Ex-Omni: New Model Enables 3D Facial Animation Generation for Omni-modal Language Models
Researchers have introduced Ex-Omni, an open-source model that enables omni-modal large language models to simultaneously produce speech and 3D facial animation. The work addresses a core technical challenge: bridging the gap between the discrete, semantic reasoning of language models and the dense, continuous temporal dynamics needed for realistic facial motion. The system could advance more natural human-computer interaction by giving AI-generated voices a synchronized, expressive 3D face.
Ex-Omni, short for Expressive Omni, is a new open-source framework that extends omni-modal large language models (OLLMs) — systems designed to handle multiple input and output modalities — to natively generate 3D facial animation in tandem with speech. The central technical obstacle the authors address is the mismatch between how language models process information discretely and semantically versus the high-frequency, continuous temporal signals required for believable facial motion. To bridge this gap, Ex-Omni introduces a blendshape-aware speech unit generator and a blendshape decoder, where intermediate speech units serve as a temporal scaffold and hidden speech representations carry facial cues. A novel token-as-query gated fusion (TQGF) mechanism is also proposed to allow controlled injection of semantic information into the animation pipeline. The team additionally releases InstructS2SF-1200K, a large-scale dataset of 1.2 million samples used for pre-training the system. Experimental results indicate that Ex-Omni achieves better audio-visual synchronization and lower face-generation latency compared to cascaded pipeline approaches, while preserving competitive speech understanding and generation performance. The work was submitted to arXiv in February 2026 and updated in June 2026, and has not yet undergone formal peer review.
What's missing
As a preprint, this work has not been peer-reviewed, so independent validation of the reported benchmarks is lacking.
What different sources said
- arXiv cs.AICenter
Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.