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 ...

A Blog post by NVIDIA on Hugging Face ...

MemT-1.0: Towards Memory-Native Evolution ...

Reinforcement learning improves reasoning accuracy without requiring a specific wait marker, which originates from training ...

Quant-Arena benchmarks end-to-end quantitative research by evaluating whether language models can build trading strategies on ...

FrontierCS 2 evaluates LLM agents on open-ended computer science R&D tasks using hidden evaluation suites and reveals that ...

Matrix-Game 4.0 separates game logic from visual synthesis via an executable engine and autoregressive video renderer, ...

A general vision-language model can serve as a multimodal reranker via single-pass choice questions, matching or exceeding ...

SolarRenderer turns any engine's untextured structure pass into a finished, styled video, guided by a reference first frame.

MMEnterprise-Bench evaluates this challenge with 1,613 questions across 30 simulated collaboration projects, grounded in ...

MIST separates scene setup from change execution to isolate memory failures in video world models, and M3-Agent improves ...