Showing papers from NVIDIA Research Show all papers
Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Grounded-Exo2Ego couples geometric anchoring with semantic grounding and camera relocalization to robustly generate egocentric video from exocentric inputs, outperforming prior methods on EgoExo4D.
Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
RePlaid, a continuous diffusion language model aligned with modern discrete architectures, achieves scaling laws rivaling discrete diffusion and sets a continuous diffusion perplexity record of 22.1 on OpenWebText.
Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
DiLaDiff proposes a latent-augmented masked diffusion language model with consistency distillation that improves quality and accelerates inference by generating continuous latents in negligible time.
Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
World from Motion generates dynamic 3D Gaussian reconstructions from monocular video via generative video modeling to fix artifacts and fill missing regions, achieving state-of-the-art 4D reconstruction.
Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Spatio-Temporal Attention Chains accelerate training-free 4D mesh generation 13x to 9 seconds via latent temporal correspondences, improving quality, scaling to longer videos, and enabling tracking and camera estimation.
Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 11 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.