Optimized unmasking policies for masked diffusion language models improve efficiency by using trajectory-contraction targets ...
Factor-Aware Predictive Learning enables video diffusion transformers to leverage multimodal language model representations ...
Reinforcement learning improves reasoning accuracy without requiring a specific wait marker, which originates from training ...
minimax_h3_fl2va_pruned_int4_convrot.safetensors T2V / first-last-frame video 11.3 GB minimax_h3_ref2va_pruned_int4_convrot.safetensors Reference-driven video 11.3 GB ...
A Blog post by NVIDIA on Hugging Face ...
Recent advances in video generation have made synthetic videos increasingly realistic, placing greater demands on reliable AI ...
MemT-1.0: Towards Memory-Native Evolution ...
Quant-Arena benchmarks end-to-end quantitative research by evaluating whether language models can build trading strategies on ...
Describe Anything Model 3B (DAM-3B) takes inputs of user-specified regions in the form of points/boxes/scribbles/masks within images, and generates detailed localized ...
FrontierCS 2 evaluates LLM agents on open-ended computer science R&D tasks using hidden evaluation suites and reveals that ...
Add files using upload-large-folder tool about 1 year ago meta Add files using upload-large-folder tool about 1 year ago videos Add files using upload-large-folder tool about 1 year ago ...
Matrix-Game 4.0 separates game logic from visual synthesis via an executable engine and autoregressive video renderer, ...
Results that may be inaccessible to you are currently showing.
Hide inaccessible results