Forecasting by generating RGB videos is computationally expensive, often physically implausible, and not directly actionable, since it requires translation into decision-making signals. Direct modality forecasting (e.g., predicting future segmentation) produces directly actionable outputs but fails to scale due to the need for labels. Vision Foundation Model (VFM) features offer the best of both worlds: they contain actionable semantic and geometric information that can be easily decoded from the predicted features, while requiring no labels on the downstream task for training. However, almost all existing VFM feature forecasting methods regress future features from fixed number of input frames, with evaluation predominantly on short horizons matching the training setup. We firstly show that existing regression methods struggle with forecasting from partial observations because they average over multiple plausible futures, failing to capture uncertainty in the future given the past. Interestingly, naively replacing deterministic forecasting with generative flow matching does not match the sample quality of the regression model, despite being a mathematically appropriate formulation of the forecasting task. In this work, we explain why this is the case, and we show how to optimally generate foundation model features. Our key insight is that generative modeling of VFM features requires (auto)encoding into a compact latent space suitable for diffusion. We show that this latent space preserves information more effectively than previously used alternatives, such as uncompressed feature diffusion or PCA-based compression, both for forecasting and other applications, such as image generation. Our results suggest that conditional generation of (compressed) VFM features offers a promising and scalable foundation for future scene forecasters.
论文检索
输入标题、作者或关键词，从 9,256 篇学术成果中精准定位
Social Aspects · Safety
Recent advancements in generative AI have led to image editing models capable of producing realistic forgeries that evade traditional image forgery localization methods, as these approaches depend on physical noise absent in synthetic data. To address this challenge, we theoretically demonstrate that the diffusion process inherently suppresses local high-frequency variance, creating a statistical energy gap that is distinguishable from the natural entropy of optical imaging. Guided by this insight, we propose FLAME, a unified framework that utilizes a LAD map to capture these intrinsic anomalies, coupled with a parameter-efficient adapter for the SAM 3 to achieve precise, pixel-level forgery localization. Furthermore, to bridge the lag between forensic benchmarks and evolving generative models, we introduce EditStream, an automated pipeline for continuous, instruction-based training data synthesis. Extensive experiments demonstrate that FLAME establishes a new state-of-the-art, significantly outperforming previous methods on AI-generated forgery datasets while effectively generalizing to unseen generative architectures.
Deep Learning · Generative Models and Autoencoders
Classifier-Free Guidance (CFG) serves as the de facto control mechanism for conditional diffusion, yet high guidance scales notoriously induce oversaturation, texture artifacts, and structural collapse. We attribute this failure to a geometric mismatch: standard CFG performs Euclidean extrapolation in ambient space, inadvertently driving sampling trajectories off the high-density data manifold. To resolve this, we present Manifold-Optimal Guidance (MOG), a framework that reformulates guidance as a local optimal control problem. MOG yields a closed-form, geometry-aware Riemannian update that corrects off-manifold drift without requiring retraining. Leveraging this perspective, we further introduce Auto-MOG, a dynamic energy-balancing schedule that adaptively calibrates guidance strength, effectively eliminating the need for manual hyperparameter tuning. Extensive validation demonstrates that MOG yields superior fidelity and alignment compared to baselines, with virtually no added computational overhead.
Applications · Computer Vision
Generating human videos with realistic and controllable motions is a challenging task. While existing methods can generate visually compelling videos, they lack separate control over four key video elements: foreground subject, background video, human trajectory, and action patterns. In this paper, we propose a decomposed human motion control and video generation framework that explicitly decouples motion from appearance, subject from background, and action from trajectory, enabling flexible mix-and-match composition of these elements. Concretely, we first build a ground-aware 3D world coordinate system and perform motion editing directly in the 3D space. Trajectory control is implemented by unprojecting edited 2D trajectories into 3D with focal-length calibration and coordinate transformation, followed by speed alignment and orientation adjustment; actions are supplied by a motion bank or generated via text-to-motion methods. Then, based on modern text-to-video diffusion transformer models, we inject the subject as tokens for full attention, concatenate the background along the channel dimension, and add motion (trajectory and action) control signals by addition. Such a design opens up the possibility for us to generate realistic videos of anyone doing anything anywhere. Extensive experiments on benchmark datasets and real-world cases demonstrate that our method achieves state-of-the-art performance on both element-wise controllability and overall video quality. **The source codes and project page with video examples are in the supplementary materials**.
Probabilistic Methods · Everything Else
Diffusion language models theoretically allow for efficient parallel generation but are practically hindered by the "factorization barrier": the assumption that simultaneously predicted tokens are independent. This limitation forces a trade-off: models must either sacrifice speed by resolving dependencies sequentially or suffer from incoherence due to factorization. We argue that this barrier arises not from limited backbone expressivity, but from a structural misspecification: models are restricted to fully factorized outputs because explicitly parameterizing a joint distribution would require the Transformer to output a prohibitively large number of parameters. We propose **Co**upled **D**iscrete **D**iffusion (**CoDD**), a hybrid framework that breaks this barrier by replacing the fully-factorized output distribution with a lightweight, tractable probabilistic inference layer. This formulation yields a distribution family that is significantly more expressive than standard factorized priors, enabling the modeling of complex joint dependencies, yet remains compact enough to avoid the prohibitive parameter explosion associated with full joint modeling. Empirically, **CoDD** seamlessly enhances diverse diffusion language model architectures with negligible overhead, matching the reasoning performance of computationally intensive Reinforcement Learning baselines at a fraction of the training cost. Furthermore, it prevents performance collapse in few-step generation, enabling high-quality outputs at significantly reduced latencies.
Social Aspects · Safety
Red-teaming Vision-Language Models is essential for identifying vulnerabilities where adversarial image-text inputs trigger toxic outputs. Existing approaches treat image generation as a black box, providing only terminal toxicity scores while remaining temporally opaque regarding when and how toxic semantics emerge during multi-step synthesis. We introduce $\textbf{STARE}$, a hierarchical reinforcement learning framework that treats the denoising trajectory as an exploitable attack surface. By synergizing a high-level prompt editor with low-level T2I fine-tuning via Group Relative Policy Optimization (GRPO), STARE achieves a 68\% improvement in Attack Success Rate over state-of-the-art baselines including black box and white-box variants. More importantly, we reveal the Optimization-Induced Phase Alignment phenomenon: while vanilla models exhibit diffuse toxicity, adversarial optimization systematically concentrates conceptual harms into early semantic phases and detail-oriented harms into late refinement. This discovery transforms toxicity formation from a chaotic process into a series of predictable vulnerability windows. This temporal alignment transforms red-teaming from a trial-and-error process into a targeted structural analysis. Our work provides both a potent attack engine and a diagnostic foundation for developing next-generation, phase-aware safety mechanisms. Content warning: This paper contains examples of toxic content that may be offensive or disturbing.
Deep Learning · Generative Models and Autoencoders
Can a diffusion model trained on bedrooms recover human faces? Diffusion models are widely used as priors for inverse problems, but standard approaches usually assume a high-fidelity model trained on data that closely match the unknown signal. In practice, one often must use a mismatched or low-fidelity diffusion prior. Surprisingly, these weak priors often perform nearly as well as full-strength, in-domain baselines. We study when and why inverse solvers are robust to weak diffusion priors. Through extensive experiments, we find that weak priors succeed when measurements are highly informative (e.g., many observed pixels), and we identify regimes where they fail. Our theory, based on Bayesian consistency, gives conditions under which high-dimensional measurements make the posterior concentrate near the true signal. These results provide a principled justification on when weak diffusion priors can be used reliably. Code is available at Code is available at https://anonymous.4open.science/r/weak-diffusion-priors-inverse-problem-1043.
Deep Learning · Generative Models and Autoencoders
Diffusion models have achieved remarkable success in graph generation, but enforcing hard constraints on generated graphs remains challenging, limiting their deployment in constraint-critical applications. Existing approaches either fail to guarantee strict constraint satisfaction or are limited to narrow constraint types, lacking the flexibility to handle diverse constraint specifications. To address this challenge, we exploit the discrete structure of graphs, which allows hard constraints to be formulated as symbolic reasoning problems. Building on this insight, we propose NSPSG, a framework that integrates unconstrained diffusion models with discrete projection operators. NSPSG employ an SMT (Satisfiability Modulo Theories)-based projector to ensure that the generated graphs strictly satisfy constraints while remaining within the training data distribution. To further accelerate generation, we employ a supervised auto-regressive neural projector to approximate the symbolic reasoning process. Across heterogeneous constraints and various graph generation datasets, NSPSG achieves 99%-100% validity rates, demonstrating state-of-the-art performance. Notably, for a complex non-linear constraint, it improves data validity by up to 43% and reaches 99% validity while maintaining comparable generation efficiency.
Deep Learning · Other Representation Learning
The natural world is richly structured over space and time. Much of this structure arises from the interplay between spatial geometry and motion. However, most existing world models ignore this structure, leading to an inability to generalize in dynamic environments. In this work, we show that enforcing equivariance between an agent's representations and the world's dynamics necessarily induces an efficient, structured memory. Concretely, we introduce Flow Equivariant World Modeling, a framework in which both self-motion and external object motion are unified as one-parameter Lie-group ``flows'' acting on a latent world memory; and models are built to be equivariant with respect to these transformations. On 2D and 3D partially observed video world modeling benchmarks, we demonstrate that Flow Equivariant World Models significantly outperform comparable state-of-the-art diffusion-based and memory-augmented world modeling architectures in their ability to track and predict the locations of moving objects over long horizons. Project page: https://anonflowm.github.io/
Applications · Computer Vision
One-Step Diffusion Models have demonstrated promising capability and fast inference in real-world Video Super-Resolution (VSR). However, the substantial model size and high computational cost of Diffusion Transformers (DiTs) hinder their practical deployment. While low-bit quantization is a common approach for model compression, the effectiveness of quantized models is challenged by the high dynamic range of input latent and diverse layer behaviors. To address these limitations, we introduce LSGQuant, a layer-sensitivity guided quantization framework for one-step diffusion-based real-world VSR. Our method incorporates a Dynamic Range Adaptive Quantizer (DRAQ) to fit video token activations. Furthermore, we estimate layer sensitivity and implement a Variance-Oriented Layer Training Strategy (VOLTS) by analyzing layer-wise statistics in calibration. We also introduce Quantization-Aware Optimization (QAO) to jointly refine the quantized branch and a retained high-precision branch. Extensive experiments demonstrate that our approach maintains performance comparable to the full-precision model and significantly exceeds existing quantization techniques. All models and code will soon be publicly available.
Social Aspects · Accountability, Transparency, and Interpretability
Large Vision-Language Models (LVLMs) represent a significant leap towards empathetic agents, demonstrating remarkable capabilities in emotion understanding. However, the internal mechanisms governing how LVLMs translate abstract visual stimuli into coherent emotional narratives remain largely unexplored, primarily due to the scarcity of visual counterfactuals and the diffuse nature of emotional expression. In this paper, we bridge this gap by introducing a steering-vector-based causal attribution framework tailored for descriptive emotional reasoning. To this end, we construct a specialized dataset to demystify the emotional circuits underlying the three-stage '' Adapt-Aggregate-Execute'' mechanism. Crucially, we discover a functional decoupling: visual emotional cues are aggregated in middle layers via $\textit{sentiment-specific}$ attention heads, but are subsequently translated into narrative generation in deep layers through $\textit{emotion-general}$ pathways. Guided by these insights, we regulate the emotional information routing to strengthen attention flow and amplify the semantic activation to consolidate expression. Extensive experiments on the comprehensive MER-UniBench demonstrate that our methods significantly improve performance via inference-time intervention, effectively mitigating emotional hallucinations and corroborating the causal fidelity of the discovered circuits.
Social Aspects · Accountability, Transparency, and Interpretability
Existing approaches for manipulating neural network activations, such as PCA and SAEs, rely on strong assumptions about activation structure. We develop a generative approach that models activations with diffusion, that makes minimal assumptions and improves with data and model scale. We use this activation diffusion model to improve downstream tasks: for instance, post-processing interventions with its learned generative prior, allowing for more effective steering without sacrificing fluency. Furthermore, the activation diffusion model can be used as an encoder, with units that cover a broad range of human-interpretable concepts, as measured by scalar probing. We also characterize the scaling properties of our approach, training models with 0.5B to 3.3B parameters on one billion residual stream activations from the Llama model family. We see that the diffusion loss decreases smoothly and reliably as a function of compute, and serves as a good proxy for downstream steering and probing performance. Our method provides a scalable approach towards interpretability without requiring commitments to strong assumptions.
Deep Learning · Generative Models and Autoencoders
Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models, offering sub-linear generation latency and bidirectional capabilities that are particularly appealing for code generation and editing. Achieving sub-linear latency in discrete DLMs requires predicting multiple tokens in parallel. However, standard DLMs sample tokens independently from conditional marginal distributions, failing to capture the joint dependencies among concurrently generated tokens. As a result, they often lead to syntactic inconsistencies and break multi-token structures. In this work, we introduce CoDiLA (Coherent Diffusion with Local Autoregression), a method that reconciles parallel sampling with local dependency modeling. Rather than forcing the DLM to resolve fine-grained syntax, CoDiLA delegates local decoding to a small, auxiliary AR model operating on the diffusion latents. This design allows for parallel block generation while ensuring sequential validity within each block and maintaining core DLM capabilities, including bidirectional modeling across blocks. We demonstrate that using a highly compact auxiliary AR model (e.g., 0.6B parameters) effectively eliminates coherence artifacts, establishing a new Pareto frontier for accuracy and speed in code generation benchmarks.
Social Aspects · Accountability, Transparency, and Interpretability
Most current paradigms in visual mechanistic interpretability (MI) remain confined to interpreting internal units of the vision model via heuristic methods (e.g., top-$K$ activation retrieval or optimization with regularization). In this work, we establish a theoretical distributional view for visual MI, which models the influence of a feature activation on the natural image distribution, thereby formulating a Kullback-Leibler (KL)-minimal optimization problem to model the MI task. Under this framework, statistical biases are identified within previous MI paradigms, which reveal that they may either be perceptually uninterpretable to humans (i.e., deviate from the natural image distribution), or mechanistically unfaithful to the vision models (i.e., unable to activate model features). To resolve the biases under the distributional view, we propose a model with a KL-minimal soft-constraint principle for visual MI that theoretically balances interpretability and faithfulness. We realize this principle via energy-guided diffusion posterior sampling. Extensive experiments validate the theoretical soundness of the proposed distributional view and demonstrate the practical effectiveness of our paradigm on the DINOv3 vision model.
Deep Learning · Large Language Models
Diffusion language models (DLMs) offer substantial speed advantages through parallel decoding, but the lack of token dependencies limits generation quality compared to autoregressive (AR) models. Recent progress attempts to bridge the gap via importance sampling, with DLM being the proposal and AR being the target. However, due to the huge gap between their probability space, the sampling requires a large number of particles and thus expensive computation. In this paper, we introduce PoE-Bridge, a novel decoding framework that drastically improves generation speed and accuracy by introducing an intermediate distribution to bridge the gap. The distribution is constructed as a Product-of-Experts (PoE) of the DLM proposal and the AR target. With the intermediate distribution, we first conduct multi-token sampling with the DLM and then apply rejection sampling using the PoE to retain only the verified tokens. The generated chunks are then evaluated by the AR target via importance sampling to produce the final faithful generation. We further propose several improved techniques, including mixed-temperature sampling for enhanced diversity and elastic rejection windows for reducing wasted verification. Empirically, PoE-Bridge achieves significantly improved accuracy with $5\times$ speedup over the standard DLM decoding approach, and recovering at least 95% of the target AR model's performance, efficiently advancing most of the quality gap on challenging mathematical reasoning and coding tasks.
Deep Learning · Other Representation Learning
Euclidean representations distort data with intrinsic non-Euclidean structure. While Riemannian representation learning offers a solution by embedding data onto matching manifolds, it typically relies on an encoder to estimate densities on chosen manifolds. This involves optimizing numerically brittle objectives, potentially harming model training and quality. To completely circumvent this issue, we introduce the Riemannian generative decoder, a unifying approach for finding manifold-valued latents on any Riemannian manifold. Latents are learned with a Riemannian optimizer while jointly training a decoder network. By discarding the encoder, we vastly simplify the manifold constraint compared to current approaches which often only handle few specific manifolds. We validate our approach on three case studies --- a synthetic branching diffusion process, human migrations inferred from mitochondrial DNA, and cells undergoing a cell division cycle --- each showing that learned representations respect the prescribed geometry and capture intrinsic non-Euclidean structure. Our method requires only a decoder, is compatible with existing architectures, and yields interpretable latent spaces aligned with data geometry.
Deep Learning · Generative Models and Autoencoders
Recent advances in generative models, such as diffusion models, have raised concerns related to privacy, copyright infringement, and data curation. Prior work has shown that training data can be reconstructed from such models, but existing attacks typically rely on substantial computational resources, access to the training set, or carefully engineered prompts. In this work, we present a low-resource reconstruction attack that operates through seemingly benign prompts and requires little to no access to the training data. Our attack targets **template-memorized images (TMI)**, where recurring layouts and visual structures are memorized during training. We show that such memorization manifests under potentially realistic usage. This raises a possibility of unintentional reconstruction by naive users that don't carry explicit adversarial intent. For example, we observe that a simple prompt such as "blue Unisex T-Shirt" can reproduce visual content depicting a real individual. Beyond extraction, we observe novel phenomena occurring in TMI (e.g., interpolation), raising questions about the novelty of generated content and the effectiveness of established methods for detecting memorized content.
Probabilistic Methods · Bayesian Models and Methods
Score-based diffusion models have recently been extended to infinite-dimensional function spaces, with uses such as inverse problems arising from partial differential equations. In the Bayesian formulation of inverse problems, the aim is to sample from a posterior distribution over functions obtained by conditioning a prior on noisy observations. While diffusion models provide expressive priors in function space, the theory of conditioning them to sample from the posterior remains open. We address this, assuming that either the prior lies in the Cameron-Martin space, or is absolutely continuous with respect to a Gaussian measure. We prove that the models can be conditioned using an infinite-dimensional extension of Doob's $h$-transform, and that the conditional score decomposes into an unconditional score and a guidance term. As the guidance term is intractable, we propose a simulation-free score matching objective (called *Supervised Guidance Training*) enabling efficient and stable posterior sampling. We illustrate the theory with numerical examples on Bayesian inverse problems in function spaces. In summary, our work offers the first function-space method for fine-tuning trained diffusion models to accurately sample from a posterior.
Deep Learning · Large Language Models
Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models. Recently, a new paradigm has emerged in the form of diffusion-based Large Language Models (dLLMs), which generate text by iteratively denoising masked segments. This approach has shown significant advantages and potential. However, dLLMs suffer from high inference latency. Traditional ARM acceleration techniques, such as Key-Value caching, are incompatible with dLLMs due to their bidirectional attention mechanism. To address this specific challenge, our work begins with a key observation that dLLM inference involves a static prompt and a partially dynamic response, where most tokens remain stable across adjacent denoising steps. Based on this, we propose dLLM-Cache, a training-free adaptive caching framework that combines long-interval prompt caching with partial response updates guided by feature similarity. This design enables efficient reuse of intermediate computations without compromising model performance. Extensive experiments on representative dLLMs, including LLaDA 8B and Dream 7B, show that dLLM-Cache achieves up to 9.1$\times$ speedup over standard inference without compromising output quality. Notably, our method brings dLLM inference latency close to that of ARMs under many settings. Codes are provided in the supplementary material and will be released publicly on GitHub.
Reinforcement Learning · Deep RL
Masked diffusion large language models (dLLMs) are a promising alternative to autoregressive generation. While reinforcement learning (RL) algorithms have been adapted to be compatible with dLLMs for fine-tuning them, their reliance on the computation of the marginal likelihood to evaluate policy objectives is intractable. To overcome this, we exploit a dynamical relation between the unmasking posterior of the base model and that which targets the reward-tilted distribution to derive Discrete Tilt Matching (DTM), an algorithm that avoids intractable likelihood evaluation entirely. DTM can be phrased as a cross-entropy loss that only requires forward evaluation of rewards and whose variance can be adaptively controlled, improving training stability. We motivate DTM on maze planning tasks, and show that fine-tuning LLaDA-8B-Instruct with DTM achieves higher accuracy at lower compute costs than prior RL-based fine-tuning methods across the Sudoku, Countdown, and MATH500 benchmarks.