Talks

Invited talks and seminars at ENCODE Lab

Upcoming Talks

No upcoming talks scheduled. Stay tuned!


Past Talks

Disheng Liu

Spatial Intelligence in Vision-Language Models: What It Is, What Works, and What's Next

Disheng Liu, Ph.D. Candidate

Case Western Reserve University

December 30, 2025, 11:00-12:00

Tencent Meeting 682-127-813

Host: Huan Wang

Vision-Language Models (VLMs) have achieved remarkable success but exhibit a fundamental deficiency in spatial intelligence, a critical capability for progress in embodied AI, autonomous driving, and spatially coherent generation. This talk provides a systematic review that spans the foundations of spatial intelligence in VLMs, root causes of spatial limitations, enhancement methodologies, evaluation protocols, and real-world applications.

Yi Ma

Pursuing the Nature of Intelligence

Yi Ma, Chair Professor

School of CDS, Hong Kong University & EECS Department, UC Berkeley

October 14, 2025, 15:30-17:00

E10-201, Yungu Campus

Host: Huan Wang, Yandong Wen

In this talk, we will try to clarify different levels and mechanisms of intelligence from historical, scientific, mathematical, and computational perspective. From the evolution of intelligence in nature, from phylogenetic, to ontogenetic, societal, and to scientific intelligence, we will try to shed light on how to understand the true nature of the seemingly dramatic advancements in the technologies of machine intelligence in the past decade. We achieve this goal by developing a principled mathematical framework to explain deductively the practices of deep learning from the first principle of pursuing low-dimensional distributions.

Yiyi Liao

3D Generative Models through the Lens of Coordinate Systems

Yiyi Liao, Assistant Professor

Zhejiang University

September 4, 2025, 16:00-17:00

Room E10-215, 2F, Yungu Campus

Host: Huan Wang

3D content offers advantages such as real-time interactivity and plays an important role in AR/VR applications, where both generation and compression are critical for practical use. This talk explores 3D content generation from the perspective of coordinate systems, highlighting the distinctions and applications of absolute, observer, and intrinsic coordinates. We present object generation methods developed in the intrinsic coordinate system and scene generation approaches formulated in the observer coordinate system, providing a structured view of how coordinate choices shape 3D generative modeling.