Home Knowledge Base DLM

DLM

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation

arXiv:2606.06712v1 Announce Type: new Abstract: We study the transformation of autoregressive models (ARLMs) into diffusion language models (DLMs). Rather than pretraining from scratch, prior work replaces the causal attention in ARLMs with bidirectional attention and then trains the resulting model using a DLM objective. However, these approaches incur two distribution shifts.

arXiv CS 2d ago

Diffusion Language Model Parallel Decoding via Product-of-Experts Bridge

arXiv:2606.08048v1 Announce Type: new Abstract: Diffusion language models (DLMs) offer substantial speed advantages through parallel decoding, but the lack of token dependencies limits generation quality compared to autoregressive (AR) models. Recent progress attempts to bridge the gap via importance sampling, with DLM being the proposal and AR being the target. However, due to the huge gap between their distributions, the sampling requires a large number of particles and is thus expensive...

arXiv CS 1d ago

A Survey on Diffusion Language Models

arXiv:2508.10875v3 Announce Type: replace Abstract: Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through an iterative denoising process, DLMs possess inherent advantages in reducing inference latency and capturing bidirectional context, thereby enabling fine-grained control over the generation process. While achieving a several-fold speed-up, recent advancements...

arXiv CS 5d ago

A first-in-class pulsatile FXR agonist for bile-acid-related liver diseases

Abstract Nuclear receptors are central regulators of metabolism1, yet therapeutic strategies that enforce continuous receptor activation frequently lead to reduced efficacy and unacceptable toxicity. Here we report a first-principles drug design strategy that aligns pharmacokinetics with physiological signalling cycles. We developed linafexor, a potent non-bile-acid agonist of the farnesoid X receptor (FXR)2; it is engineered for rapid systemic clearance, which enables pulsatile receptor...

Nature 18h ago

TimpaTeks: Automatic In-place Text Sequence Modification via Diffusion Language Model Steering

arXiv:2606.08408v1 Announce Type: new Abstract: We extend activation steering to diffusion language models (DLMs) and study a novel problem that arose due to the inference mechanism of DLMs: Modifying a text in-place to manifest a different concept. We propose TimpaTeks, an automatic in-place text modification mechanism using DLMs. Experiments on IMDB movie reviews (sentiment) and a synthetic Cats and Dogs Dataset (arbitrary, more unconventional concept steering) show that TimpaTeks provides...

arXiv CS 1d ago

Reinforcement Learning from Denoising Feedback

arXiv:2605.25638v2 Announce Type: replace Abstract: Policy loss estimation remains a fundamental and long-standing challenge in reinforcement learning (RL) for diffusion language models (DLMs). We introduce Reinforcement Learning from Denoising Feedback (RLDF), a novel training paradigm that leverages feedback obtained from rollout and training processes to facilitate accurate and efficient policy loss estimation. To balance the trade-off between computational efficiency and estimation...

arXiv CS 2d ago

Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsets

arXiv:2606.08497v1 Announce Type: new Abstract: As deep language models (DLMs) are increasingly deployed in high-stakes domains such as healthcare, understanding their decision rationale becomes paramount for ensuring trust, safety, and accountability. However, achieving this vital level of interpretability is particularly challenging when these DLMs operate as black-box systems (e.g., via APIs), where access to internal model states (e.g., parameters, gradients) is restricted. Despite...

arXiv CS 1d ago

AsyncLane: Decoupling Refinement from Advancement in Diffusion Language Model Decoding

arXiv:2606.08411v1 Announce Type: new Abstract: Block-wise semi-autoregressive decoding is the standard inference paradigm for diffusion large language models (DLMs), but it imposes a strict dependency between blocks: the next block cannot begin until the current block is fully decoded or its denoising budget is exhausted. We observe that once a block exposes a reliable delimiter boundary or stable semantic prefix, continuation generation need not wait for every residual token to be...

arXiv CS 1d ago

Learned Relay Representations for Forward-Thinking Discrete Diffusion Models

arXiv:2605.22967v2 Announce Type: replace Abstract: When Masked Diffusion Models (MDMs) generate sequences through iterative refinement, the rich internal computation over masked positions is discarded, forcing every subsequent refinement step to recompute the valuable internal information stored as model representations. To avoid a hard reset between denoising rounds, we propose Learned Relay Representations (Relay), a method that allows MDMs to be forward-thinking when denoising by...

arXiv CS 9d ago

Continuous Language Diffusion as a Decoder-Interface Problem

arXiv:2606.08810v1 Announce Type: new Abstract: Gaussian-corrupted sentence embeddings have no direct linguistic interpretation, yet continuous diffusion language models can generate fluent text from them. We study this puzzle through Embedded Language Flows (ELF) and identify a decoder-basin mechanism: denoising succeeds when trajectories reach regions where the native decoder can read stable tokens. We introduce a diagnostic protocol for denoisability, semantic recoverability, order...

arXiv CS 1d ago