20 results for “diffusion large language models”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Yuchen Zhu, Jing Shi, Chongjian Ge, Hao Tan +8 more
FLARE is a systematic conversion framework that enables a single checkpoint to support both autoregressive (AR) and diffusion-style parallel decoding for hybrid-attention large language models, achiev…
The paper introduces NaRA, a noise-aware LoRA technique that dynamically adapts fine-tuning parameters based on the noise level during diffusion, significantly improving the performance of Diffusion L…
Zirui Wu, Lin Zheng, Jiacheng Ye, Shansan Gong +4 more
The authors develop a block diffusion reasoning model called DreamReasoner-8B and study the effect of training and inference block sizes on long chain-of-thought reasoning.
The paper presents LESS, a training-free, model-agnostic adaptive sampler for diffusion large language models that improves accuracy and reduces computational cost.
Zekai Li, Ji Liu, Yiqing Huang, Ziqiong Liu +2 more
The paper proposes a novel trace-aware decoding framework, combining Temporal-Spatial Parallel Decoding (TSPD) and Confidence Extrapolation (CE), to significantly accelerate the inference of diffusion…
This paper evaluates the consistency and effectiveness of decoding methods for diffusion large language models (dLLMs) across diverse evaluation settings and reveals their sensitivity to prompt templa…
The paper introduces 'infilling extraction' to accurately model training data memorization in Diffusion Language Models (DLMs), finding that bidirectional masking significantly increases the extractab…
Jinnan Yang, Yan Wang, Zhen Bi, Kehao Wu +4 more
WaveFilter is a novel, training-free framework that uses wavelet transforms to efficiently filter critical tokens in the KV cache, significantly improving the long-context performance of Diffusion LLM…
The paper proposes EPIC, an efficient and parallel decoding framework that significantly speeds up the process of constraining diffusion language model outputs using Context-Free Grammars (CFG).
Yijie Jin, Jiajun Xu, Yuxuan Liu, Chenkai Xu +7 more
This paper proposes Multi-Block Diffusion Language Models (MBD-LMs) for text generation, which are obtained by post-training Block Diffusion Language Models (BD-LMs) with Multi-block Teacher Forcing (…
Paul Jünger, Justin Lovelace, Linxi Zhao, Dongyoung Go +1 more
The paper introduces SARDI, a novel, training-free framework that uses low-confidence 'lookahead' tokens generated during the denoising process of discrete diffusion language models to dynamically gui…
Xiaoyou Wu, Cheng-Jhih Shih, Binfei Ji, Yong Liu +1 more
BlockBatch introduces a novel framework that efficiently accelerates diffusion language model (dLLM) inference by simultaneously executing multiple block-size branches for a single request, achieving…
The paper introduces DLM-SWAI, a training-free method that effectively steers diffusion language models (DLMs) toward desired textual styles or properties by biasing the token distribution at each den…
The paper proposes DLLM-VSR, a novel Diffusion Large Language Model framework for Visual Speech Recognition, achieving state-of-the-art performance by treating transcription as iterative masked denois…
The paper introduces a novel scheme to adapt speculative decoding for continuous diffusions, enabling block verification and improving acceptance rates.
The paper analyzes order-agnostic language models (OALMs), finding that their learned conditionals are not true factorizations and proposing a variance-based diagnostic to compare the quality of diffe…
The paper proposes Large Language Gibbs, a scheme for structured probabilistic inference using conditional distributions of large language models as transition operators.
Minhua Lin, Zijun Wang, Zewen Liu, Zhaotian Weng +6 more
This paper proposes a method, LM2LM, to train large language models to generate effective improvement proposals using reinforcement learning and a research world model.