Storytelling Generation

Large language models (LLMs) adapted to specific languages through continual pretraining or instruction tuning often suffer from catastrophic forgetting, which can lead to factual inaccuracies. This issue is particularly pronounced in multilingual settings, where adaptation may override general world knowledge with language-specific patterns. We propose LoRA-Gated Contrastive Decoding (LGCD), a training-free inference-time decoding framework that improves factuality in language-adapted LLMs by leveraging knowledge from the original pretrained model. LGCD operates by (1) extracting factual representations from Feed-Forward Network (FFN) layers via LoRA-based decomposition, approximating pretrained knowledge, (2) dynamically gating decoding based on token-level confidence, and (3) applying contrastive decoding with Top-K masking to revise uncertain predictions by referencing the approximated representation of pretrained knowledge. LGCD requires no additional training or access to the original pretraining data. Extensive experiments with LGCD on multilingual multiple-choice and long-form QA tasks across nine languages demonstrate its strong effectiveness in mitigating hallucinations and enhancing factual accuracy in language-adapted models. These results further indicate that pretrained knowledge can be strategically reintroduced during decoding to promote factual multilingual generation.

This paper introduces ExpertLongBench, an expert-level benchmark containing 11 tasks from 9 domains that reflect realistic expert workflows and applications. Beyond question answering, the application-driven tasks in ExpertLongBench demand long-form outputs that can exceed 5,000 tokens and strict adherence to domain-specific requirements. Notably, each task in ExpertLongBench includes a rubric, designed or validated by domain experts, to specify task requirements and guide output evaluation. Furthermore, we propose CLEAR, an evaluation framework that supports accurate evaluation of long-form model outputs in our benchmark. To achieve fine-grained, expert-aligned evaluation, CLEAR derives checklists from both model outputs and references by extracting information corresponding to items in the task-specific rubric. Checklist items of model outputs are then compared with corresponding items of reference outputs to assess their correctness, enabling grounded evaluation. We benchmark 13 popular large language models (LLMs) and analyze components in CLEAR, showing that (1) existing LLMs, with the top performer Gemini-2.5-Pro achieving only a 33.4 F1 score, require significant improvement for expert-level tasks; (2) models can generate content corresponding to the required aspects, but far from correct; and (3) accurate checklist extraction and comparison in CLEAR can be achieved by open-weight models for more scalable, reproducible, and low-cost usage.

We present LongLive, a frame-level autoregressive (AR) framework for real-time and interactive long video generation. Long video generation presents challenges in both efficiency and quality. Diffusion and Diffusion-Forcing models can produce high-quality videos but suffer from low efficiency due to bidirectional attention. Causal attention AR models support KV caching for faster inference but often degrade in quality on long videos due to memory challenges during long-video training. In addition, beyond static prompt-based generation, interactive capabilities, such as streaming prompt inputs, are critical for dynamic content creation, enabling users to guide narratives in real time. This interactive requirement significantly increases the complexity, especially in ensuring visual consistency and semantic coherence during prompt transitions. To address these challenges, LongLive adopts a causal, frame-level AR design that integrates a KV-recache mechanism that refreshes cached states with the new prompt for smooth, adherent switches streaming long tuning to enable long video training and to align training and inference (train-long–test-long); and short window attention paired with a frame-level attention sink, preserving long-range consistency while enabling faster generation. With these key designs, LongLive fine-tunes a 1.3B-parameter short-clip model to minute-long generation in just 32 GPU-days. At inference, LongLive sustains 20.7 FPS on a single NVIDIA H100, achieves strong performance on VBench in both short- and long-video settings. LongLive supports up to 240-second videos on a single H100 GPU. With FP8 quantization, LongLive boosts inference to 24.8 FPS with marginal quality loss.

Preference alignment has enabled large language models (LLMs) to better reflect human expectations, but current methods mostly optimize for population-level preferences, overlooking individual users. Personalization is essential, yet early approaches—such as prompt customization or fine-tuning—struggle to reason over implicit preferences, limiting real-world effectiveness. Recent “think-then-generate” methods address this by reasoning before response generation. However, they face challenges in long-form generation: their static one-shot reasoning must capture all relevant information for the full response generation, making learning difficult and limiting adaptability to evolving content. To address this issue, we propose **FlyThinker**, an efficient “think-while-generating” framework for personalized long-form generation. FlyThinker employs a separate reasoning model that generates latent token-level reasoning in parallel, which is fused into the generation model to dynamically guide response generation. This design enables reasoning and generation to run concurrently, ensuring inference efficiency. In addition, the reasoning model is designed to depend only on previous responses rather than its own prior outputs, which preserves training parallelism across different positions—allowing all reasoning tokens for training data to be produced in a single forward pass like standard LLM training, ensuring training efficiency. Extensive experiments on real-world benchmarks demonstrate that FlyThinker achieves better personalized generation while keeping training and inference efficiency.

While modern text-to-image models excel at generating images from intricate prompts, they struggle to capture the key details when the prompts are expanded into descriptive paragraphs. This limitation stems from the prevalence of short captions in their training data. Existing methods attempt to address this by either fine-tuning on long-prompt data, which generalizes poorly to even longer inputs; or by projecting the oversize inputs into normal-prompt domain and compromising fidelity. We propose a compositional approach that enables pre-trained models to handle long-prompts by breaking it down into manageable components. Specifically, we introduce a trainable PromptDecomposer module to decompose the long-prompt into a set of distinct sub-prompts. The pre-trained T2I model processes these sub-prompts in parallel, and their corresponding outputs are merged together using concept conjunction. Our compositional long-text-to-image model achieves performance comparable to those with specialized tuning. Meanwhile, our approach demonstrates superior generalization, outperforming other models by 7.4% on prompts over 500 tokens in the challenging DetailMaster benchmark.

We tackle the task of long-form music generation, particularly the challenging \textbf{lyrics-to-song} problem, by introducing \textbf{YuE (乐)}, a family of open-source music generation foundation models. Specifically, YuE scales to trillions of tokens and generates up to five minutes of music while maintaining lyrical alignment, coherent musical structure, and engaging vocal melodies with appropriate accompaniment. It achieves this through \textbf{track-decoupled next-token prediction} to overcome dense mixture signals, and \textbf{structural progressive conditioning} for long-context lyrical alignment. In addition, we redesign the \textbf{in-context learning} technique for music generation, enabling bidirectional content creation, style cloning, and improving musicality. Through extensive evaluation, we demonstrate that YuE matches or even surpasses some of the proprietary systems in musicality and vocal agility (as of 2025-01). We strongly encourage readers to \textbf{listen to our demo}\footnote{\url{https://yue-anonymous.github.io}}.

Recent years have witnessed remarkable progress in generative AI, with natural language emerging as the most common conditioning input. As underlying models grow more powerful, researchers are exploring increasingly diverse conditioning signals -- such as depth maps, edge maps, camera parameters, and reference images -- to give users finer control over generation. Among different modalities, sketches constitute a natural and long-standing form of human communication, enabling rapid expression of visual concepts. Yet algorithms that effectively handle true freehand sketches -- with their inherent abstraction and distortions -- remain largely unexplored. In this work, we distinguish between edge maps, often regarded as “sketches” in the literature, and genuine freehand sketches. We pursue the challenging goal of balancing photorealism with sketch adherence when generating images from freehand input. A key obstacle is the absence of ground-truth, pixel-aligned images: by their nature, freehand sketches do not have a single correct alignment. To address this, we propose a modulation-based approach that prioritizes semantic interpretation of the sketch over strict adherence to individual edge positions. We further introduce a novel loss that enables training on freehand sketches without requiring ground-truth pixel-aligned images. We show that our method outperforms existing approaches in both semantic alignment with freehand sketch inputs and in the realism and overall quality of the generated images.

Open-ended generation tasks require outputs to satisfy diverse and often implicit task-specific evaluation rubrics. The sheer number of relevant rubrics leads to prohibitively high verification costs and incomplete assessments of a response, making reinforcement learning (RL) post-training with rubric-based rewards difficult to scale. This problem is exacerbated by the fact that often the best way to combine these rubrics into one single reward is also highly prompt-specific. We propose Reinforcement Learning from Dynamic Critic Feedback (RLDCF), a post-training approach that addresses these challenges via dynamic rubric verification. Our approach employs a large language model (LLM) as a critic that dynamically identifies only the most likely failure modes (e.g., a factual error or unhandled edge case), which are then verified by an external validator to optimize both generator and critic jointly. By training both the generator and the critic, this game enhances the critic's error detection and the generator's output quality while reducing required verifications. Our experiments demonstrate that RLDCF improves factual accuracy in text generation and correctness in code generation, while also outperforming exhaustive verification and reward model methods. We show that dynamic critics are more effective than fixed critics, showcasing the potential of RLDCF for scaling RL post-training to free-form generation tasks.

We introduce $\texttt{PairFlow}$, a lightweight preprocessing step for training Discrete Flow Models (DFMs) to achieve few-step sampling without requiring a pretrained teacher. DFMs have recently emerged as a new class of generative models for discrete data, offering strong performance. However, they suffer from slow sampling due to their iterative nature. Existing acceleration methods largely depend on finetuning, which introduces substantial additional training overhead. $\texttt{PairFlow}$ addresses this issue with a lightweight preprocessing step. Inspired by ReFlow and its extension to DFMs, we train DFMs from coupled samples of source and target distributions, without requiring any pretrained teacher. At the core of our approach is a closed-form inversion for DFMs, which allows efficient construction of paired source–target samples. Despite its extremely low cost, taking only up to 1.7\% of the compute needed for full model training, $\texttt{PairFlow}$ matches or even surpasses the performance of two-stage training involving finetuning. Furthermore, models trained with our framework provide stronger base models for subsequent distillation, yielding further acceleration after finetuning. Experiments on molecular data as well as binary and RGB images demonstrate the broad applicability and effectiveness of our approach.

With the rapid development of foundation video generation technologies, long video generation models have exhibited promising research potential thanks to expanded content creation space. Recent studies reveal that the goal of long video generation tasks is not only to extend video duration but also to accurately express richer narrative content within longer videos. However, due to the lack of evaluation benchmarks specifically designed for long video generation models, the current assessment of these models primarily relies on benchmarks with simple narrative prompts (e.g., VBench). To the best of our knowledge, our proposed NarrLV is the first benchmark to comprehensively evaluate the Narrative expression capabilities of Long Video generation models. Inspired by film narrative theory, (i) we first introduce the basic narrative unit maintaining continuous visual presentation in videos as Temporal Narrative Atom (TNA), and use its count to quantitatively measure narrative richness. Guided by three key film narrative elements influencing TNA changes, we construct an automatic prompt generation pipeline capable of producing evaluation prompts with a flexibly expandable number of TNAs. (ii) Then, based on the three progressive levels of narrative content expression, we design an effective evaluation metric using the MLLM-based question generation and answering framework. (iii) Finally, we conduct extensive evaluations on existing long video generation models and the foundation generation models that underpin them. Experimental results demonstrate that our metric aligns closely with human judgments. The derived evaluation outcomes reveal the detailed capability boundaries of current video generation models in narrative content expression.

Ultra-long generation by large language models (LLMs) is a widely demanded scenario, yet it remains a significant challenge due to their maximum generation length limit and overall quality degradation as sequence length increases. Previous approaches, exemplified by LongWriter, typically rely on ''teaching'', which involves supervised fine-tuning (SFT) on synthetic long-form outputs. However, this strategy heavily depends on synthetic SFT data, which is difficult and costly to construct, often lacks coherence and consistency, and tends to be overly artificial and structurally monotonous. In this work, we propose an incentivization-based approach that, starting entirely from scratch and without relying on any annotated or synthetic data, leverages reinforcement learning (RL) to foster the emergence of ultra-long, high-quality text generation capabilities in LLMs. We perform RL training starting from a base model, similar to R1-Zero, guiding it to engage in reasoning that facilitates planning and refinement during the writing process. To support this, we employ specialized reward models that steer the LLM towards improved length control, writing quality, and structural formatting. Experimental evaluations show that our LongWriter-Zero model, trained from Qwen2.5-32B, consistently outperforms traditional SFT methods on long-form writing tasks, achieving state-of-the-art results across all metrics on WritingBench and Arena-Write, and even surpassing 100B+ models such as DeepSeek R1 and Qwen3-235B.

Streaming video generation as one fundamental component in interactive world models and neural game engines aims to generate high-quality, low-latency, and temporally coherent long stream videos. However, most existing work suffers from severe error accumulation that often significantly degrades the generated stream videos over long horizons. We design Rolling Forcing, a novel video generation technique that enables streaming long videos with minimal error accumulation. Rolling Forcing comes with three novel designs. First, instead of iteratively sampling individual frames which accelerates error propagation, we design a joint denoising scheme that simultaneously denoises multiple frames with progressively increasing noise levels. This design relaxes the strict causality across adjacent frames, effectively suppressing error growth. Second, we introduce the attention sink mechanism into the long-horizon stream video generation task, which allows the model to keep key–value states of initial frames as a global context anchor and thereby enhances long-term global consistency. Third, we design an efficient training algorithm that enables few-step distillation over largely extended denoising windows. This algorithm operates on non-overlapping windows and mitigates exposure bias conditioned on self-generated histories. Extensive experiments show that Rolling Forcing enables real-time streaming generation of multi-minute videos on a single GPU, with substantially reduced error accumulation.

Reactive dance generation (RDG), the task of generating a dance conditioned on a lead dancer's motion, holds significant promise for enhancing human-robot interaction and immersive digital entertainment. Despite progress in duet synchronization and motion-music alignment, two key challenges remain: generating fine-grained spatial interactions and ensuring long-term temporal coherence. In this work, we introduce $\textbf{ReactDance}$, a diffusion framework that operates on a novel hierarchical latent space to address these spatiotemporal challenges in RDG. First, for fine-grained spatial control and artistic expression, we propose Hierarchical Finite Scalar Quantization ($\textbf{HFSQ}$). This multi-scale motion representation effectively disentangles coarse body posture from high-frequency dynamics, enabling independent and detailed control over both aspects through a layered guidance mechanism. Second, to efficiently generate long sequences with high temporal coherence, we propose Blockwise Local Context ($\textbf{BLC}$), a non-autoregressive sampling strategy. Departing from slow, frame-by-frame generation, BLC partitions the sequence into blocks and synthesizes them in parallel via periodic causal masking and positional encodings. Coherence across these blocks is ensured by a dense sliding-window training approach that enriches the representation with local temporal context. Extensive experiments show that ReactDance substantially outperforms state-of-the-art methods in motion quality, long-term coherence, and sampling efficiency.

Large Language Models (LLMs) achieve impressive performance across many tasks but remain prone to hallucination, especially in long-form generation where redundant retrieved contexts and lengthy reasoning chains amplify factual errors. Recent studies highlight a critical phenomenon: the closer key information appears to the model outputs, the higher the factual accuracy. However, existing retrieval-augmented language models (RALMs) lack effective mechanisms to ensure this proximity — external evidence is injected into reasoning via multi-turn retrieval, but this cannot ensure key information stays close to the outputs. We propose Micro–Macro Retrieval ($M^2R$), a novel retrieve-while-generate framework to fill this gap. At the macro level, $M^2R$ retrieves coarse-grained evidence from external sources; at the micro level, it extracts essential results from a key information repository built during reasoning and reuses them while generating answers. This design directly addresses the key-information–to-output proximity bottleneck, effectively reducing hallucination in long-form tasks. $M^2R$ is trained with a curriculum learning–based reinforcement learning strategy using customized rule-based rewards, enabling stable acquisition of retrieval and grounding skills. Extensive experiments across different benchmarks demonstrate the effectiveness of $M^2R$, especially in lengthy-context settings.

Video generation has advanced rapidly, but current models remain limited to short clips, far from the length and complexity of real-world narratives. Long video generation is thus both important and challenging. Existing approaches either attempt to extend the modeling length of video diffusion models directly or merge short clips via shared frames. However, due to the lack of temporal causality modeling for video data, they achieve only limited extensions, suffer from discontinuous or even contradictory actions, and fail to support flexible and fine-grained temporal control. Thus, we propose Instruct-Video-Continuation (InstructVC), combining Temporal Action Binding for fine-grained temporal control and Causal Video Continuation for natural long-term simulation. Temporal Action Binding decomposes complex long videos by temporal causality into scene descriptions and action sequences with predicted durations, while Causal Video Continuation autoregressively generates coherent video narratives from the text story. We further introduce SteinsGate, an inference-time instance of InstructVC that uses an MLLM for Temporal Action Binding and Video Path Integral to enforce causality between actions, converting a pre-trained TI2V diffusion model into an autoregressive video continuation model. Benchmark results demonstrate the advantages of SteinsGate and InstructVC in achieving accurate temporal control and generating natural, smooth multi-action long videos.

Generative models have gained significant traction in offline reinforcement learning (RL) due to their ability to model complex trajectory distributions. However, existing generation-based approaches still struggle with long-horizon tasks characterized by sparse rewards. Some hierarchical generation methods have been developed to mitigate this issue by decomposing the original problem into shorter-horizon subproblems using one policy and generating detailed actions with another. While effective, these methods often overlook the multi-scale temporal structure inherent in trajectories, resulting in suboptimal performance. To overcome these limitations, we propose MAGE, a Multi-scale Autoregressive GEneration-based offline RL method. MAGE incorporates a condition-guided multi-scale autoencoder to learn hierarchical trajectory representations, along with a multi-scale transformer that autoregressively generates trajectory representations from coarse to fine temporal scales. MAGE effectively captures temporal dependencies of trajectories at multiple resolutions. Additionally, a condition-guided decoder is employed to exert precise control over short-term behaviors. Extensive experiments on five offline RL benchmarks against fifteen baseline algorithms show that MAGE successfully integrates multi-scale trajectory modeling with conditional guidance, generating coherent and controllable trajectories in long-horizon sparse-reward settings.

Long video generation with Diffusion Transformers (DiTs) is bottlenecked by the quadratic scaling of full attention with sequence length. Since attention is highly redundant, outputs are dominated by a small subset of query–key pairs. Existing sparse methods rely on blockwise coarse estimation, whose accuracy–efficiency trade-offs are constrained by block size. This paper introduces Mixture-of-Groups Attention (MoGA), an efficient sparse attention that uses a lightweight, learnable token router to precisely match tokens without blockwise estimation. Through semantic-aware routing, MoGA enables effective long-range interactions. As a kernel-free method, MoGA integrates seamlessly with modern attention stacks, including FlashAttention and sequence parallelism. Building on MoGA, we develop an efficient long video generation model that end-to-end produces minute-level, multi-shot, 480p videos at 24 fps, with a context length of approximately 580k. Comprehensive experiments on various video generation tasks validate the effectiveness of our approach. We provide an anonymous link \url{https://anonymous.4open.science/r/MoGA} to showcase the generated videos.