Search papers, labs, and topics across Lattice.
University of Maryland, College Park
3
2
5
46
Achieving up to 6脳 greater sample efficiency in diffusion RLHF by strategically reweighting timesteps and reusing informative trajectories could revolutionize how we align generative models with human preferences.
TeCoNeRV achieves state-of-the-art video compression with INRs, finally making hypernetwork-based approaches practical for high-resolution videos (up to 1080p) by slashing memory overhead and bitrate.
Stable Diffusion can serve as a surprisingly effective, instruction-aware visual encoder for MLLMs, outperforming CLIP on tasks requiring spatial and compositional reasoning.
