DiHAL uses geometry proxies to pick where to replace the lower layers of a pretrained transformer with a diffusion bridge for hidden-state reconstruction, improving over token-level diffusion baselines on 8B models.
Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A recurrent-depth architecture enables language models to improve reasoning performance by iterating computation in latent space, achieving gains equivalent to much larger models on benchmarks.
Coupling Models enable single-step discrete sequence generation via learned couplings to Gaussian latents and outperform prior one-step baselines on text perplexity, biological FBD, and image FID metrics.
citing papers explorer
-
Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement
DiHAL uses geometry proxies to pick where to replace the lower layers of a pretrained transformer with a diffusion bridge for hidden-state reconstruction, improving over token-level diffusion baselines on 8B models.
-
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
A recurrent-depth architecture enables language models to improve reasoning performance by iterating computation in latent space, achieving gains equivalent to much larger models on benchmarks.
-
Coupling Models for One-Step Discrete Generation
Coupling Models enable single-step discrete sequence generation via learned couplings to Gaussian latents and outperform prior one-step baselines on text perplexity, biological FBD, and image FID metrics.