ICLR 2025 论文列表

We introduce a novel method for generating 360° panoramas from text prompts or images. Our approach leverages recent advances in 3D generation by employing multi-view diffusion models to jointly synthesize the six faces of a cubemap. Unlike previous methods that rely on processing equirectangular projections or autoregressive generation, our method treats each face as a standard perspective image, simplifying the generation process and enabling the use of existing multi-view diffusion models. We demonstrate that these models can be adapted to produce high-quality cubemaps without requiring correspondence-aware attention layers. Our model allows for fine-grained text control, generates high resolution panorama images and generalizes well beyond its training set, whilst achieving state-of-the-art results, both qualitatively and quantitatively.

Generative modeling of crystal data distribution is an important yet challenging task due to the unique periodic physical symmetry of crystals. Diffusion-based methods have shown early promise in modeling crystal distribution. More recently, Bayesian Flow Networks were introduced to aggregate noisy latent variables, resulting in a variance-reduced parameter space that has been shown to be advantageous for modeling Euclidean data distributions with structural constraints (Song, et al.,2023). Inspired by this, we seek to unlock its potential for modeling variables located in non-Euclidean manifolds e.g. those within crystal structures, by overcoming challenging theoretical issues. We introduce CrysBFN, a novel crystal generation method by proposing a periodic Bayesian flow, which essentially differs from the original Gaussian-based BFN by exhibiting non-monotonic entropy dynamics. To successfully realize the concept of periodic Bayesian flow, CrysBFN integrates a new entropy conditioning mechanism and empirically demonstrates its significance compared to time-conditioning. Extensive experiments over both crystal ab initio generation and crystal structure prediction tasks demonstrate the superiority of CrysBFN, which consistently achieves new state-of-the-art on all benchmarks. Surprisingly, we found that CrysBFN enjoys a significant improvement in sampling efficiency, e.g., 200x speedup (10 v.s. 2000 steps network forwards) compared with previous Diffusion-based methods on MP-20 dataset.

The current large auto-regressive models can generate high-quality, high-resolution images, but these models require hundreds or even thousands of steps of next-token prediction during inference, resulting in substantial time consumption. In existing studies, Jacobi decoding, an iterative parallel decoding algorithm, has been used to accelerate the auto-regressive generation and can be executed without training. However, the Jacobi decoding relies on a deterministic criterion to determine the convergence of iterations. Thus, it works for greedy decoding but is incompatible with sampling-based decoding which is crucial for visual quality and diversity in the current auto-regressive text-to-image generation. In this paper, we propose a training-free probabilistic parallel decoding algorithm, Speculative Jacobi Decoding (SJD), to accelerate auto-regressive text-to-image generation. By introducing a probabilistic convergence criterion, our SJD accelerates the inference of auto-regressive text-to-image generation while maintaining the randomness in sampling-based token decoding and allowing the model to generate diverse images. Specifically, SJD facilitates the model to predict multiple tokens at each step and accepts tokens based on the probabilistic criterion, enabling the model to generate images with fewer steps than the conventional next-token-prediction paradigm. We also investigate the token initialization strategies that leverage the spatial locality of visual data to further improve the acceleration ratio under specific scenarios. We conduct experiments for our proposed SJD on multiple auto-regressive text-to-image generation models, showing the effectiveness of model acceleration without sacrificing the visual quality. The code of our work is available here: https://github.com/tyshiwo1/Accelerating-T2I-AR-with-SJD/.

Language plays a vital role in the realm of human motion. Existing methods have largely depended on CLIP text embeddings for motion generation, yet they fall short in effectively aligning language and motion due to CLIP’s pretraining on static image-text pairs. This work introduces LaMP, a novel Language-Motion Pretraining model, which transitions from a language-vision to a more suitable language-motion latent space. It addresses key limitations by generating motion-informative text embeddings, significantly enhancing the relevance and semantics of generated motion sequences. With LaMP, we advance three key tasks: text-to-motion generation, motion-text retrieval, and motion captioning through aligned language-motion representation learning. For generation, LaMP instead of CLIP provides the text condition, and an autoregressive masked prediction is designed to achieve mask modeling without rank collapse in transformers. For retrieval, motion features from LaMP’s motion transformer interact with query tokens to retrieve text features from the text transformer, and vice versa. For captioning, we finetune a large language model with the language-informative motion features to develop a strong motion captioning model. In addition, we introduce the LaMP-BertScore metric to assess the alignment of generated motions with textual descriptions. Extensive experimental results on multiple datasets demonstrate substantial improvements over previous methods across all three tasks. Project page: https://aigc3d.github.io/LaMP

We present CogVideoX, a large-scale text-to-video generation model based on diffusion transformer, which can generate 10-second continuous videos that align seamlessly with text prompts, with a frame rate of 16 fps and resolution of 768 x 1360 pixels. Previous video generation models often struggled with limited motion and short durations. It is especially difficult to generate videos with coherent narratives based on text. We propose several designs to address these issues. First, we introduce a 3D Variational Autoencoder (VAE) to compress videos across spatial and temporal dimensions, enhancing both the compression rate and video fidelity. Second, to improve text-video alignment, we propose an expert transformer with expert adaptive LayerNorm to facilitate the deep fusion between the two modalities. Third, by employing progressive training and multi-resolution frame packing, CogVideoX excels at generating coherent, long-duration videos with diverse shapes and dynamic movements. In addition, we develop an effective pipeline that includes various pre-processing strategies for text and video data. Our innovative video captioning model significantly improves generation quality and semantic alignment. Results show that CogVideoX achieves state-of-the-art performance in both automated benchmarks and human evaluation. We publish the code and model checkpoints of CogVideoX along with our VAE model and video captioning model at https://github.com/THUDM/CogVideo.

Images generated by text-to-image (T2I) models often exhibit visual biases and stereotypes of concepts such as culture and profession. Existing quantitative measures of stereotypes are based on statistical parity that does not align with the sociological definition of stereotypes and, therefore, incorrectly categorizes biases as stereotypes. Instead of oversimplifying stereotypes as biases, we propose a quantitative measure of stereotypes that aligns with its sociological definition. We then propose OASIS to measure the stereotypes in a generated dataset and understand their origins within the T2I model. OASIS includes two scores to measure stereotypes from a generated image dataset: **(M1)** Stereotype Score to measure the distributional violation of stereotypical attributes, and **(M2)** WALS to measure spectral variance in the images along a stereotypical attribute. OASIS also includes two methods to understand the origins of stereotypes in T2I models: **(U1)** StOP to discover attributes that the T2I model internally associates with a given concept, and **(U2)** SPI to quantify the emergence of stereotypical attributes in the latent space of the T2I model during image generation. Despite the considerable progress in image fidelity, using OASIS, we conclude that newer T2I models such as FLUX.1 and SDv3 contain strong stereotypical predispositions about concepts and still generate images with widespread stereotypical attributes. Additionally, the quantity of stereotypes worsens for nationalities with lower Internet footprints.

Contrastive Learning (CL) proves to be effective for learning generalizable user representations in Sequential Recommendation (SR), but it suffers from high computational costs due to its reliance on negative samples. To overcome this limitation, we propose the first Non-Contrastive Learning (NCL) framework for SR, which eliminates computational overhead of identifying and generating negative samples. However, without negative samples, it is challenging to learn uniform representations from only positive samples, which is prone to representation collapse. Furthermore, the alignment of the learned representations may be substantially compromised because existing ad-hoc augmentations can produce positive samples that have inconsistent user preferences. To tackle these challenges, we design a novel preference-preserving profile generation method to produce high-quality positive samples for non-contrastive training. Inspired by differential privacy, our approach creates augmented user profiles that exhibit high diversity while provably retaining consistent user preferences. With larger diversity and consistency of the positive samples, our NCL framework significantly enhances the alignment and uniformity of the learned representations, which contributes to better generalization. The experimental results on various benchmark datasets and model architectures demonstrate the effectiveness of the proposed method. Finally, our investigations reveal that both uniformity and alignment play a vital role in improving generalization for SR. Interestingly, in our data-sparse setting, alignment is usually more important than uniformity.

Recent advances in vision-language models (VLMs) have made significant progress in downstream tasks that require quantitative concepts such as facial age estimation and image quality assessment, enabling VLMs to explore applications like image ranking and retrieval. However, existing studies typically focus on the reasoning based on a single image and heavily depend on text prompting, limiting their ability to learn comprehensive understanding from multiple images. To address this, we propose an effective yet efficient approach that reframes the CLIP model into a learning-to-rank task and introduces a lightweight adapter to augment CLIP for text-guided image ranking. Specifically, our approach incorporates learnable prompts to adapt to new instructions for ranking purposes and an auxiliary branch with ranking-aware attention, leveraging text-conditioned visual differences for additional supervision in image ranking. Our ranking-aware adapter consistently outperforms fine-tuned CLIPs on various tasks and achieves competitive results compared to state-of-the-art models designed for specific tasks like facial age estimation and image quality assessment. Overall, our approach primarily focuses on ranking images with a single instruction, which provides a natural and generalized way of learning from visual differences across images, bypassing the need for extensive text prompts tailored to individual tasks.

Personalizing a large-scale pretrained Text-to-Image (T2I) diffusion model is chal- lenging as it typically struggles to make an appropriate trade-off between its training data distribution and the target distribution, i.e., learning a novel concept with only a few target images to achieve personalization (aligning with the personalized target) while preserving text editability (aligning with diverse text prompts). In this paper, we propose PaRa, an effective and efficient Parameter Rank Reduction approach for T2I model personalization by explicitly controlling the rank of the diffusion model parameters to restrict its initial diverse generation space into a small and well-balanced target space. Our design is motivated by the fact that taming a T2I model toward a novel concept such as a specific art style implies a small generation space. To this end, by reducing the rank of model parameters during finetuning, we can effectively constrain the space of the denoising sampling trajectories towards the target. With comprehensive experiments, we show that PaRa achieves great advantages over existing finetuning approaches on single/multi-subject generation as well as single-image editing. Notably, compared to the prevailing fine-tuning technique LoRA, PaRa achieves better parameter efficiency (2× fewer learnable parameters) and much better target image alignment.

We propose GALA, a novel representation of 3D shapes that (i) excels at capturing and reproducing complex geometry and surface details, (ii) is computationally efficient, and (iii) lends itself to 3D generative modelling with modern, diffusion-based schemes. The key idea of GALA is to exploit both the global sparsity of surfaces within a 3D volume and their local surface properties. *Sparsity* is promoted by covering only the 3D object boundaries, not empty space, with an ensemble of tree root voxels. Each voxel contains an octree to further limit storage and compute to regions that contain surfaces. *Adaptivity* is achieved by fitting one local and geometry-aware coordinate frame in each non-empty leaf node. Adjusting the orientation of the local grid, as well as the anisotropic scales of its axes, to the local surface shape greatly increases the amount of detail that can be stored in a given amount of memory, which in turn allows for quantization without loss of quality. With our optimized C++/CUDA implementation, GALA can be fitted to an object in less than 10 seconds. Moreover, the representation can efficiently be flattened and manipulated with transformer networks. We provide a cascaded generation pipeline capable of generating 3D shapes with great geometric detail. For more information, please visit our [project page](https://santisy.github.io/GALA/).

Recently, 3D assets created via reconstruction and generation have matched the quality of manually crafted assets, highlighting their potential for replacement. However, this potential is largely unrealized because these assets always need to be converted to meshes for 3D industry applications, and the meshes produced by current mesh extraction methods are significantly inferior to Artist-Created Meshes (AMs), i.e., meshes created by human artists. Specifically, current mesh extraction methods rely on dense faces and ignore geometric features, leading to inefficiencies, complicated post-processing, and lower representation quality. To address these issues, we introduce MeshAnything, a model that treats mesh extraction as a generation problem, producing AMs aligned with specified shapes. By converting 3D assets in any 3D representation into AMs, MeshAnything can be integrated with various 3D asset production methods, thereby enhancing their application across the 3D industry. The architecture of MeshAnything comprises a VQ-VAE and a shape-conditioned decoder-only transformer. We first learn a mesh vocabulary using the VQ-VAE, then train the shape-conditioned decoder-only transformer on this vocabulary for shape-conditioned autoregressive mesh generation. Our extensive experiments show that our method generates AMs with hundreds of times fewer faces, significantly improving storage, rendering, and simulation efficiencies, while achieving precision comparable to previous methods.

Diffusion models break down the challenging task of generating data from high-dimensional distributions into a series of easier denoising steps. Inspired by this paradigm, we propose a novel approach that extends the diffusion framework into modality space, decomposing the complex task of RGB image generation into simpler, interpretable stages. Our method, termed {\papernameAbbrev}, cascades modality-specific models, each responsible for generating an intermediate representation, such as contours, palettes, and detailed textures, ultimately culminating in a high-quality RGB image. Instead of relying on the naive LDM concatenation conditioning mechanism to connect the different stages together, we employ Schr\"odinger Bridge to determine the optimal transport between different modalities. Although employing a cascaded pipeline introduces more stages, which could lead to a more complex architecture, each stage is meticulously formulated for efficiency and accuracy, surpassing Stable-Diffusion (LDM) performance. Modality composition not only enhances overall performance but enables emerging proprieties such as consistent editing, interaction capabilities, high-level interpretability, and faster convergence and sampling rate. Extensive experiments on diverse datasets, including LSUN-Churches, ImageNet, CelebHQ, and LAION-Art, demonstrate the efficacy of our approach, consistently outperforming state-of-the-art methods. For instance, {\papernameAbbrev} achieves notable efficiency, matching LDM performance on LSUN-Churches while operating 2$\times$ faster with a 3$\times$ smaller architecture. The project website is available at: \href{https://toddlerdiffusion.github.io/website/}{$https://toddlerdiffusion.github.io/website/$}

Existing image super-resolution (SR) techniques often fail to generalize effectively in complex real-world settings due to the significant divergence between training data and practical scenarios. To address this challenge, previous efforts have either manually simulated intricate physical-based degradations or utilized learning-based techniques, yet these approaches remain inadequate for producing large-scale, realistic, and diverse data simultaneously. In this paper, we introduce a novel Realistic Decoupled Data Generator (RealDGen), an unsupervised learning data generation framework designed for real-world super-resolution. We meticulously develop content and degradation extraction strategies, which are integrated into a novel content-degradation decoupled diffusion model to create realistic low-resolution images from unpaired real LR and HR images. Extensive experiments demonstrate that RealDGen excels in generating large-scale, high-quality paired data that mirrors real-world degradations, significantly advancing the performance of popular SR models on various real-world benchmarks.

Consistent text-to-image generation depicting the *same* subjects across different images has gained significant recent attention due to its widespread applications in the fields of visual-storytelling and multiple-shot video generation. While remarkable, existing methods often require costly finetuning for each subject and struggle to maintain consistency across multiple characters. In this work, we first analyse the reason for these limitations. Our exploration reveals that the primary-issue stems from *self-attention leakage*, which is exacerbated when trying to ensure consistency across multiple-characters. Motivated by these findings, we next propose a simple yet effective *training and optimization-free approach* for improving multiple-character consistency. In particular, we first leverage multi-modal *chain-of-thought* reasoning in order to *apriori* localize the different subjects across the storyboard frames. The final storyboard images are then generated using a modified diffusion model which includes *1) a bounded cross-attention layer* for ensuring adherence to the initially predicted layout, and *2) a bounded cross-frame self-attention layer* for reducing inter-character attention leakage. Furthermore, we also propose a novel *cross-frame token-merging layer* which allows for improved fine-grain consistency for the storyboard characters. Experimental analysis reveals that proposed approach is not only $\times 30$ faster than prior training-based methods (*eg, textual inversion, dreambooth-lora*) but also surpasses the prior *state-of-the-art*, exhibiting improved multi-character consistency and text-to-image alignment performance.

This paper presents a novel approach that enables autoregressive video generation with high efficiency. We propose to reformulate the video generation problem as a non-quantized autoregressive modeling of temporal frame-by-frame prediction and spatial set-by-set prediction. Unlike raster-scan prediction in prior autoregressive models or joint distribution modeling of fixed-length tokens in diffusion models, our approach maintains the causal property of GPT-style models for flexible in-context capabilities, while leveraging bidirectional modeling within individual frames for efficiency. With the proposed approach, we train a novel video autoregressive model without vector quantization, termed NOVA. Our results demonstrate that NOVA surpasses prior autoregressive video models in data efficiency, inference speed, visual fidelity, and video fluency, even with a much smaller model capacity, i.e., 0.6B parameters. NOVA also outperforms state-of-the-art image diffusion models in text-to-image generation tasks, with a significantly lower training cost. Additionally, NOVA generalizes well across extended video durations and enables diverse zero-shot applications in one unified model. Code and models are publicly available at https://github.com/baaivision/NOVA.

Large Language Models (LLMs) exhibit impressive capabilities but require careful alignment with human preferences. Traditional training-time methods finetune LLMs using human preference datasets but incur significant training costs and require repeated training to handle diverse user preferences. Test-time alignment methods address this by using reward models (RMs) to guide frozen LLMs without retraining. However, existing test-time approaches rely on trajectory-level RMs which are designed to evaluate complete responses, making them unsuitable for autoregressive text generation that requires computing next-token rewards from partial responses. To address this, we introduce GenARM, a test-time alignment approach that leverages the Autoregressive Reward Model—a novel reward parametrization designed to predict next-token rewards for efficient and effective autoregressive generation. Theoretically, we demonstrate that this parametrization can provably guide frozen LLMs toward any distribution achievable by traditional RMs within the KL-regularized reinforcement learning framework. Experimental results show that GenARM significantly outperforms prior test-time alignment baselines and matches the performance of training-time methods. Additionally, GenARM enables efficient weak-to-strong guidance, aligning larger LLMs with smaller RMs without the high costs of training larger models. Furthermore, GenARM supports multi-objective alignment, allowing real-time trade-offs between preference dimensions and catering to diverse user preferences without retraining. Our project page is available at: https://genarm.github.io.

LLMs are an integral component of retrieval-augmented generation (RAG) systems. While many studies focus on evaluating the overall quality of end-to-end RAG systems, there is a gap in understanding the appropriateness of LLMs for the RAG task. To address this, we introduce Trust-Score, a holistic metric that evaluates the trustworthiness of LLMs within the RAG framework. Our results show that various prompting methods, such as in-context learning, fail to effectively adapt LLMs to the RAG task as measured by Trust-Score. Consequently, we propose Trust-Align, a method to align LLMs for improved Trust-Score performance. 26 out of 27 models aligned using Trust-Align substantially outperform competitive baselines on ASQA, QAMPARI, and ELI5. Specifically, in LLaMA-3-8b, Trust-Align outperforms FRONT on ASQA (↑12.56), QAMPARI (↑36.04), and ELI5 (↑17.69). Trust-Align also significantly enhances models’ ability to correctly refuse and provide quality citations. We also demonstrate the effectiveness of Trust-Align across different open-weight models, including the LLaMA series (1b to 8b), Qwen-2.5 series (0.5b to 7b), and Phi3.5 (3.8b). We release our code at https://github.com/declare-lab/trust-align.

Exploring suitable solutions to improve performance by increasing the computational cost of inference in visual diffusion models is a highly promising direction. Sufficient prior studies have demonstrated that correctly scaling up computation in the sampling process can successfully lead to improved generation quality, enhanced image editing, and compositional generalization. While there have been rapid advancements in developing inference-heavy algorithms for improved image generation, relatively little work has explored inference scaling laws in video diffusion models (VDMs). Furthermore, existing research shows only minimal performance gains that are perceptible to the naked eye. To address this, we design a novel training-free algorithm IV-Mixed Sampler that leverages the strengths of image diffusion models (IDMs) to assist VDMs surpass their current capabilities. The core of IV-Mixed Sampler is to use IDMs to significantly enhance the quality of each video frame and VDMs ensure the temporal coherence of the video during the sampling process. Our experiments have demonstrated that IV-Mixed Sampler achieves state-of-the-art performance on 4 benchmarks including UCF-101-FVD, MSR-VTT-FVD, Chronomagic-Bench-150/1649, and VBench. For example, the open-source Animatediff with IV-Mixed Sampler reduces the UMT-FVD score from 275.2 to 228.6, closing to 223.1 from the closed-source Pika-2.0.

This paper introduces the counter-intuitive generalization results of overfitting pre-trained large language models (LLMs) on very small datasets. In the setting of open-ended text generation, it is well-documented that LLMs tend to generate repetitive and dull sequences, a phenomenon that is especially apparent when generating using greedy decoding. This issue persists even with state-of-the-art LLMs containing billions of parameters, trained via next-token prediction on large datasets. We find that by further fine-tuning these models to achieve a near-zero training loss on a small set of samples -- a process we refer to as hyperfitting -- the long-sequence generative capabilities are greatly enhanced. Greedy decoding with these Hyperfitted models even outperform Top-P sampling over long-sequences, both in terms of diversity and human preferences. This phenomenon extends to LLMs of various sizes, different domains, and even autoregressive image generation. We further find this phenomena to be distinctly different from that of Grokking and double descent. Surprisingly, our experiments indicate that hyperfitted models rarely fall into repeating sequences they were trained on, and even explicitly blocking these sequences results in high-quality output. All hyperfitted models produce extremely low-entropy predictions, often allocating nearly all probability to a single token.