activity
20242026
collaborators

7 papers

cs.CL2026

Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech

Omnilingual SONAR Team, João Maria Janeiro, Pere-Lluís Huguet Cabot +17

Cross-lingual sentence encoders typically cover only a few hundred languages and often trade downstream quality for stronger alignment, limiting their adoption. We introduce OmniSO…

cs.LG2026

Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

Taekyung Ki, Sangwon Jang, Jaehyeong Jo +2

Talking head generation creates lifelike avatars from static portraits for virtual communication and content creation. However, current models do not yet convey the feeling of trul…

cs.CV2026

Self-Refining Video Sampling

Sangwon Jang, Taekyung Ki, Jaehyeong Jo +3

Modern video generators still struggle with complex physical dynamics, often falling short of physical realism. Existing approaches address this using external verifiers or additio…

cs.CV2026

Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models

Sangwon Jang, Taekyung Ki, Jaehyeong Jo +4

Advancements in diffusion models have significantly improved video quality, directing attention to fine-grained controllability. However, many existing methods depend on fine-tunin…

cs.LG2025

Continuous Diffusion Model for Language Modeling

Jaehyeong Jo, Sung Ju Hwang

Diffusion models have emerged as a promising alternative to autoregressive models in modeling discrete categorical data. However, diffusion models that directly work on discrete da…

cs.CV2025

Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models

Sangwon Jang, June Suk Choi, Jaehyeong Jo +2

Text-to-image diffusion models have achieved remarkable success in generating high-quality contents from text prompts. However, their reliance on publicly available data and the gr…