Search papers, labs, and topics across Lattice.
7
3
13
15
Switching between autoregressive and diffusion modes allows Nemotron-Labs-Diffusion to achieve unprecedented throughput and efficiency in language modeling.
Diffusion-Proof not only surpasses AR LLMs in theorem proving but also solves challenging problems that state-of-the-art models fail to address.
ZPPO reveals that embedding teacher responses in prompts rather than gradients can dramatically boost the performance of small student models on challenging tasks.
Success in long-horizon tasks hinges more on an agent's iterative persistence than on the quality of its initial solution.
A simple resampling strategy closes the "Thinking-Acting Gap" in agentic VLMs, enabling smaller models to outperform larger ones on multimodal reasoning tasks.
Training multi-turn LLM agents just got easier: ProRL Agent offers a scalable, API-driven rollout service that streamlines RL training across diverse tasks.
By strategically warming up residual connections layer-by-layer, ProRes unlocks faster and more stable pretraining for language models.
