The paper introduces Variance‑Calibrated Modulation (VCM), a training‑free pre‑decoding technique that reshapes language model probability distributions before truncation. VCM uses two dynamic mechanisms: a Contextual Searchlight via PMI to suppress stopwords and highlight context‑relevant tokens, and an Adaptive Self‑Debiasing that applies scale‑invariant penalization based on real‑time logit standard deviation. Experiments on open‑ended generation, factual QA, and mathematical reasoning show that VCM consistently reduces the likelihood trap, improving diversity, coherence, and reasoning accuracy with minimal computational cost.
By Yuanhao Ding, Meimingwei Li, Esteban Garces Arias, Matthias A{\ss}enmacher, Christian Heumann, Chongsheng Zhang
arXiv:2508. 10875v3 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm.
By Tianyi Li, Mingda Chen, Bowei Guo, Zhiqiang Shen
The paper proposes an information-weighted cross‑entropy loss that rescales token contributions using TF‑IDF statistics, thereby emphasizing semantically informative tokens and down‑weighting ubiquitous ones. Experiments on five decoder‑only language models (1.1B–13B parameters) show consistent reductions in memorized substring length while maintaining perplexity and downstream performance. The method is architecture‑agnostic, adds less than 3% computational overhead, and can be integrated into existing training pipelines.
By Zhijian Li, Stefan Larson, Kevin Leach
arXiv:2606. 26120v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) offer a promising alternative to autoregressive models, excelling in text generation tasks due to their bidirectional attention mechanisms.
By Tianyi Wu, Xiaoxi Sun, Yanhua Jiao, Yulin Li, Yixin Chen, YunHao Cao, YiQi Hu, Zhuotao Tian
arXiv:2606. 27550v1 Announce Type: cross Abstract: Multi-token prediction has been shown to increase data density during training, improve downstream text-generation quality, and serves as the defacto approach for self-speculative decoding.
By Carrie Chen
arXiv:2602. 10238v2 Announce Type: replace-cross Abstract: The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Key-Value (KV) cache.
By Luca Moschella, Laura Manduchi, Ozan Sener
arXiv:2607. 20791v1 Announce Type: new Abstract: High-temperature sampling is one of the primary mechanisms for increasing diversity in LLMs.
By Phillip Howard, Xin Su, Allen Roush, Manikandan Ravikiran, Amir Abdullah
arXiv:2607. 16213v1 Announce Type: new Abstract: Large Language Models (LLMs) generate text autoregressively, relying on a key-value (KV) cache whose memory footprint grows linearly with context length, creating a major bottleneck.
By Soumia Bouyahiaoui, Manel Kara laouar, Aicha Boutorh, Mohamed Hadj Ameur
arXiv:2607. 14107v1 Announce Type: cross Abstract: The inference efficiency of diffusion large language models (dLLMs) is constrained by two challenges: bidirectional attention precludes efficient KV-cache reuse, while increasing decoding parallelism with static confidence thresholds can compromise generation quality.
By Mingyu Lee, Akshat Ramachandran, Souvik Kundu, Tushar Krishna
arXiv:2607. 20467v1 Announce Type: new Abstract: While parallel decoding is central to the efficiency of Diffusion Large Language Models (dLLMs), current strategies are often hindered by overly conservative confidence thresholds.
By Yanhua Jiao, Tianyi Wu, Xiaoxi Sun, Yulin Li, HuiLing Zhen, Libo Qin, Baotian Hu, Zhuotao Tian, Min Zhang
arXiv:2610.01687v1 Announce Type: cross
Abstract: Test-time scaling often seeks better answers by sampling multiple responses from a frozen model, yet conventional temperature sampling generates ever...
By Akshit Singh, Shyam Marjit, Wei Lin, Leonid Karlinsky, M. Jehanzeb Mirza
Ripple-Pivot Search (RPS) is a training‑free decoding method for Diffusion Large Language Models that identifies mid‑entropy pivot positions to reduce uncertainty across remaining masked tokens. By proactively committing these pivots and evaluating token assignments via lookahead, RPS enables more tokens to be unmasked in parallel, speeding up decoding. Experiments on three dLLMs and four reasoning/code‑generation benchmarks show 4–10× wall‑clock speedup over standard decoding, up to 18× with KV caching, while maintaining or improving generation quality.
By Yushi Ye, Xu Chen, Haoyun Jiang, Jinsong Lan, Haihong Tang, Xiangtao Li, Mingming Gong, Ivor Tsang, Yanfeng Wang, Jiangchao Yao