# TiDAR: Think in Diffusion, Talk in Autoregression

arXiv: https://arxiv.org/abs/2511.08923 · HTML: https://mlsanity.com/paper/2511.08923/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion reasoning and test-time scaling, one of 17 directions in LLM reasoning.
- Builds on 24 of its 52 references that are in the map.
- First posted on arXiv 12 Nov 2025.

## Placed in

- LLM reasoning / [Diffusion reasoning and test-time scaling](https://mlsanity.com/lr/diffusion-reasoning-and-test-time-scaling/)
- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)
- Efficient LLM inference and serving / [Diffusion LLM and MoE inference](https://mlsanity.com/inference/diffusion-llm-and-moe-inference/)

## Builds on (most cited first, 24 of 24)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [Dream 7B: Diffusion Large Language Models](https://mlsanity.com/paper/2508.15487/) (2025)
- [Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models](https://mlsanity.com/paper/2503.09573/) (2025)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [Better & Faster Large Language Models via Multi-token Prediction](https://mlsanity.com/paper/2404.19737/) (2024)
- [SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model](https://mlsanity.com/paper/2502.02737/) (2025)
- [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://mlsanity.com/paper/2503.01840/) (2025)
- [Flex Attention: A Programming Model for Generating Optimized Attention Kernels](https://mlsanity.com/paper/2412.05496/) (2024)
- [LLM Inference Unveiled: Survey and Roofline Model Insights](https://mlsanity.com/paper/2402.16363/) (2024)
- [Accelerating Diffusion LLMs via Adaptive Parallel Decoding](https://mlsanity.com/paper/2506.00413/) (2025)
- [Theoretical Benefit and Limitation of Diffusion Language Model](https://mlsanity.com/paper/2502.09622/) (2025)
- [Set Block Decoding is a Language Model Inference Accelerator](https://mlsanity.com/paper/2509.04185/) (2025)
- [Sequential Diffusion Language Models](https://mlsanity.com/paper/2509.24007/) (2025)

## Built on by (most cited first, 30 of 37)

- [LLaDA2.0: Scaling Up Diffusion Language Models to 100B](https://mlsanity.com/paper/2512.15745/) (2025)
- [LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding](https://mlsanity.com/paper/2605.27365/) (2026)
- [Scaling Beyond Masked Diffusion Language Models](https://mlsanity.com/paper/2602.15014/) (2026)
- [Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding](https://mlsanity.com/paper/2607.05722/) (2026)
- [CDLM: Consistency Diffusion Language Models For Faster Sampling](https://mlsanity.com/paper/2511.19269/) (2025)
- [Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone](https://mlsanity.com/paper/2512.22615/) (2025)
- [DMax: Aggressive Parallel Decoding for dLLMs](https://mlsanity.com/paper/2604.08302/) (2026)
- [dLLM: Simple Diffusion Language Modeling](https://mlsanity.com/paper/2602.22661/) (2026)
- [CoDAR: Continuous Diffusion Language Models are More Powerful Than You Think](https://mlsanity.com/paper/2603.02547/) (2026)
- [Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model](https://mlsanity.com/paper/2601.15892/) (2026)
- [Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers](https://mlsanity.com/paper/2606.31779/) (2026)
- [Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow](https://mlsanity.com/paper/2601.15593/) (2026)
- [Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM](https://mlsanity.com/paper/2604.06832/) (2026)
- [DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding](https://mlsanity.com/paper/2606.02091/) (2026)
- [Introspective Diffusion Language Models](https://mlsanity.com/paper/2604.11035/) (2026)
- [FLARE: Diffusion for Hybrid Language Model](https://mlsanity.com/paper/2606.01774/) (2026)
- [Revealing the Attention Floating Mechanism in Masked Diffusion Models](https://mlsanity.com/paper/2601.07894/) (2026)
- [TreeFlash: Parallel AR-Approximation for Faster Speculative Decoding](https://mlsanity.com/paper/2606.03819/) (2026)
- [DeLS-Spec: Decoupled Long-Short Contexts for Parallel Speculative Drafting](https://mlsanity.com/paper/2607.07409/) (2026)
- [dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models](https://mlsanity.com/paper/2603.18806/) (2026)
- [Locally Coherent Parallel Decoding in Diffusion Language Models](https://mlsanity.com/paper/2603.20216/) (2026)
- [Dataset-Level Metrics Attenuate Non-Determinism: A Fine-Grained Non-Determinism Evaluation in Diffusion Language Models](https://mlsanity.com/paper/2604.13413/) (2026)
- [TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models](https://mlsanity.com/paper/2604.00666/) (2026)
- [FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration](https://mlsanity.com/paper/2605.20022/) (2026)
- [Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting](https://mlsanity.com/paper/2605.29727/) (2026)
- [Unlocking Lossless Speedups in LLMs via Discrete Diffusion](https://mlsanity.com/paper/2609.04010/) (2026)
- [Projected Autoregression: Autoregressive Language Generation in Continuous State Space](https://mlsanity.com/paper/2601.04854/) (2026)
- [Tuning the Implicit Regularizer of Masked Diffusion Language Models: Enhancing Generalization via Insights from k-Parity](https://mlsanity.com/paper/2601.22450/) (2026)
- [Enabling KV Caching of Shared Prefix for Diffusion Language Models](https://mlsanity.com/paper/2606.07571/) (2026)
- [From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models](https://mlsanity.com/paper/2607.26504/) (2026)

## Abstract (arXiv)

Diffusion language models hold the promise of fast parallel generation, while autoregressive (AR) models typically excel in quality due to their causal structure aligning naturally with language modeling. This raises a fundamental question: can we achieve a synergy with high throughput, higher GPU utilization, and AR level quality? Existing methods fail to effectively balance these two aspects, either prioritizing AR using a weaker model for sequential drafting (speculative decoding), leading to lower drafting efficiency, or using some form of left-to-right (AR-like) decoding logic for diffusion, which still suffers from quality degradation and forfeits its potential parallelizability. We introduce TiDAR, a sequence-level hybrid architecture that drafts tokens (Thinking) in Diffusion and samples final outputs (Talking) AutoRegressively - all within a single forward pass using specially designed structured attention masks. This design exploits the free GPU compute density, achieving a strong balance between drafting and verification capacity. Moreover, TiDAR is designed to be serving-friendly (low overhead) as a standalone model. We extensively evaluate TiDAR against AR models, speculative decoding, and diffusion variants across generative and likelihood tasks at 1.5B and 8B scales. Thanks to the parallel drafting and sampling as well as exact KV cache support, TiDAR outperforms speculative decoding in measured throughput and surpasses diffusion models like Dream and Llada in both efficiency and quality. Most notably, TiDAR is the first architecture to close the quality gap with AR models while delivering 4.71x to 5.91x more tokens per second.