← Search

Tianxiao Li

7 accepted papers

2026

M3DLayout: A Multi-Source Dataset of 3D Indoor Layouts and Structured Descriptions for 3D Generation

CVPR 2026

In text-driven 3D scene generation, object layout serves as a crucial intermediate representation that bridges high-level language instructions with detailed geometric output. It not only provides a structural blueprint for ensuring physical plausibility but also supports semantic controllability an

Cited by 0SourceScholar
2026

Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection

CVPR 2026

Multimodal Deepfakes proliferating on social media threaten authenticity, information integrity, and digital forensics. Existing benchmarks are constrained by their single-modality scope, simplified manipulations, or unrealistic distributions, which limit their ability to assess real-world robustnes

Cited by 0SourceScholar
2026

WildCap: Facial Albedo Capture in the Wild via Hybrid Inverse Rendering

CVPR 2026

Existing methods achieve high-quality facial albedo capture under controllable lighting, which increases capture cost and limits usability. We propose WildCap, a novel method for high-quality facial albedo capture from a smartphone video recorded in the wild. To disentangle high-quality albedo from

Cited by 0SourcecodeScholar
2025

Learning Disentangled Equivariant Representation for Explicitly Controllable 3D Molecule Generation

AAAI 2025technical

We consider the conditional generation of 3D drug-like molecules with explicit control over molecular properties such as drug-like properties (e.g., Quantitative Estimate of Druglikeness or Synthetic Accessibility score) and effectively binding to specific protein sites. To tackle this problem, we…

Cited by 0SourcePDFScholar
2025

PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design

ICML 2025poster

Designing protein-binding proteins with high affinity is critical in biomedical research and biotechnology. Despite recent advancements targeting specific proteins, the ability to create high-affinity binders for arbitrary protein targets on demand, without extensive rounds of wet-lab testing, remai…

Cited by 0SourcePDFScholar
2023

Disentangled Wasserstein Autoencoder for T-Cell Receptor Engineering

NeurIPS 2023poster

In protein biophysics, the separation between the functionally important residues (forming the active site or binding surface) and those that create the overall structure (the fold) is a well-established and fundamental concept. Identifying and modifying those functional sites is critical for protei…

Cited by 5SourcePDFScholar
2021

Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders

ACL 2021short

Learning prerequisite chains is an important task for one to pick up knowledge efficiently in both known and unknown domains. For example, one may be an expert in the natural language processing (NLP) domain, but want to determine the best order in which to learn new concepts in an unfamiliar Comput…

Cited by 18SourcePDFScholar