Pith. sign in

REVIEW 8 cited by

Self-conditioned Embedding Diffusion for Text Generation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2211.04236 v1 pith:3AVYUXBB submitted 2022-11-08 cs.CL cs.LG

classification cs.CLcs.LG
keywords diffusionmodelstextcontinuousgenerationlanguageautoregressiveembedding
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can simply project tokens in a continuous space of embeddings, as is standard in language modeling. We propose Self-conditioned Embedding Diffusion, a continuous diffusion mechanism that operates on token embeddings and allows to learn flexible and scalable diffusion models for both conditional and unconditional text generation. Through qualitative and quantitative evaluation, we show that our text diffusion models generate samples comparable with those produced by standard autoregressive language models - while being in theory more efficient on accelerator hardware at inference time. Our work paves the way for scaling up diffusion models for text, similarly to autoregressive models, and for improving performance with recent refinements to continuous diffusion.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics

    cs.CL 2026-06 conditional novelty 7.0 of 10

    Zero-parameter naive samplers achieve state-of-the-art generative perplexity while producing incoherent text, proving the metric is unsound; distributional divergences like MAUVE and energy distance correctly rank the...

  2. Subliminal Clocks: Latent Time Modelling in Diffusion Language Models

    cs.AI 2026-07 unverdicted novelty 6.0 of 10

    DLMs encode a decodable latent timestep signal in residual activations that can be steered to predictably change model confidence and entropy.

  3. CANDI: Hybrid Discrete-Continuous Diffusion Models

    cs.LG 2025-10 conditional novelty 6.0 of 10

    CANDI combines masked and Gaussian corruption in one noising process, letting discrete diffusion models use continuous gradients for joint updates and guidance.

  4. Do LLM Modules Generalize? A Study on Motion Generation for Autonomous Driving

    cs.AI 2025-09 conditional novelty 6.0 of 10

    On Waymo Sim Agents, LLM-style tokenization, positional embeddings, pretraining, RL post-training, and test-time search can be adapted to improve motion generation, but not all transfer without domain-specific changes.

  5. DiffusionGemma Technical Report

    cs.CL 2026-07 conditional novelty 5.0 of 10

    DiffusionGemma turns a 25B-parameter open-weight autoregressive MoE into a discrete diffusion model that produces ~20 tokens per forward pass and ~1,500 tokens/sec on one H100, establishing a speed-quality tradeoff po...

  6. DLM-One: Diffusion Language Models for One-Step Sequence Generation

    cs.CL 2025-05 conditional novelty 5.0 of 10

    DLM-One distills a continuous diffusion language model into a one-step student, achieving roughly 500x inference speedup while staying within a few percent of the teacher on BLEU, ROUGE, and BERTScore, with substantia...

  7. The Philosophy and Physics of Duality

    physics.hist-ph 2025-08 unverdicted novelty 4.0 of 10

    A philosophical monograph that surveys dualities across physics and proposes a 'geometric view of theories' for theoretical equivalence, realism, and explanation.

  8. A Survey on Diffusion Language Models

    cs.CL 2025-08 unverdicted novelty 3.0 of 10

    A comprehensive survey of diffusion language models covering taxonomy, training and inference techniques, and comparisons with autoregressive models.

Pith tools