{"total":15,"items":[{"citing_arxiv_id":"2607.05722","ref_index":66,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding","primary_cat":"cs.CL","submitted_at":"2026-07-07T01:09:54+00:00","verdict":"ACCEPT","verdict_confidence":"HIGH","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Joint AR–diffusion training yields one tri-mode LM that switches AR, diffusion, and self-speculation, beating open AR/diffusion models on accuracy and tokens-per-forward.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29215","ref_index":43,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Multi-Block Diffusion Language Models","primary_cat":"cs.LG","submitted_at":"2026-06-28T05:53:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MBD-LMs raise average tokens per forward pass from 3.47 to 6.19 (and to 9.34 with DMax) via multi-block teacher forcing and optimized parallel decoding while holding or slightly improving accuracy on math and code tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10820","ref_index":55,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling","primary_cat":"cs.LG","submitted_at":"2026-06-09T13:02:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"K-Forcing introduces progressive self-forcing distillation to train a conditional push-forward model that jointly decodes k future tokens per forward pass, yielding 2.4-3.5x speedup at k=4 with modest quality loss on LM1B and OpenWebText.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.04486","ref_index":54,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Global Sketch-Based Watermarking for Diffusion Language Models","primary_cat":"cs.CR","submitted_at":"2026-06-03T06:08:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces a sketch-based watermarking method for masked diffusion language models providing an order-agnostic detection statistic decoupled from local context.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20813","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PulseCol: Periodically Refreshed Column-Sparse Attention for Accelerating Diffusion Language Models","primary_cat":"cs.CL","submitted_at":"2026-05-20T07:06:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PulseCol introduces periodically refreshed column-sparse attention to achieve up to 1.95x speedup over FlashAttention in diffusion LLMs with maintained model quality.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14530","ref_index":20,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Mitigating Mask Prior Drift and Positional Attention Collapse in Large Diffusion Vision-Language Models","primary_cat":"cs.CV","submitted_at":"2026-05-14T08:11:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Diagnoses mask prior drift and positional attention collapse in LDVLMs and introduces two plug-and-play decoding interventions that raise long-form generation quality without retraining.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09536","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM","primary_cat":"cs.CL","submitted_at":"2026-05-10T13:38:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TAD improves the accuracy-parallelism trade-off in diffusion LLMs via temporal-aware self-distillation that applies hard labels to soon-to-be-decoded tokens and soft supervision to future tokens.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Following prior work [9], we apply a 4-shot setting for MATH and a 3-shot setting for LLaDA on MBPP, while using a 0-shot setting for the remaining evaluations. For inference, we set the generation length to 256 and the block length to 32, adopt entropy-based dynamic decoding with a threshold of 0.5, and employ a multi-block decoding strategy consistent with D2F [15] and d3LLM [9]. We report accuracy, tokens per forward (TPF), and the Accuracy Under Parallelism (AUP) score [9] to provide a comprehensive measurement of model performance and acceleration. 6 Table 1: Comparison ofTAD-LLaDAwith other LLaDA-based models. The best results among acceleration methods are highlighted inboldand the second best are underlined ."},{"citing_arxiv_id":"2605.10980","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection","primary_cat":"cs.LG","submitted_at":"2026-05-09T03:26:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LEAP detects early-converging tokens in dLLMs via future context filtering and multi-sequence superposition, reducing average denoising steps by about 30% while maintaining accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.19349","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Where to Place the Query? Unveiling and Mitigating Positional Bias in In-Context Learning for Diffusion LLMs via Decoding Dynamics","primary_cat":"cs.CL","submitted_at":"2026-04-26T20:22:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Query position is a first-order variable in dLLM ICL whose variance matches semantic quality impact; mitigated via Average Confidence metric and training-free Auto-ICL routing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.09450","ref_index":47,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion","primary_cat":"cs.LG","submitted_at":"2026-04-10T16:07:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ECHO introduces one-step block diffusion via Direct Conditional Distillation and Response-Asymmetric Diffusion to generate chest X-ray reports faster than autoregressive models while improving clinical metrics.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"evaluation. InProceedings of the IEEE conference on computer vision and pattern recognition, 2015. [46] Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, et al. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution.arXiv preprint arXiv:2409.12191, 2024. [47] Xu Wang, Chenkai Xu, Yijie Jin, Jiachun Jin, Hao Zhang, and Zhijie Deng. Diffusion llms can do faster-than-ar inference via discrete diffusion forcing.arXiv preprint arXiv:2508.09192, 2025. [48] Chaoyi Wu, Xiaoman Zhang, Ya Zhang, Hui Hui, Yanfeng Wang, and Weidi Xie. Towards generalist foundation model for radiology by leveraging web-scale 2d&3d medical data."},{"citing_arxiv_id":"2604.08302","ref_index":78,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DMax: Aggressive Parallel Decoding for dLLMs","primary_cat":"cs.LG","submitted_at":"2026-04-09T14:35:42+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"DMax uses On-Policy Uniform Training and Soft Parallel Decoding to enable aggressive parallelism in dLLMs, raising TPF on GSM8K from 2.04 to 5.47 and on MBPP from 2.71 to 5.86 while preserving accuracy.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[76] Dimitri V on Rütte, Janis Fluri, Yuhui Ding, Antonio Orvieto, Bernhard Schölkopf, and Thomas Hofmann. Generalized interpolating discrete diffusion.arXiv preprint arXiv:2503.04482, 2025. [77] Kangyu Wang, Zhiyun Jiang, Haibo Feng, Weijia Zhao, Lin Liu, Jianguo Li, Zhenzhong Lan, and Weiyao Lin. Creditdecoding: Accelerating parallel decoding in diffusion large language models with trace credits. arXiv preprint arXiv:2510.06133, 2025. [78] Xu Wang, Chenkai Xu, Yijie Jin, Jiachun Jin, Hao Zhang, and Zhijie Deng. Diffusion llms can do faster-than-ar inference via discrete diffusion forcing.arXiv preprint arXiv:2508.09192, 2025. [79] Zeqing Wang, Gongfan Fang, Xinyin Ma, Xingyi Yang, and Xinchao Wang. Sparsed: Sparse attention for diffusion language models. InThe Fourteenth International Conference on Learning Representations,"},{"citing_arxiv_id":"2604.06330","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"STDec: Spatio-Temporal Stability Guided Decoding for dLLMs","primary_cat":"cs.CL","submitted_at":"2026-04-07T18:13:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"STDec raises dLLM decoding speed by up to 14x on benchmarks like MBPP by using observed spatio-temporal stability to create dynamic, token-specific confidence thresholds while preserving task performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.08404","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration","primary_cat":"cs.CL","submitted_at":"2026-02-09T09:05:46+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Three expert-activation strategies (delayed caching, speculative exploration, limited activation) accelerate MoE diffusion LLMs by up to 2.2x with minimal quality change.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.14067","ref_index":46,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed","primary_cat":"cs.CL","submitted_at":"2025-12-16T04:12:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Efficient-DLM converts AR models to dLMs via block-wise causal attention and position-dependent masking, yielding higher accuracy and 2.7-4.5x throughput than Dream 7B and Qwen3 4B.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.15745","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LLaDA2.0: Scaling Up Diffusion Language Models to 100B","primary_cat":"cs.LG","submitted_at":"2025-12-10T09:26:18+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LLaDA2.0 scales discrete diffusion language models to 100B parameters via systematic conversion from autoregressive models using a 3-phase WSD training scheme and releases open-source 16B and 100B MoE variants.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}