Multimodal large language models (MLLMs) achieve strong performance across diverse tasks but remain prone to hallucinations, where outputs are not grounded in visual inputs. This issue can be attributed to two main biases: text-visual bias, the overreliance on prompts and prior outputs, and co-occurrence bias, spurious correlations between frequently paired objects. We propose Gradient-based Influence-Aware Constrained Decoding (GACD), an inference-based method, that addresses both biases without auxiliary models, and is readily applicable to existing models without finetuning. The core of our approach is bias estimation, which uses first-order Taylor gradients to understand the contribution of individual tokens--visual features and text tokens--to the current output. Based on this analysis, GACD mitigates hallucinations through two components: (1) suppressing spurious visual features correlated with the output objects, and (2) rebalancing cross-modal contributions by strengthening visual features relative to text. Experiments across multiple benchmarks demonstrate that GACD effectively reduces hallucinations and improves the visual grounding of MLLMs outputs.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
Innovative visual stylization is a cornerstone of artistic creation, yet generating novel and consistent visual styles remains a significant challenge. Existing generative approaches typically rely on lengthy textual prompts, reference images, or parameter-efficient fine-tuning to guide style-aware image generation, but often struggle with style consistency, limited creativity, and complex style representations. In this paper, we consider the code-to-style image generation task, which aims to produce images with novel and consistent visual styles specified by only a numerical code. To date, this field has only been primarily explored by the industry (e.g., Midjourney), with no open-source research from the academic community. To fill this gap, we propose CoTyle, the first open-source method for this task. Specifically, we first train a discrete style codebook from a collection of images to extract style embeddings. These embeddings serve as conditions for a text-to-image diffusion model (T2I-DM) to generate stylistic images. Subsequently, we train an autoregressive style generator on the discrete style embeddings to model their distribution, allowing the synthesis of novel style embeddings. During inference, a numerical style code is mapped to a unique style embedding by the style generator, and this embedding guides the T2I-DM to generate images in the corresponding style. Extensive experiments validate that CoTyle effectively converts a numerical code into a style controller, demonstrating a style is worth one code. Compared to existing methods, the stylized images generated by our method are more diverse and consistent, unlocking a vast space of reproducible styles from minimal input.
PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling
PDF ↗Consistent image generation requires faithfully preserving identities, styles, and logical coherence across multiple images,which is essential for applications such as storytelling and character design.Supervised training approaches struggle with this task due to the lack of large-scale datasets capturing visual consistency and the complexity of modeling human perceptual preferences.In this paper, we argue that reinforcement learning (RL) offers a promising alternative by enabling models to learn complex and subjective visual criteria in a data-free manner.To achieve this, we introduce PaCo-RL, a comprehensive framework that combines a specialized consistency reward model with an efficient RL algorithm.The first component, PaCo-Reward, is a pairwise consistency evaluator trained on a large-scale dataset constructed via automated sub-figure pairing.It evaluates consistency through a generative, autoregressive scoring mechanism enhanced by task-aware instructions and CoT reasons.The second component, PaCo-GRPO,leverages a novel resolution-decoupled optimization strategy to substantially reduce RL cost,alongside a log-tamed multi-reward aggregation mechanism that ensures balanced and stable reward optimization.Extensive experiments across the two representative subtasks show that PaCo-Reward significantly improves alignment with human perceptions of visual consistency,and PaCo-GRPO achieves state-of-the-art consistency performance with improved training efficiency and stability.Together, these results highlight the promise of PaCo-RL as a practical and scalable solution for consistent image generation.We will release the code, dataset, and models.
In this paper, we propose Extend3D, a training-free pipeline for 3D scene generation from a single image, built upon an object-centric 3D generative model. To overcome the limitations of fixed-size latent spaces in object-centric models for representing wide scenes, we extend the latent space in the x and y directions. Then, by dividing the extended latent space into overlapping patches, we apply the object-centric 3D generative model to each patch and couple them at each time step. Since patch-wise 3D generation with image conditioning requires strict spatial alignment between image and latent patches, we initialize the scene using a point cloud prior from a monocular depth estimator and iteratively refine occluded regions through SDEdit. We discovered that treating the incompleteness of 3D structure as noise during 3D refinement enables 3D completion via a concept, which we term under-noising. Furthermore, to address the sub-optimality of object-centric models for sub-scene generation, we optimize the extended latent during denoising, ensuring that the denoising trajectories remain consistent with the sub-scene dynamics. To this end, we introduce 3D-aware optimization objectives for improved geometric structure and texture fidelity. We demonstrate that our method yields better results than prior methods, as evidenced by human preference and quantitative experiments.
KVSmooth: Mitigating Hallucination in Multi-modal Large Language Models through Key-Value Smoothing
PDF ↗Despite the significant progress of Multi-modal Large Language Models (MLLMs) across diverse tasks, hallucination, which corresponds to the generation of visually inconsistent objects, attributes, or relations, remains a major obstacle to their reliable deployment. Unlike pure language models, MLLMs must ground their generation process in visual inputs; However, existing models often suffer from semantic drift during decoding, causing outputs to diverge from visual facts as the sequence length increases.To address this, we propose KVSmooth, a training-free, plug-and-play method that mitigates hallucination by performing attention-entropy-guided adaptive smoothing on hidden states. Specifically, KVSmooth applies an exponential moving average (EMA) to both keys and values in the KV-Cache while dynamically quantifying the sink degree of each token through its attention distribution entropy to adaptively adjust the smoothing strength. Unlike computationally expensive retraining or contrastive decoding methods, KVSmooth operates efficiently during inference without additional training or model modification. Extensive experiments demonstrate that KVSmooth significantly reduces hallucination (\mathit CHAIR _ S from 41.8 -> 18.2) while improving overall performance (F_1 score from 77.5 -> 79.2), achieving higher precision and recall simultaneously, whereas prior methods often sacrifice one for the other, thereby validating the effectiveness and generality of our method.
SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition
PDF ↗Zero-shot skeleton-based action recognition aims to recognize unseen actions by transferring knowledge from seen categories through semantic descriptions. Most existing methods typically align skeleton features with textual embeddings within a shared latent space. However, the absence of contextual cues, such as objects involved in the action, introduces an inherent gap between skeleton and semantic representations, making it difficult to distinguish visually similar actions. To address this, we propose SkeletonContext, a prompt-based framework that enriches skeletal motion representations with language-driven contextual semantics. Specifically, we introduce a Cross-Modal Context Prompt Module, which leverages a pretrained language model to reconstruct masked contextual prompts under guidance derived from LLMs. This design effectively transfers linguistic context to the skeleton encoder for instance-level semantic grounding and improved cross-modal alignment. In addition, a Key-Part Decoupling Module is incorporated to decouple motion-relevant joint features, ensuring robust action understanding even in the absence of explicit object interactions. Extensive experiments on multiple benchmarks demonstrate that SkeletonContext achieves state-of-the-art performance under both conventional and generalized zero-shot settings, validating its effectiveness in reasoning about context and distinguishing fine-grained, visually similar actions. Our project is available at:https://github.com/NingWang2049/skeletoncontext.
Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation
PDF ↗Referring Video Object Segmentation (RVOS) aims to segment objects in videos based on textual queries. Current methods mainly rely on large-scale supervised fine-tuning (SFT) of Multi-modal Large Language Models (MLLMs). However, this paradigm suffers from heavy data dependence and limited scalability against the rapid evolution of MLLMs. Although recent zero-shot approaches offer a flexible alternative, their performance remains significantly behind SFT-based methods, due to the straightforward workflow designs. To address these limitations, we propose Refer-Agent, a collaborative multi-agent system with alternating reasoning-reflection mechanisms. This system decomposes RVOS into step-by-step reasoning process. During reasoning, we introduce a Coarse-to-Fine frame selection strategy to ensure the frame diversity and textual relevance, along with a Dynamic Focus Layout that adaptively adjusts the agent's visual focus.Furthermore, we propose a Chain-of-Reflection mechanism, which employs a Questioner-Responder pair to generate a self-reflection chain, enabling the system to verify intermediate results and generates feedback for next-round reasoning refinement. Extensive experiments on five challenging benchmarks demonstrate that Refer-Agent significantly outperforms state-of-the-art methods, including both SFT-based models and zero-shot approaches.Moreover, Refer-Agent is flexible and enables fast integration of new MLLMs without any additional fine-tuning costs. Code will be released.
While language models have become impactful in many real-world applications, video generation remains largely confined to entertainment. Motivated by video's inherent capacity to demonstrate physical-world information that is difficult to convey through language alone (e.g., imagine teaching someone to tie a tie using only text), we identify an underutilized opportunity to extend video as a new answer modality for Next-Event Prediction (NEP), formalized as Video-Next-Event Prediction (VNEP). While the established NEP task takes a video with a procedural or predictive question as input to predict the next event in text, VNEP requires dynamic video responses. This shift from telling to showing unlocks more intuitive and customized answers for procedural learning and creative exploration. However, this task remains challenging for existing models, as it demands an understanding of multimodal input, instruction-conditioned reasoning, and the generation of video with visual and semantic consistency. To address this, we introduce VANS, a model that leverages reinforcement learning to align a Vision-Language Model (VLM) with a Video Diffusion Model (VDM) for VNEP. The core of VANS is our proposed Joint-GRPO that orchestrates the VLM and VDM to function as a unit. Driven by a shared reward on their respective output, it optimizes the VLM to produce captions that are both accurate and friendly to visualize, while guiding the VDM to generate videos that are faithful to these captions and the input visual context. To enable this learning, we craft VANS-Data-100K, a dedicated dataset for the VNEP task. Experiments on procedural and predictive benchmarks demonstrate that VANS achieves state-of-the-art performance in both video event prediction and visualization.
Owing to the weak stereo geometry of satellite images, Planar Block Adjustment (PBA) is a predominant technique for correcting geometric distortions in satellite images, which treats elevation as a known constraint and primarily optimizes planar coordinates. Existing PBA methods mainly rely on explicit tie points, suffering from parallax caused by inaccurate elevation (e.g., near high buildings) and irreversible error accumulation, which severely degrades adjustment accuracy. In this paper, a "Beyond Tie Points" paradigm for satellite image adjustment is proposed. A pretrained feature extractor is employed to extract robust dense features and a parallax-aware confidence map from each image. A gridded coarse-to-fine optimization framework then directly solves for the adjustment parameters basing on confidence-weighted feature consistency. Experiments conducted on multiview satellite image datasets covering Beijing, Guangzhou and San Jose demonstrate that the proposed method is significantly superior to traditional approaches in both accuracy and robustness, reducing the average error by up to 75.43% compared to traditional PBA.
Medical visual question answering models often face potential train-test distribution shifts that hinder generalization across unseen imaging and linguistic patterns. To address this challenge, we propose a dual-level confidence based framework (DuCoR) that achieves implicit self-refinement through iterative pseudo-supervised optimization. Instead of relying on fixed pseudo answers, the model progressively refines its predictions by estimating their reliability from two complementary perspectives. A loss-level confidence captures the reliability of supervision by modeling clean and noisy loss distributions, while a feature-level confidence measures the semantic coherence between sample representations and their pseudo-answer conditioned prototypes. Since these two confidences originate from distinct information sources, including the supervision signal and the input semantics, they provide mutually corrective cues. They are adaptively fused to derive per-sample reliability weights that guide pseudo-supervised optimization toward better alignment with the target distribution. Extensive experiments on multiple medical VQA benchmarks show that our method achieves superior performance and exhibits improved cross-domain generalization over fully supervised baseline.
Detectors often suffer from degraded performance, primarily due to the distributional gap between the source and target domains. This issue is especially evident in single-source domains with limited data, as models tend to rely on confounders (e.g., illumination, co-occurrence, and style) from the source domain, leading to spurious correlations that hinder generalization. To this end, this paper proposes a novel Basis-driven framework for domain generalization, namely Bridge, that incorporates causal inference into object detection. By learning the low-rank bases for front-door adjustment, Bridge blocks confounders' effects to mitigate spurious correlations, while simultaneously refining representations by filtering redundant and task-irrelevant components.Bridge can be seamlessly integrated with both discriminative (e.g., DINOv2/3, SAM) and generative (e.g., Stable Diffusion) Vision Foundation Models (VFMs). Extensive experiments across multiple domain generalization object detection datasets, i.e., Cross-Camera, Adverse Weather, Real-to-Artistic, Diverse Weather Datasets, and Diverse Weather DroneVehicle (our newly augmented real-world UAV-based benchmark), underscore the superiority of our proposed method over previous state-of-the-art approaches. The project page is available at: https://mingbohong.github.io/Bridge/.
Visually-grounded language models (VLMs) are highly effective in linking visual and textual information, yet they often struggle with basic classification and localization tasks. While classification mechanisms have been studied more extensively, the processes that support object localization remain poorly understood. In this work, we investigate two representative families, LLaVA-1.5 and InternVL-3.5, using a suite of mechanistic interpretability tools, including token ablations, attention knockout, and causal mediation analysis. We find that localization is driven by a containerization mechanism in which object-aligned tokens define the spatial extent of the object, while the semantic arrangement of tokens within those boundaries is largely irrelevant to the predicted box. Only a very small set of attention heads mediates the causal effect for both classification and localization, concentrating in early-mid layers for LLaVA and mid-late layers for InternVL. The two tasks share some early processing but ultimately depend on largely distinct specialized heads. Overall, we provide the first layer- and head-level account of localization in VLMs, revealing narrow computational pathways that can guide future model design and grounding objectives.
SOTA: Self-adaptive Optimal Transport for Zero-Shot Classification with Multiple Foundation Models
PDF ↗Foundation models have attracted widespread attention across domains due to their powerful zero-shot classification capabilities. This work is motivated by two key observations: (1) Vision-Language Models (VLMs), such as CLIP, often over-rely on class-level textual priors and struggle to capture fine-grained visual cues, whereas Vision-only Foundation Models (VFMs), such as DINO, provide rich and discriminative visual features but lack semantic alignment; (2) the performance of different VLMs varies considerably across datasets owing to differences in pre-training. To address these challenges, we propose SOTA (Self-adaptive Optimal TrAnsport), a training-free ensemble framework that integrates the outputs of multiple foundation models (VFMs or VLMs) by learning a self-adaptive transport plan. Notably, SOTA is prior-free and automatically balances model contributions. Extensive experiments across diverse domains, including natural images, medical pathology, and remote sensing, validate the generalizability of SOTA. The results consistently show that it effectively leverages the complementary strengths of different foundation models and achieves substantial improvements over individual models. The implementation code is available at: https://github.com/Afleve/self-adaptive-Optimal-Transport.
Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has--the failures. When all rollouts are wrong, gradients stall; when one happens to be correct, the update usually ignores why the others are close-but-wrong, and credit can be misassigned to spurious chains. We present CARE (Contrastive Anchored REflection), a failure-centric post-training framework for multimodal reasoning that turns errors into supervision. CARE combines: (i) an anchored-contrastive objective that forms a compact subgroup around the best rollout and a set of semantically proximate hard negatives, performs within-subgroup z-score normalization with negative-only scaling, and includes an all-negative rescue to prevent zero-signal batches; and (ii) Reflection-Guided Resampling(RGR), a one-shot structured self-repair that rewrites a representative failure and re-scores it with the same verifier, converting near-misses into usable positives without any test-time reflection. CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures. On Qwen2.5-VL-7B, CARE lifts macro-averaged accuracy by 4.6 points over GRPO across six verifiable visual-reasoning benchmarks; with Qwen3-VL-8B it reaches competitive or state-of-the-art results on MathVista and MMMU-Pro under an identical evaluation protocol.
Visual effects (VFX) are essential for enhancing the expressiveness and creativity of video content, yet producing high-quality effects typically requires expert knowledge and costly production pipelines. Existing AIGC systems face significant challenges in VFX generation due to the scarcity of effect-specific data and the inherent difficulty of modeling supernatural or stylized effects. Moreover, these approaches often require per-effect fine-tuning, which severely limits their scalability and generalization to novel VFX. In this work, we present EffectMaker, a unified reasoning-generation framework that enables reference-based VFX customization. EffectMaker employs a multimodal large language model to interpret high-level effect semantics and reason about how they should adapt to a target subject, while a diffusion transformer leverages in-context learning to capture fine-grained visual cues from reference videos. These two components form a semantic-visual dual-path guidance mechanism that enables accurate, controllable, and effect-consistent synthesis without per-effect fine-tuning. Furthermore, we construct EffectData, the largest high-quality synthetic VFX dataset to date, containing 130k videos across 3k VFX categories, to improve generalization and scalability. Experiments show that EffectMaker achieves superior visual quality and effect consistency over state-of-the-art baselines, offering a scalable and flexible paradigm for customized VFX generation. Project page: https://effectmaker.github.io.
In open-world semi-supervised learning (OWSSL), a model learns from labeled data and unlabeled data containing both known and novel classes. In practical OWSSL applications, models are expected to perform rigorous classification by directly selecting the most semantically relevant label from a candidate set for each sample. Existing OWSSL methods fail to achieve this because novel samples are trained without explicit supervision, and these methods lack mechanisms to extract latent semantic information, resulting in predicted labels that have no semantic correspondence to candidate textual labels. To address this, we introduce SEmantic Capture for Open-world Semi-supervised learning (SECOS), which directly predicts textual labels from the candidate set without post-processing, meeting the requirements of practical OWSSL applications. SECOS leverages external knowledge to extract and align semantic representations across modalities for both known and novel classes, providing explicit supervisory signals for training novel classes. Extensive experiments demonstrate that even when existing OWSSL methods are evaluated under the more lenient post-hoc matching setting, SECOS still surpasses them by up to 5.4% without such assistance, highlighting its superior effectiveness. Code is available at https://github.com/ganchi-huanggua/OSSL-Classification.
Achieving human-level dexterity in robots via imitation learning from heterogeneous datasets is hindered by the challenge of cross-embodiment skill transfer, particularly for high-DoF robotic hands. Existing methods, often relying on 2D observations and temporal-centric action representation, struggle to capture 3D spatial relations and fail to handle embodiment heterogeneity. This paper proposes the Structural Action Transformer (SAT), a new 3D dexterous manipulation policy that challenges this paradigm by introducing a structural-centric perspective. We reframe each action chunk not as a temporal sequence, but as a variable-length, unordered sequence of joint-wise trajectories. This structural formulation allows a Transformer to natively handle heterogeneous embodiments, treating the joint count as a variable sequence length. To encode structural priors and resolve ambiguity, we introduce an Embodied Joint Codebook that embeds each joint's functional role and kinematic properties. Our model learns to generate these trajectories from 3D point clouds via a continuous-time flow matching objective. We validate our approach by pre-training on large-scale heterogeneous datasets and fine-tuning on simulation and real-world dexterous manipulation tasks. Our method consistently outperforms all baselines, demonstrating superior sample efficiency and effective cross-embodiment skill transfer. This structural-centric representation offers a new path toward scaling policies for high-DoF, heterogeneous manipulators.
Cross-Domain Few-Shot Learning (CDFSL) adapts models trained with large-scale general data (source domain) to downstream target domains with only scarce training data, where the research on vision-language models (e.g., CLIP) is still in the early stages. Typical downstream domains, such as medical diagnosis, require fine-grained visual cues for interpretable recognition, but we find that current fine-tuned CLIP models can hardly focus on these cues, albeit they can roughly focus on important regions in source domains. Although current works have demonstrated CLIP's shortcomings in capturing local subtle patterns, in this paper, we find that **the domain gap and scarce training data further exacerbate such shortcomings, much more than that of holistic patterns**, which we call the local misalignment problem in CLIP-based CDFSL. To address this problem, due to the lack of supervision in aligning local visual features and text semantics, we turn to self-supervision information. Inspired by the translation task, we propose the CC-CDFSL method with cycle consistency, which translates local visual features into text features and then translates them back into visual features (and vice versa), and constrains the original features close to the translated back features.To reduce the noise imported by richer information in the visual modality, we further propose a Semantic Anchor mechanism, which first augments visual features to provide a larger corpus for the text-to-image mapping, and then shrinks the image features to filter out irrelevant image-to-text mapping. Extensive experiments on various benchmarks, backbones, and fine-tuning methods show we can (1) effectively improve the local vision-language alignment, (2) enhance the interpretability of learned patterns and model decisions by visualizing patches, and (3) achieve state-of-the-art performance. Our codes will be released.
Existing Test-Time Adaptation (TTA) methods for Vision-Language Models (VLMs), focusing on designing efficient adaptation parameters (eg. prompts or residual prototypes), predominantly rely on high-confidence samples obtained via entropy-based filtering. However, this prevailing paradigm implicitly inherits the VLM's class-wise prediction biases and leads to insufficient coverage of the test distribution, rendering the adaptation process biased and insufficiently exploratory.To overcome these limitations, we propose Dynamic Logits Adjustment and Exploration (DLAE), a novel framework that integrates Dynamic Logit Adjustment (DLA) with a Consistency-Guided Exploratory Cache (CGEC). DLA dynamically recalibrates model logits based on test prediction statistics, thereby mitigating class-wise prediction inconsistencies. Different from traditional cache mechanisms, our CGEC actively identifies additional samples near decision boundaries whose predicted labels are sensitive to the logit adjustment, thereby exploring beyond only high-confidence samples. By enforcing semantic and temporal consistency, the cache preserves the reliability of selected samples while enabling cautious yet effective exploration of low-confidence regions, ultimately yielding stable and reliable adaptation.Extensive experiments across multiple vision-language benchmarks demonstrate that our approach consistently surpasses state-of-the-art TTA methods, showing superior stability, adaptability, and generalization.
Current diffusion-based acceleration methods for long-portrait animation struggle to ensure identity (ID) consistency. This paper presents FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6xacceleration in inference speed. In particular, FlashPortrait begins by computing the identity-agnostic facial expression features with an off-the-shelf extractor. It then introduces a Normalized Facial Expression Block to align facial features with diffusion latents by normalizing them with their respective means and variances, thereby improving identity stability in facial modeling. During inference, FlashPortrait adopts a dynamic sliding-window scheme with weighted blending in overlapping areas, ensuring smooth transitions and ID consistency in long animations. In each context window, based on the latent variation rate at particular timesteps and the derivative magnitude ratio among diffusion layers, FlashPortrait utilizes higher-order latent derivatives at the current timestep to directly predict latents at future timesteps, thereby skipping several denoising steps and achieving 6xspeed acceleration. Experiments on benchmarks show the effectiveness of FlashPortrait both qualitatively and quantitatively.