visiting Professor, Guangdong University of Technology (China) Consultant Professor, Northwestern Polytechnic of Xi’An (China) Title: Graph Deep Learning for Irregular Spatiotemporal Data

Speaker: Ms. Barbara Jiabao BENEDIKT PhD in Cryptography and Complexity Theory, Technical University of Darmstadt Title: The Order of Hashing in Fiat-Shamir Schemes

Speaker: Dr. WANG Zhuang Senior Applied Scientist, Amazon Annapurna Labs Title: Scaling LLM Pre-training through Optimizing Data- and Management-Plane Communications

Speaker: Professor ZHANG Hongce Assistant Professor, Microelectronics Thrust, The Hong Kong University of Science and Technology (Guangzhou) Title: AI for Hardware Formal Verification

Speaker: Patrick Groeneveld, Senior Fellow at AMD and adjunct lecturer in Stanford University’s Department of Electrical Engineering, Title: Place, Route, and Evolve: Design Lessons Shared by Silicon and Biology

Speaker: Professor Ansuman BANERJEE Advanced Computing and Microelectronics Unit Indian Statistical Institute, Kolkata Title: Agentic AI and Formal Verification Joining Hands

Speaker: Dr. Yiyu Shi currently a professor in the Department of Computer Science and Engineering at the University of Notre Dame Title: When Small Variations Become Big Failures: Reliability Challenges in Computing-in-Memory Neural Accelerators

Speaker: Dr. ZHANG Xujun Postdoctoral Researcher, Zhejiang University Title: Methodological Study on Machine Learning-Based Molecular Docking

Speaker: Mr. MAO Xinyu, PhD in Theoretical Computer Science, University of Southern California, Title: Black-Box Separation between Multi-Collision Resistance and Collision Resistance

HOW TO PROVE POST-QUANTUM SECURITY FOR SUCCINCT NON-INTERACTIVE REDUCTIONS, ms Zheng yuxi, Phd in computer & comminication sciences epfl, switzerland

multimodal llms as social media analysis engines prof luo jiebo albert arendt hopeman professor of engineering and computer science university of rochester

dr. liu qiang, postdoctoral fellow hexhive, epfl, switzerland (advised by prof. mathias payer), enforcing trust at runtime

Speaker: Professor LI Yu Assistant Professor, Department of Computer Science and Engineering The Chinese University of Hong Kong Title:Go Beyond Building Virtual Cell with Artificial Intelligence

Speaker:Mr. GU Yufeng, Ph.D. candidate (advised by Prof. Reetuparna Das), University of Michigan ; Title:Architecture and System Co-Design for Scalable Large Language Model Inference

Speaker: Professor Alastair DONALDSON, Professor & Director of Research, Department of Computing, Imperial College London, Title: Randomised testing and test case reduction for GPU compilers

Speaker: Dr. CHEN Guangyi, Postdoctoral Research Fellow, Carnegie Mellon University (CMU), Research Scientist, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Title: Causal Representation Learning

Speaker:Dr. CHEN Xiusi; Postdoctoral Research Associate, University of Illinois Urbana-Champaign ; Title: Towards Embodied Reasoning and Alignment of Large Language Models

Speaker: Dr. Johann KNECHTEL, Senior Research Scientist, New York University Abu Dhabi (NYUAD)Title: LLMs for Secure Hardware Design: Opportunities and Challenges

Dr arnaud huaulme research engineer medicis research group of umr 1099 ltsi, inserm research institute and univeristy of rennes (france)
ASSESSMENT OF THE TECHNICAL AND NON-TECHNICAL SKILLS OF THE SURGICAL TEAM

prof. krystel nyangoh timoh professor of gynecology university of rennes and prof. pierre janning INSERM Research Director Medical School, University of Rennes
SURGICAL DATA SCIENCE FOR WOMEN’S HEALTH

dr. qin tao, dr. liu haiguang, dr. yu chao, mr. guan haoxiang
PIONEERING AI FOR SCIENTIFIC DISCOVERY AND SOCIETAL IMPACT – ZHONGGUANCUN INNOVATIONS

Dr Sharib ALI Assistant Professor, School of Computer Science, University of Leeds, United Kingdom
Computer Vision for Endoscopic Image Analysis – From Diagnostics to Intraoperative Applications

Prof. Xu Hong, Department of Computer Science & Engineering, The Chinese University of Hong Kong
Hyper-Scale AI Infrastructure: Efficiency, Reliability, And Beyond

Mr. Alper Çakan PhD in Computer Science, Carnegie Mellon University
Public-Key Quantum Fire and Key-Fire From Classical Oracles

Prof. Fei Yunsi
Professor
Electrical and Computer Engineering Northeastern University
Side-Channel For AI Security: For or Friend