2 papers
cs.CV2026
LTX-2: Efficient Joint Audio-Visual Foundation Model
Yoav HaCohen, Benny Brazowski, Nisan Chiprut +26
Recent text-to-video diffusion models can generate compelling video sequences, yet they remain silent -- missing the semantic, emotional, and atmospheric cues that audio provides.…
cs.CV2025
RewardSDS: Aligning Score Distillation via Reward-Weighted Sampling
Itay Chachy, Guy Yariv, Sagie Benaim
Score Distillation Sampling (SDS) has emerged as an effective technique for leveraging 2D diffusion priors for tasks such as text-to-3D generation. While powerful, SDS struggles wi…