ICLR 2025 Papers

The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), which demonstrate exceptional performance in learning complex associations between images and text. Despite these advancements, ensuring the interpretability of such models is paramount for their safe deployment in real-world applications, such as healthcare. While numerous interpretability methods have been developed for unimodal tasks, these approaches often fail to transfer effectively to multimodal contexts due to inherent differences in the representation structures. Bottleneck methods, well-established in information theory, have been applied to enhance CLIP's interpretability. However, they are often hindered by strong assumptions or intrinsic randomness. To overcome these challenges, we propose the Narrowing Information Bottleneck Theory, a novel framework that fundamentally redefines the traditional bottleneck approach. This theory is specifically designed to satisfy contemporary attribution axioms, providing a more robust and reliable solution for improving the interpretability of multimodal models. In our experiments, compared to state-of-the-art methods, our approach enhances image interpretability by an average of 9\%, text interpretability by an average of 58.83\%, and accelerates processing speed by 63.95\%. Our code is publicly accessible at https://github.com/LMBTough/NIB.

Text-to-motion generation has significant potential in a wide range of applications including animation, robotics, and AR/VR. While recent works on masked motion models are promising, the task remains challenging due to the inherent ambiguity in text and the complexity of human motion dynamics. To overcome the issues, we propose a novel text-to-motion generation framework that integrates two key components: Hard Token Mining (HTM) and a Hierarchical Generative Masked Motion Model (HGM³). Our HTM identifies and masks challenging regions in motion sequences and directs the model to focus on hard-to-learn components for efficacy. Concurrently, the hierarchical model uses a semantic graph to represent sentences at different granularity, allowing the model to learn contextually feasible motions. By leveraging a shared-weight masked motion model, it reconstructs the same sequence under different conditioning levels and facilitates comprehensive learning of complex motion patterns. During inference, the model progressively generates motions by incrementally building up coarse-to-fine details. Extensive experiments on benchmark datasets, including HumanML3D and KIT-ML, demonstrate that our method outperforms existing methods in both qualitative and quantitative measures for generating context-aware motions.

Interleaved multimodal comprehension and generation, enabling models to produce and interpret both images and text in arbitrary sequences, have become a pivotal area in multimodal learning. Despite significant advancements, the evaluation of this capability remains insufficient. Existing benchmarks suffer from limitations in data scale, scope, and evaluation depth, while current evaluation metrics are often costly or biased, lacking in reliability for practical applications. To address these challenges, we introduce MMIE, a large-scale knowledge-intensive benchmark for evaluating interleaved multimodal comprehension and generation in Large Vision-Language Models (LVLMs). MMIE comprises 20K meticulously curated multimodal queries, spanning 3 categories, 12 fields, and 102 subfields, including mathematics, coding, physics, literature, health, and arts. It supports both interleaved inputs and outputs, offering a mix of multiple-choice and open-ended question formats to evaluate diverse competencies. Moreover, we propose a reliable automated evaluation metric, leveraging a scoring model fine-tuned with human-annotated data and systematic evaluation criteria, aimed at reducing bias and improving evaluation accuracy. Extensive experiments demonstrate the effectiveness of our benchmark and metrics in providing a comprehensive evaluation of interleaved LVLMs. Specifically, we evaluate eight LVLMs, revealing that even the best models show significant room for improvement, with most achieving only moderate results. We believe MMIE will drive further advancements in the development of interleaved LVLMs.

Large language models (LLMs) can suffer from hallucinations when generating text. These hallucinations impede various applications in society and industry by making LLMs untrustworthy. Current LLMs generate text in an autoregressive fashion by predicting and appending text tokens. When an LLM is uncertain about the semantic meaning of the next tokens to generate, it is likely to start hallucinating. Thus, it has been suggested that predictive uncertainty is one of the main causes of hallucinations. We introduce Semantically Diverse Language Generation (SDLG) to quantify predictive uncertainty in LLMs. SDLG steers the LLM to generate semantically diverse yet likely alternatives for an initially generated text. This approach provides a precise measure of aleatoric semantic uncertainty, detecting whether the initial text is likely to be hallucinated. Experiments on question-answering tasks demonstrate that SDLG consistently outperforms existing methods while being the most computationally efficient, setting a new standard for uncertainty estimation in LLMs.

Diffusion-based text-to-image generation models trained on extensive text-image pairs have demonstrated the ability to produce photorealistic images aligned with textual descriptions. However, a significant limitation of these models is their slow sample generation process, which requires iterative refinement through the same network. To overcome this, we introduce a data-free guided distillation method that enables the efficient distillation of pretrained Stable Diffusion models without access to the real training data, often restricted due to legal, privacy, or cost concerns. This method enhances Score identity Distillation (SiD) with Long and Short Classifier-Free Guidance (LSG), an innovative strategy that applies Classifier-Free Guidance (CFG) not only to the evaluation of the pretrained diffusion model but also to the training and evaluation of the fake score network. We optimize a model-based explicit score matching loss using a score-identity-based approximation alongside our proposed guidance strategies for practical computation. By exclusively training with synthetic images generated by its one-step generator, our data-free distillation method rapidly improves FID and CLIP scores, achieving state-of-the-art FID performance while maintaining a competitive CLIP score. Notably, the one-step distillation of Stable Diffusion 1.5 achieves an FID of **8.15** on the COCO-2014 validation set, a record low value under the data-free setting. Our code and checkpoints are available at https://github.com/mingyuanzhou/SiD-LSG.

Using the latent diffusion model has proven effective in developing novel 3D generation techniques. To harness the latent diffusion model, a key challenge is designing a high-fidelity and efficient representation that links the latent space and the 3D space. In this paper, we introduce Atlas Gaussians, a novel representation for feed-forward native 3D generation. Atlas Gaussians represent a shape as the union of local patches, and each patch can decode 3D Gaussians. We parameterize a patch as a sequence of feature vectors and design a learnable function to decode 3D Gaussians from the feature vectors. In this process, we incorporate UV-based sampling, enabling the generation of a sufficiently large, and theoretically infinite, number of 3D Gaussian points. The large amount of 3D Gaussians enables the generation of high-quality details. Moreover, due to local awareness of the representation, the transformer-based decoding procedure operates on a patch level, ensuring efficiency. We train a variational autoencoder to learn the Atlas Gaussians representation, and then apply a latent diffusion model on its latent space for learning 3D Generation. Experiments show that our approach outperforms the prior arts of feed-forward native 3D generation. Project page: https://yanghtr.github.io/projects/atlas_gaussians.

This paper aims to manipulate multi-entity 3D motions in video generation. Previous methods on controllable video generation primarily leverage 2D control signals to manipulate object motions and have achieved remarkable synthesis results. However, 2D control signals are inherently limited in expressing the 3D nature of object motions. To overcome this problem, we introduce 3DTrajMaster, a robust controller that regulates multi-entity dynamics in 3D space, given user-desired 6DoF pose (location and rotation) sequences of entities. At the core of our approach is a plug-and-play 3D-motion grounded object injector that fuses multiple input entities with their respective 3D trajectories through a gated self-attention mechanism. In addition, we exploit an injector architecture to preserve the video diffusion prior, which is crucial for generalization ability. To mitigate video quality degradation, we introduce a domain adaptor during training and employ an annealed sampling strategy during inference. To address the lack of suitable training data, we construct a 360-Motion Dataset, which first correlates collected 3D human and animal assets with GPT-generated trajectory and then captures their motion with 12 evenly-surround cameras on diverse 3D UE platforms. Extensive experiments show that 3DTrajMaster sets a new state-of-the-art in both accuracy and generalization for controlling multi-entity 3D motions. Project page: http://fuxiao0719.github.io/projects/3dtrajmaster

Generating high-quality 3D objects from textual descriptions remains a challenging problem due to high computational costs, the scarcity of 3D data, and the complexity of 3D representations. We introduce Geometry Image Diffusion (GIMDiffusion), a novel Text-to-3D model that utilizes geometry images to efficiently represent 3D shapes using 2D images, thereby avoiding the need for complex 3D-aware architectures. By integrating a Collaborative Control mechanism, we exploit the rich 2D priors of existing Text-to-Image models, such as Stable Diffusion, to achieve strong generalization despite limited 3D training data. This allows us to use only high-quality training data while retaining compatibility with guidance techniques such as IPAdapter. GIMDiffusion enables the generation of 3D assets at speeds comparable to current Text-to-Image models, without being restricted to manifold meshes during either training or inference. We simultaneously generate a UV unwrapping for the objects, consisting of semantically meaningful parts as well as internal structures, enhancing both usability and versatility.

This paper presents the first-ever study of adapting compressed image latents to suit the needs of downstream vision tasks that adopt Multimodal Large Language Models (MLLMs). MLLMs have extended the success of large language models to modalities (e.g. images) beyond text, but their billion scale hinders deployment on resource-constrained end devices. While cloud-hosted MLLMs could be available, transmitting raw, uncompressed images captured by end devices to the cloud requires an efficient image compression system. To address this, we focus on emerging neural image compression and propose a novel framework with a lightweight transform-neck and a surrogate loss to adapt compressed image latents for MLLM-based vision tasks. Given the huge scale of MLLMs, our framework excludes the entire downstream MLLM except part of its visual encoder from training our system. This stands out from most existing coding for machine approaches that involve downstream networks in training and thus could be impractical when the networks are MLLMs. The proposed framework is general in that it is applicable to various MLLMs, neural image codecs, and multiple application scenarios, where the neural image codec can be (1) pre-trained for human perception without updating, (2) fully updated for joint human and machine perception, or (3) fully updated for only machine perception. Extensive experiments on different neural image codecs and various MLLMs show that our method achieves great rate-accuracy performance with much less complexity.

Existing Video Scene Graph Generation (VidSGG) studies are trained in a fully supervised manner, which requires all frames in a video to be annotated, thereby incurring high annotation cost compared to Image Scene Graph Generation (ImgSGG). Although the annotation cost of VidSGG can be alleviated by adopting a weakly supervised approach commonly used for ImgSGG (WS-ImgSGG) that uses image captions, there are two key reasons that hinder such a naive adoption: 1) Temporality within video captions, i.e., unlike image captions, video captions include temporal markers (e.g., before, while, then, after) that indicate time-related details, and 2) Variability in action duration, i.e., unlike human actions in image captions, human actions in video captions unfold over varying duration. To address these issues, we propose a Natural Language-based Video Scene Graph Generation (NL-VSGG) framework that only utilizes the readily available video captions for training a VidSGG model. NL-VSGG consists of two key modules: Temporality-aware Caption Segmentation (TCS) module and Action Duration Variability-aware caption-frame alignment (ADV) module. Specifically, TCS segments the video captions into multiple sentences in a temporal order based on a Large Language Model (LLM), and ADV aligns each segmented sentence with appropriate frames considering the variability in action duration. Our approach leads to a significant enhancement in performance compared to simply applying the WS-ImgSGG pipeline to VidSGG on the Action Genome dataset. As a further benefit of utilizing the video captions as weak supervision, we show that the VidSGG model trained by NL-VSGG is able to predict a broader range of action classes that are not included in the training data, which makes our framework practical in reality.

We present Meissonic, which elevates non-autoregressive text-to-image Masked Image Modeling (MIM) to a level comparable with state-of-the-art diffusion models like SDXL. By incorporating a comprehensive suite of architectural innovations, advanced positional encoding strategies, and optimized sampling conditions, Meissonic substantially improves MIM's performance and efficiency. Additionally, we leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers to further enhance image fidelity and resolution. Our model not only matches but often exceeds the performance of existing methods in generating high-quality, high-resolution images. Extensive experiments validate Meissonic’s capabilities, demonstrating its potential as a new standard in text-to-image synthesis.

Compositional reasoning in Vision-Language Models (VLMs) remains challenging as these models often struggle to relate objects, attributes, and spatial relationships. Recent methods aim to address these limitations by relying on the semantics of the textual description, using Large Language Models (LLMs) to break them down into subsets of questions and answers. However, these methods primarily operate on the surface level, failing to incorporate deeper lexical understanding while introducing incorrect assumptions generated by the LLM. In response to these issues, we present Caption Expansion with Contradictions and Entailments (CECE), a principled approach that leverages Natural Language Inference (NLI) to generate entailments and contradictions from a given premise. CECE produces lexically diverse sentences while maintaining their core meaning. Through extensive experiments, we show that CECE enhances interpretability and reduces overreliance on biased or superficial features. By balancing CECE along the original premise, we achieve significant improvements over previous methods without requiring additional fine-tuning, producing state-of-the-art results on benchmarks that score agreement with human judgments for image-text alignment, and achieving an increase in performance on Winoground of $+19.2\%$ (group score) and $+12.9\%$ on EqBen (group score) over the best prior work (finetuned with targeted data).

Recent advancements in human motion synthesis have focused on specific types of motions, such as human-scene interaction, locomotion or human-human interaction, however, there is a lack of a unified system capable of generating a diverse combination of motion types. In response, we introduce *Sitcom-Crafter*, a comprehensive and extendable system for human motion generation in 3D space, which can be guided by extensive plot contexts to enhance workflow efficiency for anime and game designers. The system is comprised of eight modules, three of which are dedicated to motion generation, while the remaining five are augmentation modules that ensure consistent fusion of motion sequences and system functionality. Central to the generation modules is our novel 3D scene-aware human-human interaction module, which addresses collision issues by synthesizing implicit 3D Signed Distance Function (SDF) points around motion spaces, thereby minimizing human-scene collisions without additional data collection costs. Complementing this, our locomotion and human-scene interaction modules leverage existing methods to enrich the system's motion generation capabilities. Augmentation modules encompass plot comprehension for command generation, motion synchronization for seamless integration of different motion types, hand pose retrieval to enhance motion realism, motion collision revision to prevent human collisions, and 3D retargeting to ensure visual fidelity. Experimental evaluations validate the system's ability to generate high-quality, diverse, and physically realistic motions, underscoring its potential for advancing creative workflows. Code and demonstration videos can be found in the supplementary files.

Discrete diffusion models have recently shown significant progress in modeling complex data, such as natural languages and DNA sequences. However, unlike diffusion models for continuous data, which can generate high-quality samples in just a few denoising steps, modern discrete diffusion models still require hundreds or even thousands of denoising steps to perform well. In this paper, we identify a fundamental limitation that prevents discrete diffusion models from achieving strong performance with fewer steps -- they fail to capture dependencies between output variables at each denoising step. To address this issue, we provide a formal explanation and introduce a general approach to supplement the missing dependency information by incorporating another deep generative model, termed the copula model. Our method does not require fine-tuning either the diffusion model or the copula model, yet it enables high-quality sample generation with significantly fewer denoising steps. When we apply this approach to autoregressive copula models, the combined model outperforms both models individually in unconditional and conditional text generation. Specifically, the hybrid model achieves better (un)conditional text generation using 8 to 32 times fewer denoising steps than the diffusion model alone. In addition to presenting an effective discrete diffusion generation algorithm, this paper emphasizes the importance of modeling inter-variable dependencies in discrete diffusion.

Large Language Models (LLMs) generate text by sampling the next token from a probability distribution over the vocabulary at each decoding step. Popular sampling methods like top-p (nucleus sampling) often struggle to balance quality and diversity, especially at higher temperatures which lead to incoherent or repetitive outputs. We propose min-p sampling, a dynamic truncation method that adjusts the sampling threshold based on the model's confidence by using the top token's probability as a scaling factor. Our experiments on benchmarks including GPQA, GSM8K, and AlpacaEval Creative Writing show that min-p sampling improves both the quality and diversity of generated text across different model families (Mistral and Llama 3) and model sizes (1B to 123B parameters), especially at higher temperatures. Human evaluations further show a clear preference for min-p sampling, in both text quality and creativity. Min-p sampling has been adopted by popular open-source LLM frameworks, including Hugging Face Transformers, VLLM, and many others, highlighting its considerable impact on improving text generation quality.

Visual instructions for long-horizon tasks are crucial as they intuitively clarify complex concepts and enhance retention across extended steps. Directly generating a series of images using text-to-image models without considering the context of previous steps results in inconsistent images, increasing cognitive load. Additionally, the generated images often miss objects or the attributes such as color, shape, and state of the objects are inaccurate. To address these challenges, we propose LIGER, the first training-free framework for Long-horizon Instruction GEneration with logic and attribute self-Reflection. LIGER first generates a draft image for each step with the historical prompt and visual memory of previous steps. This step-by-step generation approach maintains consistency between images in long-horizon tasks. Moreover, LIGER utilizes various image editing tools to rectify errors including wrong attributes, logic errors, object redundancy, and identity inconsistency in the draft images. Through this self-reflection mechanism, LIGER improves the logic and object attribute correctness of the images. To verify whether the generated images assist human understanding, we manually curated a new benchmark consisting of various long-horizon tasks. Human-annotated ground truth expressions reflect the human-defined criteria for how an image should appear to be illustrative. Experiments demonstrate the visual instructions generated by LIGER are more comprehensive compared with baseline methods. The code and dataset will be available once accepted.

Sora unveils the potential of scaling Diffusion Transformer (DiT) for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details. In this paper, we introduce the Lumina-T2X family -- a series of Flow-based Large Diffusion Transformers (Flag-DiT) equipped with zero-initialized attention, as a simple and scalable generative framework that can be adapted to various modalities, e.g., transforming noise into images, videos, multi-view 3D objects, or audio clips conditioned on text instructions. By tokenizing the latent spatial-temporal space and incorporating learnable placeholders such as |[nextline]| and |[nextframe]| tokens, Lumina-T2X seamlessly unifies the representations of different modalities across various spatial-temporal resolutions. Advanced techniques like RoPE, KQ-Norm, and flow matching enhance the stability, flexibility, and scalability of Flag-DiT, enabling models of Lumina-T2X to scale up to 7 billion parameters and extend the context window to 128K tokens. This is particularly beneficial for creating ultra-high-definition images with our Lumina-T2I model and long 720p videos with our Lumina-T2V model. Remarkably, Lumina-T2I, powered by a 5-billion-parameter Flag-DiT, requires only 35% of the training computational costs of a 600-million-parameter naive DiT (PixArt-alpha), indicating that increasing the number of parameters significantly accelerates convergence of generative models without compromising visual quality. Our further comprehensive analysis underscores Lumina-T2X's preliminary capability in resolution extrapolation, high-resolution editing, generating consistent 3D views, and synthesizing videos with seamless transitions. All code and checkpoints of Lumina-T2X are released at https://github.com/Alpha-VLLM/Lumina-T2X to further foster creativity, transparency, and diversity in the generative AI community.

Diffusion transformers have demonstrated remarkable performance in visual generation tasks, such as generating realistic images or videos based on textual instructions. However, larger model sizes and multi-frame processing for video generation lead to increased computational and memory costs, posing challenges for practical deployment on edge devices. Post-Training Quantization (PTQ) is an effective method for reducing memory costs and computational complexity. When quantizing diffusion transformers, we find that existing quantization methods face challenges when applied to text-to-image and video tasks. To address these challenges, we begin by systematically analyzing the source of quantization error and conclude with the unique challenges posed by DiT quantization. Accordingly, we design an improved quantization scheme: ViDiT-Q (**V**ideo \& **I**mage **Di**ffusion **T**ransformer **Q**uantization), tailored specifically for DiT models. We validate the effectiveness of ViDiT-Q across a variety of text-to-image and video models, achieving W8A8 and W4A8 with negligible degradation in visual quality and metrics. Additionally, we implement efficient GPU kernels to achieve practical 2-2.5x memory optimization and a 1.4-1.7x end-to-end latency speedup.

While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding tasks. For this reason, self-supervised image-only pretraining is still the go-to method for many dense vision applications (e.g. depth estimation, semantic segmentation), despite the lack of explicit supervisory signals. In this paper, we close this gap between image-text and self-supervised learning, by proposing a novel general-purpose image-text model, which can be effectively used off the shelf for dense and global vision tasks. Our method, which we refer to as Text-Image Pretraining with Spatial awareness (TIPS), leverages two simple and effective insights. First, on textual supervision: we reveal that replacing noisy web image captions by synthetically generated textual descriptions boosts dense understanding performance significantly, due to a much richer signal for learning spatially aware representations. We propose an adapted training method that combines noisy and synthetic captions, resulting in improvements across both dense and global understanding tasks. Second, on the learning technique: we propose to combine contrastive image-text learning with self-supervised masked image modeling, to encourage spatial coherence, unlocking substantial enhancements for downstream applications. Building on these two ideas, we scale our model using the transformer architecture, trained on a curated set of public images. Our experiments are conducted on $8$ tasks involving $16$ datasets in total, demonstrating strong off-the-shelf performance on both dense and global understanding, for several image-only and image-text tasks. Code and models are released at https://github.com/google-deepmind/tips .