arXiv:2606. 06547v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) refine tokens iteratively but commit them irreversibly, leading to a "stability lag" where early decisions remain fragile even after being written.
arXiv:2608.21019v1 Announce Type: cross Abstract: Quantization is widely used to deploy large language models, but its effect on uncertainty behavior, such as confidence, margins, and abstention, is...
arXiv:2602. 15327v2 Announce Type: replace-cross Abstract: Machine learning model performance improvements tend to arise from competition and application.
arXiv:2607. 27386v1 Announce Type: cross Abstract: Diffusion Language Models (DLMs) offer a compelling alternative to autoregressive (AR) generation by enabling bidirectional context and iterative refinement.
arXiv:2606. 27474v1 Announce Type: cross Abstract: How should we evaluate generation systems that combine autoregressive (AR) and diffusion decoding?
arXiv:2606. 16847v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) offer a promising avenue for parallel generation but face a trade-off between decoding speed and quality.
arXiv:2608. 13925v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) accelerate language generation by predicting multiple masks in a single forward pass.
arXiv:2606. 04945v1 Announce Type: new Abstract: Diffusion large language models (DLLMs) have recently emerged as a promising alternative to autoregressive LLMs by generating text through iterative masked denoising with bidirectional context.
arXiv:2608. 01460v1 Announce Type: new Abstract: Conformal prediction (CP) is a distribution-free framework for uncertainty quantification that has recently been adapted to large language models (LLMs), providing prediction sets with finite-sample coverage guarantees under exchangeability.
The paper introduces Dependency-Aware Revocable Decoding (DARD), a training‑free framework for diffusion large language models that separates tokens into masked, candidate, and unmasked states. DARD verifies candidate tokens using a selective context that excludes less reliable tokens and adaptively regulates their influence on subsequent decoding. Experiments on 12 textual and multimodal benchmarks across three open‑source dLLMs show that DARD improves the speed‑quality Pareto frontier, achieving a 2.71× speedup and a 4.35‑point CIDEr gain over Saber on Flickr30K.
arXiv:2606. 11552v1 Announce Type: cross Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference costs due to inherently sequential token generation.
The paper introduces PACE-dLLM, an acceleration method for diffusion language models (dLLMs) that uses the model’s own per‑step confidence to estimate a ‘confidence cliff’ and determine the optimal look‑ahead horizon for block decoding. By fitting this cliff in closed form at each step, PACE-dLLM sets the horizon to its saturation point and applies an independent confidence threshold for token commitment, thereby avoiding the trade‑offs inherent in fixed‑size block decoding. Experiments on reasoning and code benchmarks show that PACE-dLLM achieves the best average accuracy on open‑source dLLM backbones while delivering significant wall‑clock speedups—up to 5.23× on LLaDA and 3.06× on Dream—improving the quality‑throughput Pareto frontier.
arXiv:2609.37887v1 Announce Type: new Abstract: Activation and key-value cache precision change what a quantized language model computes without altering its stored weights. Direct weight-code bounds...