Autoregressive Generation

Recent advances in sign language (SL) research have shown a trend toward unifying multiple sign language understanding (SLU) subtasks, such as isolated sign language recognition (ISLR), continuous sign language recognition (CSLR), and sign language translation (SLT), within a single framework, leading to substantial progress. Meanwhile, sign language production (SLP), which generates sign sequences from text, has also attracted growing attention. This naturally raises an important question: can sign language understanding and production be unified within a single framework? Compared with unifying SLU subtasks, this problem is substantially more challenging. Existing SLU tasks largely share the same direction of mapping, namely from sign inputs to linguistic outputs, whereas SLT and SLP lie in opposite directions of sign-text mapping. A unified framework must therefore address two key challenges: (1) bridging the modality gap between continuous sign motions and discrete text tokens through a shared sign tokenizer that supports both linguistic abstraction and motion reconstruction; and (2) learning a single conditional autoregressive model that can take either sign or text as input and generate the corresponding target sequence in the opposite modality. To this end, we propose Uni-SLTP, a unified framework for SLT and SLP with two key components: (1) a shared sign tokenizer that converts sign sequences into discrete tokens and latent representations, capturing both semantic and reconstructive information; and (2) a unified autoregressive generation model that formulates both tasks as conditional sequence generation. Experiments on widely used public datasets show that Uni-SLTP achieves superior motion accuracy for SLP while maintaining competitive SLT performance.

Diffusion language models (DLMs) iteratively refine a sequence, allowing earlier predictions to be revised as context evolves. This rollback capability distinguishes them from irreversible autoregressive generation, but makes inference costly. Every denoising update alters the global context, forcing both prompt and response states to be recomputed even though only response tokens are revisable. Key-value (KV) caching could reduce this cost, yet conventional caching assumes immutable historical states and is therefore difficult to reconcile with rollback. In this paper, we introduce Adaptive Reuse of Cached Hidden States for Efficient Rollback (Archer), a training-free KV caching method for rollback-capable DLMs. Archer asymmetrically keeps the mutable response synchronized with the current hypothesis while reusing prompt K/V within a bounded state neighborhood. Although prompt representations also change under bidirectional attention, their token identities remain fixed; bounded reuse therefore amortizes repeated prompt computation without caching mutable response states. It also delays feedback from tentative tokens, reducing premature reinforcement of transient high-confidence errors and giving rollback more opportunity to correct them. Our analysis characterizes prompt reuse as a reversibility-aligned cache boundary, bounds its state-dependent approximation error, and gives a decoder-margin condition for preserving full-refresh decisions. Existing DLM acceleration often trades quality for speed. Archer shifts this frontier, attaining the best mean performance of 33.63% together with a 2.57x mean speedup on the main suite. Across evaluated settings, it improves Pass@1 by up to 3.05 points and reaches up to 2.95x speedup. Controlled analyses connect the quality gain to delayed prompt feedback and validate state-aware refresh. Our code is available at https://github.com/Hxnng/Archer.

Papers 1-2 of the Kathleen series showed that a byte-level, attention-free architecture built from a wavetable encoder and multi-scale reverberant state can match strong baselines on classification at ~450-700K parameters, without pretraining. We ask whether the same ingredients can generate. (1) Scaling: on byte-level language modeling (WikiText-103, raw UTF-8, no tokenizer), the reverberant model beats a parameter-matched transformer at every dataset scale measured (2-512 MB), e.g. 1.84 vs 2.04 bits/byte at 512 MB with ~0.5M parameters; the transformer needs more than 512 MB to match what the attention-free model learns from 32 MB. (2) Measurement: we introduce FORM DISTANCE, a non-parametric, gaming-resistant instrument for "reads like text": nine statistical axes of human text define a reference cloud, and five constructed fakes are all rejected. (3) Generation: decoding policy dominates architecture -- widening the sampler halves the same model's distance (3.17 to 1.52), and a retrieval-augmented decoding scheme takes the frozen model further (1.52 to 1.14) with no training step involved; the ablation attributes the gain to the sparse phrase dose itself, not the selection gate. The gain has a sharp boundary condition: the phrases must come from the model's own training corpus -- a 40x larger foreign library helps not at all, an effect the attention twin shares, consistent with in-context integration being a capability of scale. We also report four architectural additions that did not help, and a computed lexicon reaching 94% of a learned table's top-1 accuracy at one fifth of the parameters. Everything runs offline; all experiments are reproducible on a free Kaggle T4.

Hallucination remains a persistent challenge in generative super-resolution (GSR), where reconstructed results may contain visually plausible yet weakly supported content, structural deviations, or unnatural textures with respect to the low-resolution (LR) input. Existing GSR methods have extensively explored the trade-off between perceptual realism and reconstruction fidelity, but the division between preserving reliable coarse-scale information and restoring more uncertain fine details is often handled implicitly within the overall restoration process. Visual autoregressive (VAR) modeling provides a natural opportunity to revisit this issue, as its coarse-to-fine next-scale prediction offers an explicit scale-wise generation interface. However, existing VAR-based SR methods still inherit the original full 1-to-$N$ autoregressive generation path, even though, for super-resolution, coarse-scale information in LR is often relatively more reliable, while long autoregressive chains may accumulate prediction errors. Motivated by these observations, we propose \textbf{K2N}, which reformulates VAR-based SR from full-path generation into a $k$-to-$N$ detail continuation process. Specifically, early coarse-scale states are established directly from LR, while only the remaining finer scales are restored autoregressively. Experimental results show that K2N remains competitive with the VARSR baseline on standard SR metrics, while exhibiting clearer advantages on hallucination-focused evaluation. These findings suggest that explicitly rethinking the generation path in a scale-wise manner can be a promising direction for improving the reliability of generative super-resolution. Our code will be released soon at https://github.com/BRL-SYSU/K2NSR.

We introduce DiffusionGemma, an experimental open-weight language model that uses discrete diffusion to generate text at exceptionally high speed. Rather than decoding one token at a time, DiffusionGemma iteratively refines blocks of 256 tokens in parallel, avoiding the sequential decoding bottleneck of conventional autoregressive (AR) large language models. Instead of training from scratch, we obtain DiffusionGemma by fine-tuning the mixture-of-experts Gemma 4 model with 3.8B activated and 25.2B total parameters. Our compute-efficient two-stage training pipeline uses fewer than 10% of the starting AR model's total training token budget. The first stage uses supervised fine-tuning to teach bidirectional denoising, while the second stage combines reinforcement learning with sampler distillation to jointly improve generation quality and inference efficiency. DiffusionGemma establishes a new Pareto frontier for the trade-off between generation speed and model capability. Averaged across our full evaluation suite, it generates around 20 tokens per forward pass and achieves roughly 1,500 output tokens per second on a single NVIDIA H100 GPU, which is substantially faster than AR models even with state-of-the-art speculative decoding. DiffusionGemma also retains the starting model's support for thinking mode, multimodal inputs, and long contexts. Despite diffusion fine-tuning, it remains capable of AR generation with only minor performance degradation, suggesting a path toward hybrid diffusion-AR decoding.

Autoregressive decoders emit flat token sequences and cannot enforce hierarchical constraints across output segments, a limitation that becomes acute in patent claim generation, where a claim set forms a dependency forest whose scope must narrow monotonically with depth. Topology and content are mutually dependent: a dependent claim's wording must reflect its parent's scope, yet the parent must be chosen before that wording exists, so neither post-hoc parsing nor grammar-constrained decoding suffices. We propose SPG (Structure-aware Patent Generation), which predicts topology inside the autoregressive pass. A pointer head selects each dependent claim's parent, and its gradients, together with a depth-adaptive scope regularizer, reshape the shared decoder's representations during training. A second stage then applies a violation-weighted preference objective over self-generated deficient candidates, supplying the negative signal that granted-patent corpora lack. On HUPD-DCG, SPG on Llama-3-8B-Instruct recovers 79.0% of gold parent links, a quantity its training reward never supervises, and raises antecedent consistency from 0.292 to 0.478 over a supervised baseline of equal scale, with expert evaluation corroborating these gains.

Existing vector-sketch models treat recognition and generation as separate tasks, leaving a gap for streaming interfaces that must understand a drawing as it is being made. We present SketchMamba, a single causal sequence model that continuously classifies a sketch from any partial prefix while simultaneously generating its continuation. We achieve this by applying a dense per-step classification loss to a selective state-space backbone. Evaluated on a 58-class subset of the Quick, Draw! dataset, SketchMamba yields 94.93% final-step accuracy and a progressive-accuracy Area Under the Curve (AUC) of 0.706, crossing 90% of its final accuracy by the time 70% of the strokes are drawn. In a matched-budget comparison, the 1.55 million-parameter backbone ties a causal Transformer while outperforming recurrent and convolutional baselines. Ablations confirm that the dense supervision regime, rather than the architecture alone, drives the early-prediction capability. The results demonstrate that a single causal hidden state can unify progressive recognition and autoregressive generation without auxiliary encoders or task-specific branching.

Speculative decoding accelerates autoregressive generation by having a cheap draft propose tokens that a target verifies in parallel. Frontier models increasingly ship a built-in Multi-Token-Prediction (MTP/NEXTN) draft head under the assumption that the draft is negligibly cheap. At million-token context this breaks: an MTP draft head typically runs full attention over the entire KV cache at every draft step, so its read grows linearly with context and comes to dominate the draft cost -- precisely where speculation is most valuable. The effect compounds with draft length (a deep native draft can turn net-negative, slower than no speculation) and sharpens under hybrid/linear-attention targets, where cheaper verification leaves the draft's full-attention read exposed. We apply a StreamingLLM-style sliding window plus attention sink to the draft's attention only (Windowed-MTP), leaving full-attention verification intact. It is training-free, drop-in, and lossless by construction: the full-attention target still decides every accepted token, so windowing changes only which tokens are proposed, never which are accepted. It bounds the draft's KV working set to a constant, dropping ~99% of KV entries at 1M. Across three architecture families (Qwen GDN-MoE 35B/122B and a Mamba2-hybrid NoPE 120B) at 1M context on a single GPU in SGLang, windowing cuts the per-decode-step cost over the shipping native MTP draft by +28% to +44%, an input-invariant margin that widens with context. Since per-token latency is this cost divided by acceptance length, at matched acceptance end-to-end decode latency improves by the same amount, and more where windowing also lifts acceptance, while preserving the target's verified output distribution. Finally, the unread draft KV -- 7.7-11% of total KV at 1M -- is reclaimed via a compact ring buffer at no acceptance or quality cost.

We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) generates harmful output to a given prompt. We study a new application of the Clopper-Pearson confidence intervals to obtain probably approximately correct (PAC) bounds for this problem. As our main technical contribution, we propose an algorithm that leverages features in the latent space to prioritize exploring branches in the auto-regressive generation tree that are more likely to produce harmful outputs. Our approach in particular enables the efficient computation of useful lower bounds, even in scenarios where the true harm probability is extremely small, and crucially, the obtained lower bounds are sound, i.e., formally proven to be less than the actual harmfulness probability: our experimental results demonstrate the effectiveness of our method by computing non-trivial lower bounds on state-of-the-art LLMs. This study newly enables the evaluation and statistical certification of LLMs.

Efficient teamwork typically combines global coordination with parallel execution, a principle not yet fully reflected in unified Vision-Language Model (VLM)-based document parsers. Existing unified parsers process an entire page jointly but generate its output through a single token-by-token autoregressive trajectory, creating a sequential bottleneck that grows with document length. Such full-page sequential generation overlooks a key property of document parsing: layout must be analyzed globally, whereas block content can be parsed in parallel. Based on this observation, we introduce HPD-Parsing, which replaces full-page autoregressive generation with a Hierarchical Parallel Decoding paradigm. A main layout branch organizes the overall document structure and dynamically assigns block-level content decoding to concurrent branches, while progressive multi-token prediction (P-MTP) further reduces the decoding steps within each branch. Experiments on public benchmarks show that HPD-Parsing achieves 4,752 tokens per second, delivering $2.62\times$ the throughput of the fastest existing document parsing model and $3.06\times$ that of the vanilla autoregressive baseline, while maintaining competitive parsing accuracy. These results establish hierarchical parallel decoding as an effective alternative to full-page autoregressive generation, opening a new direction for efficient unified document parsing.

Diffusion models have recently become the dominant paradigm for monocular depth estimation (MDE). However, they implicitly assume that depth can be recovered as a globally smooth field through iterative denoising, which does not explicitly reflect the piecewise and scale-dependent organization of scene geometry. In practice, geometric structure emerges progressively across spatial scales, where coarse layout, surfaces, and boundaries are constructed in a hierarchical manner. Motivated by this observation, we introduce ARDepth, which formulates depth estimation as structured auto-regressive generation. Instead of recovering depth through global refinement, ARDepth progressively constructs depth representations as spatial resolution increases. To support this generative process, we introduce Scale-Progressive Conditioning (SPC) to inject multi-scale visual features at each generation stage, and Semantic-Aware Guidance (SAG) to provide scene-level semantic priors that enhance global structural consistency. Together, these designs enable the model to capture fine-grained local details while maintaining coherent global geometry. Empirical results demonstrate that our approach achieves strong performance and produces structurally consistent depth predictions across scales, validating auto-regressive generation as a promising alternative paradigm for geometric modeling.

Virtual try-on (VTON) is a bi-conditional image generation problem that requires not only accurate person preservation but also faithful garment deformation and detail synthesis. Diffusion-based VTON methods can jointly model these factors in a compressed latent space, but suffer from high-frequency detail loss due to inherent latent compression, even with costly multi-step denoising. Recent visual autoregressive (VAR) models offer a promising alternative for high-quality generation with faster inference, yet remain unexplored for VTON due to the lack of effective bi-conditioning mechanisms. To bridge this gap, we first introduce VAR-VTON, a VAR-based VTON model that incorporates garment conditioning and structural guidance for efficient latent-space VTON. Despite its efficacy, latent-space generation still struggles to preserve fine-grained garment details. We argue that different VTON sub-tasks should be addressed in different representation spaces: structural synthesis such as garment warping and person layout is suited to the latent space, whereas fine-grained detail recovery should be tackled in the pixel space. Motivated by this insight, we further propose STAR-VTON, a Two-Stage AutoRegressive framework that builds upon VAR-VTON by decoupling latent-space structural synthesis from pixel-space detail recovery. Our idea is to resort to a matching-informed refiner to establish dense correspondences between the stage-one generation and the source garment to directly map fine-grained pixel-space details. Extensive experiments show that STAR-VTON achieves an impressive efficiency-fidelity trade-off: VAR-VTON runs at least $4\times$ faster than diffusion-based counterparts without degrading quality, and the pixel-space refiner effectively restores fine details and acts as a plug-and-play module that can benefit existing VTON approaches.

Speculative decoding accelerates autoregressive generation by letting a lightweight drafter propose multiple tokens that are verified by a larger target model. Although effective for text-only LLMs, speculative decoding yields limited gains in VLMs because drafters often diverge on vision-critical content, while existing multimodal acceleration methods do not directly address irrelevant visual evidence or optimize the verifier-accepted prefix length that governs speedup. We propose TIGER, a Text-conditioned vIsual GatEd Routing framework for multimodal speculative decoding. TIGER dynamically selects a sparse set of context-relevant visual tokens based on the drafter's current textual state, rather than expose the full visual token set or a fixed compressed interface. To better align training with inference-time efficiency, we optimize the drafter with acceptance-aligned group-based policy training using verifier-derived rewards based on accepted prefix length, built on top of distillation warm start with KL anchoring. This encourages the drafter not only to imitate the target model, but also to produce speculative continuations that survive verification for longer prefixes. Experiments show that TIGER yields consistent gains in accepted prefix length and speculative speedup under exact verifier-side speculative decoding, while achieving favorable quality-latency trade-offs with comparable downstream accuracy in visual-routing analyses.

Large autoregressive language models exhibit a self-correction blind spot: they reliably fix identical errors when attributed to an external source yet fail to fix the same errors in their own outputs. Prior work has documented this phenomenon empirically, through controlled error injection, error-depth decompositions, RL-based verifier-corrector training, and intrinsic self-verification, but offers no formal model of why generating a token suppresses the ability to detect its error, no quantitative activation condition for correction markers, and no convergence guarantee for reinforcement-learning-based self-correction. We close these gaps with SPARC, a spectral-algebraic theory of self-correction in autoregressive generation. We define the error-propagation operator as the product of per-step attention Jacobians on the residual stream and prove that the blind spot arises if and only if the spectral radius of this operator is at least one. We derive a sharp activation threshold, given as a function of the spectral radius, that a correction marker must exceed, recovering the 89.3% blind-spot reduction observed with a simple ``Wait'' marker. We further prove that RL-based verifier-corrector training converges at a rate proportional to the squared coupling strength over the square root of the number of samples if and only if the verifier-corrector coupling matrix has spectral norm below one, and that this criterion is invariant across residual-stream autoregressive modalities, unifying text LLMs and autoregressive image and video generation. Experiments across four backbones and a visual autoregressive probe validate every theorem, with spectral predictions matching measured blind-spot rates within 3.2% RMSE.

Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel drafters efficiently propose long token sequences in a single forward pass, they suffer from rapid acceptance decay due to a lack of inter-token dependencies. Furthermore, indiscriminately verifying these extended blocks wastes critical batch capacity on tokens with high rejection risks, severely degrading throughput in high-concurrency serving systems. We introduce DSpark, a speculative decoding framework that unifies high-throughput parallel generation with adaptive, load-aware verification. To maintain draft quality, DSpark utilizes a semi-autoregressive architecture, coupling a parallel backbone with a lightweight sequential module, to introduce intra-block dependency modeling and mitigate suffix decay. To optimize system efficiency, DSpark employs confidence-scheduled verification, dynamically tailoring the verification length for each request based on estimated prefix survival probabilities and engine-specific throughput profiles. On offline benchmarks across diverse domains, DSpark substantially improves the accepted length over state-of-the-art autoregressive and parallel drafters. When deployed within the DeepSeek-V4 serving system under live user traffic, DSpark successfully mitigates verification waste. Compared to the established production baseline (MTP-1), DSpark accelerates per-user generation speeds by 60 to 85 percent at matched throughput levels. More importantly, by preventing severe throughput degradation under strict interactivity constraints, it enables performance tiers that were previously unattainable, shifting the Pareto frontier of our serving system.

Autoregressive (AR) text-to-speech (TTS) models generate discrete speech tokens sequentially, which makes inference slow and can degrade robustness by propagating local errors and hallucinations. This limitation stems from their left-to-right AR commitment: each token must be determined before future speech-token context is available. However, such ordering is not an inherent requirement for TTS, as the full input text is available before synthesis. In this paper, we introduce DELTA-TTS, a lightweight LoRA-based adaptation framework that converts a pretrained AR TTS model into a discrete diffusion language model (dLLM) for confidence-ordered speech-token decoding. To better capture the local structure of speech, DELTA-TTS incorporates a convolution module that injects local acoustic context, together with a $1/t$-weighted training objective and a time-shifted inference schedule that defer low-confidence positions to later steps. Trained on only $585$ hours of LibriTTS, DELTA-TTS achieves a $\textbf{1.75}\%$ WER on Seed-TTS test-en, outperforming its AR backbone while generating tokens $\textbf{3.3}\times$ faster. Further analysis shows that DELTA-TTS produces sharper text--speech alignment, increases overall decoding confidence, and mitigates hallucinations observed in AR generation.

Recent progress in large-scale generative models has substantially advanced video generation, yet existing methods remain constrained by a rigid inference paradigm. Bidirectional diffusion models excel at global coherence and visual fidelity but suffer from slow inference, while autoregressive models offer efficient and streaming generation at the cost of long-range consistency and exposure bias. We introduce Flex-Forcing, a unified training and inference framework that enables a video diffusion model to seamlessly operate under both bidirectional and autoregressive generation regimes. The core idea is a flexible chunking mechanism jointly defined over the temporal axis and denoising steps. This design allows the model to (1) perform flexible chunking according to different device budgets, (2) perform bidirectional inference across chunks for global structure planning, while generating frames autoregressively within each chunk for efficient and fine-grained synthesis, and (3) perform any-order, any-timestep autoregressive generation without the strict causal constraint. Extensive experiments on multiple video generation benchmarks demonstrate that Flex-Forcing achieves consistently better video quality, long-video stability than strong baselines with a rigid inference schedule, while offering faster inference.

Speculative decoding accelerates autoregressive generation by drafting a block of tokens that the target model verifies left-to-right, committing only the longest accepted prefix. Block (DLM-style) drafters predict the whole block in parallel, which is fast but trained with a full-block cross-entropy that supervises every position against the gold continuation -- even though inference discards every token after the first rejection. Recent acceptance-aware objectives patch this by reweighting the full-block loss; we instead use teacher-forced learning as a motivation for how supervision should concentrate on the accepted prefix. A mask-only block drafter has no input-side channel for gold-prefix conditioning, so AUF approximates that prefix-sensitive supervision on the loss side by keeping the cross-entropy support only through the drafter's first predicted failure. AUF is a single, detached change to the CE support -- no auxiliary objective, no verifier rollouts, and no change to the inference pipeline or the exactness contract. Within fixed drafter backbones and serving settings on Qwen3-8B, AUF raises the DFlash drafter's average emitted length $τ$, averaged over six benchmarks, from 2.40 to 2.61, with a gain on every benchmark, and transfers to Domino's two-branch head (2.56 to 2.68). Two findings sharpen the picture: the decay-only baseline reaches higher token accuracy on the shared block mask yet decodes worse, and on DFlash, once AUF truncates the support, the standard exponential position-decay weighting becomes empirically inert.

Efficient sampling of molecular systems at thermodynamic equilibrium is a hallmark challenge in statistical physics. This challenge has driven the development of Boltzmann Generators (BGs), which allow rapid generation of uncorrelated equilibrium samples by combining a generative model with exact likelihoods and an importance sampling correction. However, modern BGs predominantly rely on normalizing flows (NFs), which either suffer from limited expressivity due to strict invertibility constraints (discrete time) or computationally expensive likelihoods (continuous time). In this paper, we propose Autoregressive Boltzmann Generators (ArBG) -- a novel autoregressive modelling framework -- that overcomes these limitations by departing from the flow-based BG paradigm. ArBG circumvents the topological constraints of flows and enables sequential inference-time interventions, while offering enhanced scalability by leveraging architectures effective in Large Language Models. We empirically demonstrate that ArBG leads to significant improvements over flow-based models across all benchmarks, but particularly in larger peptide systems such as the 10-residue Chignolin. Furthermore, we introduce Robin, a 132 million parameter transferable model trained with the ArBG framework which improves over the previous state-of-the-art, reducing the zero-shot energy error, E-W$_2$, on 8-residue systems by over 60$\%$. The code can be found at the following link: https://github.com/danyalrehman/autobg.

Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discretized visual tokens. These tokens are derived from a codebook that maps embeddings to quantized visual patterns. The language-like architecture enables unified multimodal models to effectively capture text conditional information for generation, making them promising for text-to-image tasks. This also raises an interesting question: how safe are the images generated in such an autoregressive way? In this work, we propose iterative self-improving codebooks for safe autoregressive generation. We leverage the understanding and judgment capabilities of the unified multimodal model itself to identify unsafe generated images without human annotation. Subsequently, the inherent representations in the codebook are fixed to eliminate harmful mappings. Our method comprises two steps: first, we use the unified model to identify unsafe generations and construct corresponding harmful and safe image-text pairs. These pairs are used to construct the Harmful Space and guide updates to the codebook, thereby eliminating harmful outputs. Second, we perform adaptive fine-tuning on the codebook within the harmless space using safe image-text pairs to ensure the quality of generated images. These two steps are repeated until no further improvement is observed, producing a safety-enhanced model codebook. Without additional external feedback, the safety of models is improved iteratively.

Manual reporting of 3D MRI studies is time-consuming, yet end-to-end structured report generation for 3D liver MRI remains underexplored due to volumetric complexity and scarce paired data. We propose MRI2Rep, an autoregressive framework for liver MRI report generation. From 3,929 real-world MRI-report pairs acquired over a 10-year single-institution cohort, a Report-to-Label Canonicalization (RLC) module converts free-text reports into structured, closed-vocabulary diagnostic sequences without lesion-level annotations. On a held-out test set, MRI2Rep achieves 76.0% case-level sensitivity, 29.4% lesion-level F1, compared with no more than 8.3% for adapted medical vision-language baselines, and 82.4% liver-level accuracy. In a blinded reader study, two radiologists rated 75% and 70% of AI-generated reports as clinically acceptable, compared with 95% and 100% for original reports. Our automated LLM-based judge, LLM-Eval, rated 61.8% of AI-generated reports as acceptable, applying a stricter standard and supporting its use as a conservative proxy. To our knowledge, this is the first end-to-end LI-RADS-structured reporting system for 3D liver MRI.

Non-autoregressive generation offers a powerful paradigm for iterative refinement, allowing models to recursively critique, erase and regenerate arbitrary subsets of tokens. However, existing non-autoregressive models fail to realize this potential. Masked Diffusion Models (MDMs) suffer from factorization error, causing sample quality to collapse when generating multiple tokens simultaneously. Flow Map Language Models (FMLMs) circumvent this bottleneck via joint sequence transport for excellent few-step generation, but sacrifice the inference-time flexibility of MDMs. We introduce FMLM+, a framework that bridges this gap by equipping FMLM with masking-style noise schedules. While generating the full sequence in a single step, FMLM+ simultaneously scores the global consistency of each token a posteriori. We leverage this to introduce Posterior Refinement, a novel inference-time refinement strategy that enables the model to adaptively self-correct its outputs, matching the performance of discrete baselines with 32x fewer NFEs. Across diverse benchmarks, we demonstrate that FMLM+ with Posterior Refinement improves the speed--quality tradeoff over both MDM and FMLM families, providing a scalable foundation for high-fidelity language modeling.

Modeling and sampling from the underlying distribution of asynchronous event sequences are crucial in various real-world applications, including social networks, medical diagnosis, and financial transactions. Existing autoregressive methods suffer from error accumulation during multi-step generation, while non-autoregressive diffusion methods are typically limited to fixed-length output sequences. In this paper, we propose Latent Block-Diffusion Temporal Point Processes (LBDTPP), a novel semi-autoregressive TPP framework that introduces a latent block diffusion mechanism for high-quality and variable-length event sequence generation. The core idea is to define an autoregressive probability distribution over event blocks in latent space and perform Gaussian diffusion within each block. By sequentially generating blocks while simultaneously sampling events in each block, LBDTPP preserves the length flexibility of autoregressive TPPs and inherits the parallel high-quality generation capability of diffusion models. Theoretically, we derive Wasserstein error bounds showing that, under suitable local approximation and prefix-stability assumptions, block-wise generation can reduce error accumulation compared with event-wise autoregressive generation. Extensive experiments on six real-world benchmark datasets demonstrate that LBDTPP outperforms state-of-the-art TPP baselines in both unconditional and conditional generation tasks. Further empirical analyses verify the benefits of latent-space diffusion and block-wise generation, and reveal the trade-off between generation quality and block size. Our code is available at https://github.com/Zh-Shuai/LBDTPP.

Autoregressive generation in large language models (LLMs) conventionally decodes from the final layer, assuming that deeper representations yield more reliable next-token predictions. We revisit this assumption by revealing a recurring Guess-Refine-Perturb dynamic: early layers form coarse guesses, intermediate layers refine reasoning-relevant semantics, and final layers can perturb these refined predictions toward generic or alignment-preferred tokens. We introduce Confident Decoding, a training-free decoding strategy that dynamically selects the most reliable near-final layer through entropy-guided conservative backward search. We further provide a theoretical formulation of layer selection as an optimal stopping problem, showing that under bounded projection noise and dominant late-stage alignment perturbation, our search rule filters perturbation while bounding the loss relative to the oracle refinement layer. Experiments across dense and Mixture-of-Experts LLMs demonstrate consistent gains on challenging reasoning benchmarks, including GPQA-Diamond, Omni-MATH, and HLE, with zero memory overhead and less than 2% latency increase. These results suggest dynamically bypassing final-layer perturbations can unlock stronger reasoning behavior from aligned LLMs.

We study internalization processes, by which neural-network-based systems absorb an explicit computational procedure into their own weights, and how they facilitate learning. We investigate how transformers internalize the simulation of semiautomata by internalizing chain-of-thought (CoT) tokens, which classes of semiautomata are harder to internalize, and expose the flip side of internalization, that is, a progressive degradation of out-of-distribution performance. We then provide the first provable analysis of successful internalization: for the task of learning parities, we show that a simplified one-layer transformer provably first learns the target with explicit CoT supervision and then internalizes the autoregressive generation as CoT tokens are progressively removed, learning to directly compute the parity. This task is computationally hard to learn from data without CoT supervision. Finally, we discuss how learning through internalization relates to the \textit{Positive Distribution Shift} phenomenon recently introduced by~\citet{Med+26}.

Large Language Models (LLMs) have revolutionized language modeling through autoregressive generation, enabling strong performance across a wide range of tasks. Recently, Diffusion Language Models (DLMs) have emerged as an alternative paradigm that generates text through iterative denoising rather than next-token prediction, allowing parallel refinement of entire sequences. While numerous diffusion-based architectures have been proposed, differences in evaluation protocols, datasets, inference budgets, and generation hyperparameters make it difficult to compare their capabilities and understand the trade-offs they offer. In this work, we present a systematic experimental analysis of modern DLMs. Specifically, we evaluate eight state-of-the-art DLMs across eight benchmarks spanning reasoning, coding, translation, knowledge, and structured problem solving, while explicitly considering both generation quality and computational efficiency. Beyond downstream evaluation, we analyze the impact of key inference-time factors, including denoising steps, context length, block size, and parallel unmasking strategies, and complement large-scale experiments with controlled comparisons of smaller models trained under identical conditions. Our analysis highlights the strengths and limitations of diffusion-based language modeling across different tasks, architectures, and inference budgets. We show that the behavior of DLMs is strongly influenced by generation-time design choices, leading to distinct trade-offs between performance and computational efficiency. Overall, our study provides practical insights into the capabilities and deployment characteristics of contemporary DLMs.

Enhancing the formal math reasoning capabilities of Large Language Models (LLMs) has become a key focus in both mathematical and computer science communities in recent years. While significant progress has been made in using state-of-the-art Auto-Regressive (AR) LLMs for formal theorem proving, these models suffer from inherent limitations. Their next-token prediction generation methods may yield suboptimal performance due to the challenges of long-range coherence and the compounding of errors over long sequences. Recent advancements in diffusion LLMs (dLLMs), which generate text through iterative denoising of a multi-token block, offer a promising alternative. However, the application of dLLMs to formal mathematics, where maintaining long-range coherence is critical, remains largely understudied. To address the challenges above, we propose Diffusion-Proof, to the best of our knowledge, the first framework to train and apply dLLMs for formal theorem proving. Our frameworks contain training and inference methods for two models. The first one is dLLM-Prover-7B, which performs whole-proof writing with long-range coherent tactic usage. The second one is dLLM-Corrector-7B, which is a novel large block diffusion-based correction model. It leverages the in-filling capabilities of dLLMs to perform local proof correction using bi-directional information. Extensive experiments demonstrate that Diffusion-Proof relatively significantly outperforms the AR LLM baseline trained under the same dataset. Diffusion-Proof achieves an absolute improvement of 1.61% on ProofNet-Test and 6.14% on MiniF2F-Test benchmarks compare to the baseline. Notably, Diffusion-Proof successfully resolves one IMO problem that more advanced thinking model DeepSeek-Prover-V2-7B could not solve, showcasing the unique advantage of dLLMs in formal theorem proving.

The knowledge encoded in large language models (LLMs) can serve as a substrate for structured reasoning over variables describing a complex world, but accessing this knowledge in a probabilistically coherent manner poses a difficult inference problem. We propose Large Language Gibbs, a scheme for structured probabilistic inference that uses conditional distributions of an LLM as transition operators. Rather than sampling structured objects through single-pass autoregressive generation, we iteratively resample individual variables conditioned on others using an LLM's next-token conditionals. This approach avoids order-dependent biases and produces a stationary distribution that reflects a compromise between all local conditionals. We apply this approach to sampling from synthetic distributions, consistent reasoning tasks, and Bayesian structure learning. The results suggest that the use of LLM conditionals in MCMC is a practical alternative to one-pass generation for structured probabilistic inference under a world prior accessible through noisy LLM conditionals.

Modern particles physics experiments have demonstrated an increasing need for fast, high-fidelity detector simulation as detector components have improved and subsequent computational requirements approach the limits of available resources. Recently, deep generative models have emerged as a promising alternative to traditional Monte-Carlo methods, with recent works drawing inspiration from large language models (LLMs) and self-supervised next-token prediction methods. In this work, we present an application of a GPT-style autoregressive transformer as a fast surrogate model for the calorimeter inside the CLAS12 experiment at the Thomas Jefferson National Accelerator Facility. The model is conditioned on incident momentum and generates realistic detector hits autoregressively across all nine calorimeter layers as sequences of strip, ADC, and TDC tokens. We demonstrate that the model faithfully reproduces hit multiplicity, spatial distributions, energy deposits, and the energy-momentum response of the electromagnetic calorimeter. The generator achieves inference rates exceeding 700 events per second on a single GPU, providing a substantial speedup over traditional Geant4-based simulations while maintaining physics fidelity essential for high-luminosity experimental programs.

Generating realistic humanoid motion from scene images and text involves both low-frequency pose semantics and high-frequency physical dynamics. However, many existing methods tokenize motion with a single shared codebook, forcing heterogeneous motion signals into the same quantization space. Our frequency-domain analysis of human motion data reveals a clear mismatch between single-codebook quantization and motion statistics: five DCT coefficients capture 93% of joint-position energy but only 37% of joint-velocity energy, which can bias quantization toward pose statistics and under-represent high-frequency velocity components. A second challenge lies in adapting a standard autoregressive model to effectively model high-frequency physical signals in motion sequences. Therefore, we propose DSFT, a dual-stream frequency tokenizer that separates motion into Base and physical streams and compresses them independently with DCT truncation and BPE. Furthermore, we present MotionVLA, a Qwen3.5-based model that arranges Base and physical tokens in a unified sequence, where Phys tokens are predicted after Base tokens. Experiments on HumanML3D and MBench show that, despite using a lightweight 2B backbone, MotionVLA reduces the Diversity gap to real data by over 50% on HumanML3D and improves Motion-Condition Consistency by 3.8% on MBench, supporting frequency-aware dual-stream decoupling as an effective formulation for autoregressive motion generation. Code: https://github.com/AIGeeksGroup/MotionVLA. Website: https://aigeeksgroup.github.io/MotionVLA.

Autoregressive (AR) language modeling is the dominant paradigm for text generation, yet its sequential token-by-token decoding makes inference memory-bound and inefficient. Existing acceleration approaches, such as speculative decoding and diffusion language models, can yield speedups under certain conditions but do not directly address high-load batch serving--the scenario most critical for industrial-scale deployment. We introduce K-Forcing, a push-forward language modeling paradigm for joint next-k-token decoding. K-Forcing distills an existing AR model into a conditional push-forward mapping--one that transforms independent uniform noise variables into a joint sample of multiple future tokens in a single forward pass. This design preserves fixed-length outputs, reuses the AR teacher backbone, and remains compatible with standard AR serving infrastructure. We train this mapping via progressive self-forcing distillation, which gradually expands the prediction window while enabling the student to closely match the sequence distribution of the AR teacher. We evaluate K-Forcing on LM1B and OpenWebText using a standard causal Transformer backbone. When aggressively configured to generate k = 4 tokens per forward pass, K-Forcing delivers approximately 2.4-3.5x speedup across different batch sizes, while incurring modest quality degradation relative to its AR teacher. As inference increasingly dominates the lifetime compute cost of modern LLMs, K-Forcing offers a promising route toward accelerating AR generation under real-world high-load deployment.

Diffusion language models generate text through iterative denoising, offering a powerful alternative to autoregressive generation. However, discrete language spaces lack a natural neighborhood structure for defining effective perturbations, so some artificial corruption schemes are proposed in the forward process. Such prescribed forward processes often produce states that are mathematically convenient but misaligned with drafts and errors encountered during generation, resulting in degraded sample quality. To address this limitation, we propose FReDA, a forward-free diffusion language model that eliminates the need for a hand-designed forward process. We formulate diffusion language modeling as recursive distribution refinement, in which model-generated drafts serve as implicit intermediate states, and the learned refinement model progressively moves the draft distribution toward the target distribution. Concretely, FReDA refines drafts by proposing candidate draft sequences and either directly performing self-refinement or selecting among parallel candidates via best-of-N refinement. With this design, FReDA is neighborhood-agnostic, model-complexity-aware, and compatible with flexible refinement parameterizations. Extensive evaluations in the sub-8B regime show that FReDA-4B outperforms larger diffusion base models on reasoning and coding benchmarks, achieving absolute gains of up to 15%, while reaching a 1.5-1.8x average speedup over diffusion baselines and scaling effectively with additional refinement computation.

We propose a statistical-field framework for text generated by large language models (LLMs), treating token embeddings as continuous spin variables on a one-dimensional chain. Defining a susceptibility from the connected two-point correlator and an order parameter from the ensemble-averaged embedding field, we vary the \texttt{softmax} temperature $T$ and observe a sharp susceptibility peak near a characteristic $T_c$ with power-law-like scaling, a concurrent rapid change in the order parameter, and a collapse onto a single semantic direction below $T_c$. The intrinsic dimension estimated by the two nearest neighbor (TwoNN) method independently corroborates these findings, reaching a minimum near $T_c$. Results are robust across model scales (Qwen3: 0.6B--32B) and prompt categories. While the phenomenology closely resembles a continuous phase transition, the non-equilibrium nature of autoregressive generation warrants further investigation. Our framework provides quantitative tools for probing the collective statistical structure of LLM outputs and suggests connections between decoding strategies and critical phenomena.

Generating executable tool plans requires selecting appropriate subsets from tool libraries, a combinatorial search problem with an exponentially large solution space. However, we identify a critical misalignment in predominant approaches: standard autoregressive (AR) decoding suffers from early commitment, where initial token choices rigidly constrain the search trajectory. A controlled study shows that masked denoising raises Pass@10 solution coverage from 0.320 to 0.943 over AR sampling under matched compute. Motivated by this, we propose DiG-Plan, a framework that decouples combinatorial exploration from structural refinement. DiG-Plan employs a diffusion-based proposer to generate diverse tool sets via iterative refinement, followed by an AR refiner for dependency prediction. On TaskBench, DiG-Plan improves over AR baselines by a 10% relative margin, with the largest gains on complex compositional tasks; API-Bank results show that the propose-refine-select design remains effective across domains. Code is available at https://github.com/puddingyeah/DiG-Plan.

Diffusion large language models (DLLMs) enable non-autoregressive generation by iteratively denoising corrupted token sequences with bidirectional context. Despite their ability to update multiple positions in parallel, inference remains costly due to the many denoising steps required for high-quality generation. We propose SAID, a Scaffold-Aware Iterative Decoding framework that accelerates DLLMs by reallocating computation across tokens. SAID first spends denoising computation on scaffold tokens to establish the coarse semantic structure, and then completes predictable detail tokens with fewer steps. We further adapt SAID to block-wise diffusion decoding and introduce Confidence-Hierarchical Layered Generation (CHLG), which assigns additional steps only to low-confidence tokens. Experiments on LLaDA-8B and LLaDA 1.5 across math, coding, and knowledge benchmarks show that SAID significantly accelerates DLLM inference with a maximum speedup of 9.1x while maintaining competitive performance. Our code is publicly available: https://github.com/TH-AI-Lab-PKU/SAID.

We present Echo Infinity, an autoregressive (AR) framework towards real-time infinite video generation that employs a learnable evolving memory to dynamically filter, abstract, and compress any-length history at constant cost. Existing methods mainly curate memory with predefined KV-cache schedules, fixed-ratio heuristic compression, or inference-time RoPE adaptation. These designs inevitably lose historical information and amplify compounding errors due to their limited cache window and ignorance of autoregressive generation noise. Inspired by human memory consolidation, Echo-Infinity replaces handcrafted memory curation with learnable Memory Query, which are updated by attention and a gating mechanism when past frames are evicted from the local window. The queries are optimized end-to-end with the video diffusion transformers (DiTs), forming an evolving memory that supports arbitrary compression ratios with constant computation independent of video length. They also act as a generalizable generation prior, improving quality even when only the optimized initial state is used. We further introduce Unified Relative RoPE Recipe, which anchors the sink frames to start from id 0 and lets the newest frame id grow at most to the DiTs' pretrained maximum temporal RoPE id throughout training and inference, freeing the model from the finite RoPE constraint and closing the train-test RoPE extrapolation gap. In long and short video generation, Echo-Infinity achieves state-of-the-art performance, and, to our knowledge, demonstrates promising 24-hour (>1.3 M frames) real-time rollouts for the first time, suggesting a practical path toward infinite video generation.

We present MORPHOS, a novel autoregressive framework that generates dynamic 3D assets from videos across diverse representations, including meshes, 3D Gaussians, and radiance fields. Existing methods are typically limited to a single representation, struggle to model topological changes, or fail to maintain temporal consistency over long videos. To address these limitations, we introduce the Temporal Structured Latents (T-SLAT), a unified 4D representation that jointly encodes geometry and appearance along the temporal dimension. Leveraging T-SLAT, MORPHOS autoregressively generates dynamic 3D assets via causal attention, conditioning each frame on its preceding history to ensure temporal consistency while handling evolving topologies. We also propose a temporal-structural augmentation to mitigate error accumulation in autoregressive generation. MORPHOS achieves state-of-the-art performance in appearance and competitive results in geometry across multiple benchmarks, demonstrating superior generalization across various representations and robustness in long-horizon generation.

Speculative decoding (SD) has proven to be an effective technique for accelerating autoregressive generation in large language models (LLMs) however, its application to vision-language models (VLMs) remains relatively unexplored. We propose~\textit{DREAM-S}, a novel SD framework designed specifically for fast and efficient decoding in VLMs. DREAM-S leverages a neural architecture search (NAS) framework with target-aware supernet training to automatically identify both the optimal interaction strategy between the draft and target models, and the most suitable draft model architecture for the underlying hardware implementation platform. DREAM-S additionally incorporates adaptive intermediate feature distillation, guided by attention entropy, to enable efficient draft training. Experiments on a range of well-established VLMs show that DREAM-S achieves up to a $3.85\times$ speedup compared to standard decoding approaches and significantly outperforms existing SD baselines. The code is publicly available at: https://github.com/SAI-Lab-NYU/DREAM-S .

To improve the reasoning capabilities of large language models, test-time compute is typically scaled by generating intermediate tokens before the final answer. However, this couples reasoning to autoregressive generation and thereby conflates internal computation with external communication. In contrast, human cognition can use working memory to hold and manipulate information internally without the need to externalize intermediate thoughts. Drawing on this principle, we introduce Reasoning in Memory (RiM), a latent reasoning method that replaces the autoregressive generation of reasoning steps with memory blocks. These memory blocks are fixed sequences of special tokens that unlock the working-memory capacity of large language models. Since they are fixed rather than generated, they can be processed in a single forward pass, enabling compute-efficient latent reasoning. To operationalize these memory blocks, we employ a two-stage curriculum. First, we ground them by predicting explicit reasoning steps after each memory block. Second, we discard this step-level supervision and iteratively refine the final answer after each memory block. Our experiments on reasoning benchmarks show that, across language models of different families and sizes, RiM matches or exceeds existing latent reasoning methods while avoiding the autoregressive generation of thoughts. These results demonstrate that large language models can be trained to use working memory as an effective mechanism for latent reasoning.

Autoregressive multimodal large language models (MLLMs) enable 3D generation but struggle to scale to high-resolution shapes due to inadequate 3D tokenizations. Compact set-based representations discard deterministic spatial ordering, leading to ambiguous sequence prediction, while uniform or octree-based voxel grids preserve ordering at the cost of severe redundancy and excessively long sequences. This structural trade-off limits stable and efficient autoregressive 3D generation. We present SuperVoxelGPT, a representation-first framework that resolves this tension through adaptive and deterministically ordered supervoxel tokenization. Given a prompt, we first predict a coarse geometric saliency distribution and construct a shape-adaptive supervoxel partition using saliency-guided centroidal Voronoi tessellation, allocating fine-grained cells to complex regions and larger cells to smooth regions. Conditioned on this prompt and ordered supervoxel layout, we introduce a SuperVoxelVAE and fine-tune a pretrained MLLM to autoregressively generate supervoxel tokens. Experiments using Trellis-500K data show that SuperVoxelGPT reduces token sequence length to 12.8% of uniform voxel tokenization while achieving state-of-the-art generation quality and an average 10x speedup over prior methods.

Rapid identification of candidate materials with target properties has become a key task in materials science. Machine learning has emerged as an alternative to physics-based simulation, offering a faster and cheaper way to filter materials based on their stability and other target properties, reducing the number of candidates that reach the costly synthesis stage. Recently, Large Language Models (LLMs) have been applied to this role, but these models are parameter-heavy and computationally expensive both during training and at inference time, making them unsuitable for high-throughput tasks. This inefficiency stems from both the large over-parameterization of language models and the difficulty of framing material generation as a sequence learning problem. In this paper, we present PRISMat, a cost-effective, permutation-invariant model, which addresses these limitations. We show that PRISMat, despite taking less time for inference, is able to outperform LLMs in generating crystal slabs conditioned on critical materials' surface properties. In targeted material discovery, we achieve mean absolute errors of 0.188 eV/A$^2$ and 2.79 eV for cleavage energy and work function tasks, respectively, reducing the error of the next best model by 4$\times$.

Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on discrete sequence generation. We argue that the bottleneck is not continuity itself, but a representation in which denoising depends on timestep-indexed noise regimes. We introduce \emph{Discrete Stochastic Localization} (DSL), a continuous-state framework with unit-sphere token embeddings whose Bayes-optimal denoiser is invariant to the nominal signal-to-noise ratio (SNR) under the localization channel. One trained network then supports an entire family of per-token SNR paths, with endpoint masked-diffusion paths as a special case. Fine-tuning a pretrained MDLM checkpoint with DSL substantially improves distributional faithfulness (MAUVE) on OpenWebText across all step budgets from $T{=}128$ to $T{=}1024$, and the same checkpoint supports random-order autoregressive sampling, as well as a hybrid continuous-then-discrete sampler using as few as T=48 total steps -- without distillation or retraining.

Autoregressive video generation aims at real-time, open-ended synthesis. Yet, cinematic storytelling is not merely the endless extension of a single scene; it requires progressing through evolving events, viewpoint shifts, and discrete shot boundaries. Existing autoregressive models often struggle in this setting. Trained primarily for short-horizon continuation, they treat long sequences as extended single shots, inevitably suffering from motion stagnation and semantic drift during long rollouts. To bridge this gap, we introduce CausalCine, an interactive autoregressive framework that transforms multi-shot video generation into an online directing process. CausalCine generates causally across shot changes, accepts dynamic prompts on the fly, and reuses context without regenerating previous shots. To achieve this, we first train a causal base model on native multi-shot sequences to learn complex shot transitions prior to acceleration. We then propose Content-Aware Memory Routing (CAMR), which dynamically retrieves historical KV entries according to attention-based relevance scores rather than temporal proximity, preserving cross-shot coherence under bounded active memory. Finally, we distill the causal base model into a few-step generator for real-time interactive generation. Extensive experiments demonstrate that CausalCine significantly outperforms autoregressive baselines and approaches the capability of bidirectional models while unlocking the streaming interactivity of causal generation. Demo available at https://yihao-meng.github.io/CausalCine/

Generative recommendation (GR) has emerged as a promising paradigm that predicts target items by autoregressively generating their semantic identifiers (SID). Most GR methods follow a quantization-representation-generation pipeline, first assigning each item a SID, then constructing input representations from SID-token embeddings, and finally predicting the target SID through autoregressive generation. Existing item-level representation constructions mainly take two forms: directly merging SID-token embeddings into a compact vector, or enriching item-level representations with external inputs through additional networks. However, these item-level constructors still expose two practical challenges: direct merging may amplify the information loss caused by quantization and ID collision while obscuring SID code relations, whereas external-input-based methods can strengthen item semantics but cannot reliably preserve the SID-structured evidence required for token-level generation. These limitations make representation construction an underexplored bottleneck, leading to two severe problems, \ie{} the Identity-Structure Preservation Conflict and Input-Output Granularity Mismatch. To this end, we propose ComeIR, a Conditional Memory enhanced Item Representation framework that reconstructs SID-token embeddings into item-aware inputs and restores the token granularity during SID decoding. Specifically, MM-guided token scoring adaptively estimates the contribution of each code within the SID, dual-level Engram memory captures intra-item code composition and inter-item transition patterns, and a memory-restoring prediction head reuses the memories during SID decoding. Extensive experiments demonstrate the effectiveness and flexibility of ComeIR, and further reveal scalable gains from enlarging conditional memory.

Speculative decoding speeds up autoregressive generation in Large Language Models (LLMs) through a two-step procedure, where a lightweight draft model proposes tokens which the target model then verifies in a single forward pass. Although the drafter network is small in modern architectures, its LM-head still performs projection to a large vocabulary, becoming one of the major computational bottlenecks. In prior work this issue has been predominantly addressed via static or dynamic vocabulary truncation. Yet mitigating the bottleneck, these methods bring in extra complexity, such as special vocabulary curation, sophisticated inference-time logic or modifications of the training setup. In this paper, we propose SlimSpec, a low-rank parameterization of the drafter's LM-head that compresses the inner representation rather than the output, preserving full vocabulary support. We evaluate our method with EAGLE-3 drafter across three target models and diverse benchmarks in both latency- and throughput-bound inference regimes. SlimSpec achieves $4\text{-}5\times$ acceleration over the standard LM-head architecture while maintaining a competitive acceptance length, surpassing existing methods by up to $8\text{-}9\%$ of the end-to-end speedup. Our method requires minimal adjustments of training and inference pipelines. Combined with the aforementioned speedup improvements, it makes SlimSpec a strong alternative across wide variety of draft LM-head architectures.

Recent byte-level language models (LMs) match the performance of token-level models without relying on subword vocabularies, yet their utility is limited by slow, byte-by-byte autoregressive generation. We address this bottleneck in the Byte Latent Transformer (BLT) through new training and generation techniques. First, we introduce BLT Diffusion (BLT-D), a new model and our fastest BLT variant, trained with an auxiliary block-wise diffusion objective alongside the standard next-byte prediction loss. This enables an inference procedure that generates multiple bytes in parallel per decoding step, substantially reducing the number of forward passes required to generate a sequence. Second, we propose two extensions inspired by speculative decoding that trade some of this speed for higher generation quality: BLT Self-speculation (BLT-S), in which BLT's local decoder continues generating past its normal patch boundaries to draft bytes, which are then verified with a single full-model forward pass; and BLT Diffusion+Verification (BLT-DV), which augments BLT-D with an autoregressive verification step after diffusion-based generation. All methods may achieve an estimated memory-bandwidth cost over 50% lower than BLT on generation tasks. Each approach offers its own unique advantages, together removing key barriers to the practical use of byte-level LMs.

Autoregressive generation is a powerful approach for high-fidelity image synthesis, but it remains computationally demanding and slow even on the most advanced accelerators. While speculative decoding has been explored to mitigate this bottleneck, existing approaches fail to achieve efficiency gains comparable to those observed in text generation. A key limitation is the target model's high uncertainty during image generation, which leads to high draft token rejection rates. In this work, we identify previously overlooked patterns in the target model's behavior that emerge naturally in tree-based speculative decoding. Specifically, we formalize two properties, semantic interchangeability and convergence, arising from the redundancies in the target model's hidden state representations. By capturing these redundancies across the depth and breadth of the predicted token tree, our method identifies principled opportunities for acceptance relaxation without requiring additional training. Additionally, we enhance standalone drafter performance by injecting the redundancy signals from the target model into drafter training with minimal modification. We evaluate our approach across multiple text-to-image models and drafter architectures. Results show that CASCADE achieves state-of-the-art speedups for drafter-based speculative decoding, with up to 3.6x acceleration, while maintaining image quality and text-prompt fidelity.

Autoregressive generation lies at the heart of the mechanism of large language models. It can be viewed as the repeated application of a next-token generator: starting from an input string (prompt), the generator is applied for $M$ steps, and the last generated token is taken as the final output. [Joshi et al., 2025] proposed a PAC model for studying the learnability of the input-output maps arising from this process. We develop an online analogue of this framework, focusing on the mistake bound of learning the final output induced by an unknown next-token generator. We distinguish between two forms of feedback. In the End-to-End model, after each round the learner observes only the final token produced after $M$ autoregressive steps. In the Chain-of-Thought model, the learner is additionally shown the entire $M$-step trajectory. Our goal is to understand how the optimal mistake bound depends on the generation horizon $M$, and to what extent observing intermediate tokens can reduce this dependence. Our main results show that the online theory of autoregressive learning exhibits a qualitative picture analogous to the statistical one found by [Hanneke et al., 2026], but with a different scale of dependence on the generation horizon. In the End-to-End model, we prove a taxonomy of possible mistake-bound growth rates in the generation horizon $M$: essentially any rate between constant and logarithmic can arise. We further show that this logarithmic ceiling is unavoidable. In the Chain-of-Thought model, we show that access to the full generated trajectory eliminates the dependence on $M$ altogether. We also analyze autoregressive linear threshold classes, and prove optimal mistake bounds, as well as a new lower bound for the statistical setting. Along the way, our results resolve several questions left open by [Joshi et al., 2025].

Recent diffusion large language models (dLLMs) have demonstrated both effectiveness and efficiency in reasoning via a block-based semi-autoregressive generation paradigm. Despite their progress, the fixed-size block generations remain a critical bottleneck for effective and coherent reasoning. 1. From a global perspective, different reasoning tasks would correspond to different optimal decoding block sizes, which makes a ``one-size-fits-all'' assumption ineffective. 2. Even within a single reasoning task, the rigid block partitioning would break the logical flow and reduce reasoning coherence. Through empirical observations, we reveal that for block-wise entropy, incorrect reasoning exhibits a fluctuating and unsteady trend between blocks, whereas the correctly generated tasks follow a consistent descending trend. Therefore, this paper proposes b1, a novel post-training framework for dLLMs that learns dynamic-size reasoning blocks via a Monotonic Entropy Descent objective with reinforcement learning to enhance reasoning coherence.b1 integrates seamlessly as a plug-and-play module with existing dLLM's post-training algorithms. Extensive experiments across various reasoning benchmarks showcase b1's consistent improvement over existing fixed-size block baselines. Our code has been released at https://github.com/YanJiangJerry/Block-R1.

With the rapid development of the Internet, users have increasingly higher expectations for the recommendation accuracy of online content consumption platforms. However, short videos often contain diverse segments, and users may not hold the same attitude toward all of them. Traditional binary-classification recommendation models, which treat a video as a single holistic entity, face limitations in accurately capturing such nuanced preferences. Considering that user consumption is a temporal process, this paper demonstrates that the timing of user actions can represent diverse intentions through statistical analysis and examination of action patterns. Based on this insight, we propose a novel modeling paradigm: Action-Aware Generative Sequence Network (A2Gen), which refines user actions along the temporal dimension and chains them into sequences for unified processing and prediction. First, we introduce the Context-aware Attention Module (CAM) to model action sequences enriched with item-specific contextual features. Building upon this, we develop the Hierarchical Sequence Encoder (HSE) to learn temporal action patterns from users' historical actions. Finally, through leveraging CAM, we design a module for action sequence generation: the Action-seq Autoregressive Generator (AAG). Extensive offline experiments on the Kuaishou's dataset and the Tmall public dataset demonstrate the superiority of our proposed model. Furthermore, through large-scale online A/B testing deployed on Kuaishou's platform, our model achieves significant improvements over baseline methods in multi-task prediction by leveraging sequential information. Specifically, it yields increases of 0.34% in user watch time, 8.1% in interaction rate, and 0.162% in overall user retention (LifeTime-7), leading to successful deployment across all traffic, serving over 400 million users every day.

Recent work on text diffusion models offers a promising alternative to autoregressive generation, but controlling their safety remains underexplored. Existing safety approaches are geared toward autoregressive models and typically rely on post-hoc filtering or inference-time interventions. These are inadequate for effectively addressing safety risks in text diffusion models. We propose the Safety-Aware Denoiser (SAD), a safety-guidance framework in text diffusion models. The SAD modifies the iterative denoising process such that the text sample at the final denoising step is steered toward provably safe regions of the text space. This inference-time method can integrate safety constraints into the denoiser, avoiding computationally expensive retraining of the underlying diffusion model and enabling flexible, lightweight safety guidance. We evaluate the safety of the generated text using the SAD, with respect to hazard taxonomy, memorization, and jailbreak. Experimental results show that SAD substantially reduces unsafe generations while preserving generation quality, diversity, and fluency, outperforming existing methods. These results demonstrate that our safety guidance during denoising provides an effective and scalable mechanism for enforcing safety in text diffusion models.

We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a novel resolution-agnostic 1D Transformer-based image tokenizer that encodes images into a dynamic, user-controllable sequence of 32-256 tokens, achieving a state-of-the-art efficiency and performance trade-off. Building on VibeToken, we present VibeToken-Gen, a class-conditioned AR generator with out-of-the-box support for arbitrary resolutions while requiring significantly fewer compute resources. Notably, VibeToken-Gen synthesizes 1024x1024 images using only 64 tokens and achieves 3.94 gFID; by comparison, a diffusion-based state-of-the-art alternative requires 1,024 tokens and attains 5.87 gFID. In contrast to fixed-resolution AR models such as LlamaGen -- whose inference FLOPs grow quadratically with resolution (11T FLOPs at 1024x1024) -- VibeToken-Gen maintains a constant 179G FLOPs (63.4x efficient) independent of resolution. We hope VibeToken can help unlock the wide adoption of AR visual generative models in production use cases.

Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling. Commonly, tokens describe local information, such as regions of pixels in images or word pieces in text, and AR generation predicts these tokens in a fixed order. A worthwhile question is whether token structures affect the ability to steer the generation through test-time search, where multiple candidate generations are explored and evaluated by a verifier. Using image generation as our testbed, we hypothesize that recent 1D ordered tokenizers with coarse-to-fine structure can be more amenable to search than classical 2D grid structures. This is rooted in the fact that the intermediate states in coarse-to-fine sequences carry semantic meaning that verifiers can reliably evaluate, enabling effective steering during generation. Through controlled experiments, we find that AR models trained on coarse-to-fine ordered tokens exhibit improved test-time scaling behavior compared to grid-based counterparts. Moreover, we demonstrate that, thanks to the ordered structure, pure test-time search over token sequences (i.e., without training an AR model) can perform training-free text-to-image generation when guided by an image-text verifier. Beyond this, we systematically study how classical search algorithms (best-of-N, beam search, lookahead search) interact with different token structures, as well as the role of different verifiers and AR priors. Our results highlight the impact of token structure on inference-time scalability and provide practical guidance for test-time scaling in AR models.

While diffusion models dominate the field of visual generation, they are computationally inefficient, applying a uniform computational effort regardless of different complexity. In contrast, autoregressive (AR) models are inherently complexity-aware, as evidenced by their variable likelihoods, but are often hindered by lossy discrete tokenization and error accumulation. In this work, we introduce Generative Refinement Networks (GRN), a next-generation visual synthesis paradigm that addresses these issues. At its core, GRN addresses the discrete tokenization bottleneck through a theoretically near-lossless Hierarchical Binary Quantization (HBQ), achieving a reconstruction quality comparable to continuous counterparts. Built upon HBQ's latent space, GRN fundamentally upgrades AR generation with a global refinement mechanism that progressively perfects and corrects artworks -- like a human artist painting. Besides, GRN integrates an entropy-guided sampling strategy, enabling complexity-aware, adaptive-step generation without compromising visual quality. On the ImageNet benchmark, GRN establishes new records in image reconstruction (0.56 rFID) and class-conditional image generation (1.81 gFID). We also scale GRN to more challenging text-to-image and text-to-video generation, delivering superior performance on an equivalent scale. We release all models and code to foster further research on GRN.

Tree-based speculative decoding accelerates autoregressive generation by verifying a branching tree of draft tokens in a single target-model forward pass. However, existing methods prioritize maximizing token-level likelihood or the number of accepted tokens while ignoring a critical ``efficiency paradox'': the computational overhead of drafting and verifying big trees can grow super-linearly, particularly at scale. This often leads to negative wall-clock speedup when batch sizes increase or hardware saturation limits are reached. To address this, we propose SMART, a system-aware marginal analysis framework for runtime tree construction. SMART reformulates tree expansion as a hardware-aware optimization problem that directly maximizes end-to-end speedup. By applying a principled marginal benefit--cost rule at inference time, SMART expands a node only when its marginal benefit--cost ratio exceeds the tree-level speedup. SMART is training-free and serves as a plug-and-play controller for existing frameworks like MSD and EAGLE. Extensive evaluations across three MLLMs (e.g., LLaVA, Qwen2-VL) and four LLMs (e.g., Llama-3.1, DeepSeek-R1) demonstrate that SMART consistently outperforms state-of-the-art baselines. It delivers an average additional speedup of 20.0% for MLLMs and 15.4% for LLMs across compute-bound batching regimes and diverse GPU architectures without performance loss.

We pose uncertainty quantification and exploration in online decision-making as a problem of training and generation from an autoregressive sequence model, an area experiencing rapid innovation. Our approach rests on viewing uncertainty as arising from missing future outcomes that could be revealed through action choices, rather than from unobservable latent parameters of the environment. This reformulation aligns naturally with modern machine learning capabilities: we can i) train generative models through next-outcome prediction rather than fit explicit priors, ii) assess uncertainty through autoregressive generation rather than sampling latent parameters from posteriors, and iii) adapt to new information by extending the sequence model's context rather than explicit posterior updating. Our main theoretical result establishes a reduction from online decision-making to offline next-outcome prediction: Bayesian regret is controlled directly by the sequence model's offline prediction loss, without requiring an explicit latent-variable posterior. Experiments, including a semi-synthetic news recommendation task, show that autoregressive generation produces calibrated epistemic uncertainty and enables effective exploration by using article text as prior information to focus exploration on resolving remaining uncertainties.