Aligning Forest and Trees in Images and Long Captions for Visually Grounded Understanding

Large vision-language models such as CLIP struggle with long captions because they align images and texts as undifferentiated wholes. Fine-grained vision-language understanding requires hierarchical semantics capturing both global context and localized details across visual and textual domains. Yet linguistic hierarchies from syntax or semantics rarely match visual organization, and purely visual hierarchies tend to fragment scenes into appearance-driven parts without semantic focus. We propose CAFT (Cross-domain Alignment of Forests and Trees), a hierarchical image-text representation learning framework that aligns global and local semantics across images and long captions without pixel-level supervision. Coupling a fine-to-coarse visual encoder with a hierarchical text transformer, it uses a hierarchical alignment loss that matches whole images with whole captions while biasing region-sentence correspondences, so that coarse semantics are built from fine-grained evidence rather than from aggregation untethered to part-level grounding. Trained on 30M image-text pairs, CAFT achieves state-of-the-art performance on six long-text retrieval benchmarks and exhibits strong scaling behavior. Experiments show that hierarchical cross-domain alignment enables fine-grained, visually grounded image-text representations to emerge without explicit region-level supervision.

Know Your Step: Faster and Better Alignment for Flow Matching Models via Step-aware Advantages

Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in few step text to image generators. However, existing RL based approaches for flow matching models typically rely on numerous denoising steps, while suffering from sparse and imprecise reward signals that often lead to suboptimal alignment. To address these limitations, we propose Temperature Annealed Few step Sampling with Group Relative Policy Optimization (TAFS GRPO), a novel framework for training flow matching text to image models into efficient few step generators well aligned with human preferences. Our method iteratively injects adaptive temporal noise onto the results of one step samples. By repeatedly annealing the model's sampled outputs, it introduces stochasticity into the sampling process while preserving the semantic integrity of each generated image. Moreover, its step aware advantage integration mechanism combines the GRPO to avoid the need for the differentiable of reward function and provide dense and step specific rewards for stable policy optimization. Extensive experiments demonstrate that TAFS GRPO achieves strong performance in few step text to image generation and significantly improves the alignment of generated images with human preferences. The code and models of this work will be available to facilitate further research.

Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers

Recent DiT-based text-to-image models increasingly adopt LLMs as text encoders, yet text conditioning remains largely static and often utilizes only a single LLM layer, despite pronounced semantic hierarchy across LLM layers and non-stationary denoising dynamics over both diffusion time and network depth. To better match the dynamic process of DiT generation and thereby enhance the diffusion model's generative capability, we introduce a unified normalized convex fusion framework equipped with lightweight gates to systematically organize multi-layer LLM hidden states via time-wise, depth-wise, and joint fusion. Experiments establish Depth-wise Semantic Routing as the superior conditioning strategy, consistently improving text-image alignment and compositional generation (e.g., +9.97 on the GenAI-Bench Counting task). Conversely, we find that purely time-wise fusion can paradoxically degrade visual generation fidelity. We attribute this to a train-inference trajectory mismatch: under classifier-free guidance, nominal timesteps fail to track the effective SNR, causing semantically mistimed feature injection during inference. Overall, our results position depth-wise routing as a strong and effective baseline and highlight the critical need for trajectory-aware signals to enable robust time-dependent conditioning.

Hierarchical Concept-to-Appearance Guidance for Multi-Subject Image Generation

Multi-subject image generation aims to synthesize images that faithfully preserve the identities of multiple reference subjects while following textual instructions. However, existing methods often suffer from identity inconsistency and limited compositional control, as they rely on diffusion models to implicitly associate text prompts with reference images. In this work, we propose Hierarchical Concept-to-Appearance Guidance (CAG), a framework that provides explicit, structured supervision from high-level concepts to fine-grained appearances. At the conceptual level, we introduce a VAE dropout training strategy that randomly omits reference VAE features, encouraging the model to rely more on robust semantic signals from a Visual Language Model (VLM) and thereby promoting consistent concept-level generation in the absence of complete appearance cues. At the appearance level, we integrate the VLM-derived correspondences into a correspondence-aware masked attention module within the Diffusion Transformer (DiT). This module restricts each text token to attend only to its matched reference regions, ensuring precise attribute binding and reliable multi-subject composition. Extensive experiments demonstrate that our method achieves state-of-the-art performance on the multi-subject image generation, substantially improving prompt following and subject consistency.

Test-Time Conditioning with Representation-Aligned Visual Features

While representation alignment with self-supervised models has been shown to improve diffusion model training, its potential for enhancing inference-time conditioning remains largely unexplored. We introduce Representation-Aligned Guidance (REPA-G), a framework that leverages these aligned representations, with rich semantic properties, to enable test-time conditioning from features in generation. By optimizing a similarity objective (the potential) at inference, we steer the denoising process toward a conditioned representation extracted from a pre-trained feature extractor. Our method provides versatile control at multiple scales, ranging from fine-grained texture matching via single patches to broad semantic guidance using global image feature tokens. We further extend this to multi-concept composition, allowing for the faithful combination of distinct concepts. REPA-G operates entirely at inference time, offering a flexible and precise alternative to often ambiguous text prompts or coarse class labels. We theoretically justify how this guidance enables sampling from the potential-induced tilted distribution. Quantitative results on ImageNet and COCO demonstrate that our approach achieves high-quality, diverse generations. Code is available at https://github.com/valeoai/REPA-G.

ObjEmbed: Towards Universal Multimodal Object Embeddings

Aligning objects with corresponding textual descriptions is a fundamental challenge and a realistic requirement in vision-language understanding. While recent multimodal embedding models excel at global image-text alignment, they often struggle with fine-grained alignment between image regions and specific phrases. In this work, we present ObjEmbed, a novel MLLM embedding model that decomposes the input image into multiple regional embeddings, each corresponding to an individual object, along with global embeddings. It supports a wide range of visual understanding tasks like visual grounding, local image retrieval, and global image retrieval. ObjEmbed enjoys three key properties: (1) Object-Oriented Representation: It captures both semantic and spatial aspects of objects by generating two complementary embeddings for each region: an object embedding for semantic matching and an IoU embedding that predicts localization quality. The final object matching score combines semantic similarity with the predicted IoU, enabling more accurate retrieval. (2) Versatility: It seamlessly handles both region-level and image-level tasks. (3) Efficient Encoding: All objects in an image, along with the full image, are encoded in a single forward pass for high efficiency. Superior performance on 18 diverse benchmarks demonstrates its strong semantic discrimination.

Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have advanced VQA and now support Vision-DeepResearch systems that use search engines for complex visual-textual fact-finding. However, evaluating these visual and textual search abilities is still difficult, and existing benchmarks have two major limitations. First, existing benchmarks are not visual search-centric: answers that should require visual search are often leaked through cross-textual cues in the text questions or can be inferred from the prior world knowledge in current MLLMs. Second, overly idealized evaluation scenario: On the image-search side, the required information can often be obtained via near-exact matching against the full image, while the text-search side is overly direct and insufficiently challenging. To address these issues, we construct the Vision-DeepResearch benchmark (VDR-Bench) comprising 2,000 VQA instances. All questions are created via a careful, multi-stage curation pipeline and rigorous expert review, designed to assess the behavior of Vision-DeepResearch systems under realistic real-world conditions. Moreover, to address the insufficient visual retrieval capabilities of current MLLMs, we propose a simple multi-round cropped-search workflow. This strategy is shown to effectively improve model performance in realistic visual retrieval scenarios. Overall, our results provide practical guidance for the design of future multimodal deep-research systems. The code will be released in https://github.com/Osilly/Vision-DeepResearch.

Generating a Paracosm for Training-Free Zero-Shot Composed Image Retrieval

Composed Image Retrieval (CIR) is the task of retrieving a target image from a database using a multimodal query, which consists of a reference image and a modification text. The text specifies how to alter the reference image to form a ``mental image'', based on which CIR should find the target image in the database. The fundamental challenge of CIR is that this ``mental image'' is not physically available and is only implicitly defined by the query. The contemporary literature pursues zero-shot methods and uses a Large Multimodal Model (LMM) to generate a textual description for a given multimodal query, and then employs a Vision-Language Model (VLM) for textual-visual matching to search the target image. In contrast, we address CIR from first principles by directly generating the ``mental image'' for more accurate matching. Particularly, we prompt an LMM to generate a ``mental image'' for a given multimodal query and propose to use this ``mental image'' to search for the target image. As the ``mental image'' has a synthetic-to-real domain gap with real images, we also generate a synthetic counterpart for each real image in the database to facilitate matching. In this sense, our method uses LMM to construct a ``paracosm'', where it matches the multimodal query and database images. Hence, we call this method Paracosm. Notably, Paracosm is a training-free zero-shot CIR method. It significantly outperforms existing zero-shot methods on four challenging benchmarks, achieving state-of-the-art performance for zero-shot CIR.

Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis

Distribution matching distillation (DMD) aligns a multi-step generator with its few-step counterpart to enable high-quality generation under low inference cost. However, DMD tends to suffer from mode collapse, as its reverse-KL formulation inherently encourages mode-seeking behavior, for which existing remedies typically rely on perceptual or adversarial regularization, thereby incurring substantial computational overhead and training instability. In this work, we propose a role-separated distillation framework that explicitly disentangles the roles of distilled steps: the first step is dedicated to preserving sample diversity via a target-prediction (e.g., v-prediction) objective, while subsequent steps focus on quality refinement under the standard DMD loss, with gradients from the DMD objective blocked at the first step. We term this approach Diversity-Preserved DMD (DP-DMD), which, despite its simplicity -- no perceptual backbone, no discriminator, no auxiliary networks, and no additional ground-truth images -- preserves sample diversity while maintaining visual quality on par with state-of-the-art methods in extensive text-to-image experiments.

Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models

Text-to-image diffusion models have demonstrated remarkable capabilities in generating high-quality images, yet their tendency to reproduce undesirable concepts, such as NSFW content, copyrighted styles, or specific objects, poses growing concerns for safe and controllable deployment. While existing concept erasure approaches primarily focus on DDPM-based diffusion models and rely on costly fine-tuning, the recent emergence of flow matching models introduces a fundamentally different generative paradigm for which prior methods are not directly applicable. In this paper, we propose Differential Vector Erasure (DVE), a training-free concept erasure method specifically designed for flow matching models. Our key insight is that semantic concepts are implicitly encoded in the directional structure of the velocity field governing the generative flow. Leveraging this observation, we construct a differential vector field that characterizes the directional discrepancy between a target concept and a carefully chosen anchor concept. During inference, DVE selectively removes concept-specific components by projecting the velocity field onto the differential direction, enabling precise concept suppression without affecting irrelevant semantics. Extensive experiments on FLUX demonstrate that DVE consistently outperforms existing baselines on a wide range of concept erasure tasks, including NSFW suppression, artistic style removal, and object erasure, while preserving image quality and diversity.