arXiv subjects

Davide Modolo

Publications and source records attributed to Davide Modolo.

At least 19 recordsLinked to original sources

arXiv2026

Escaping Confidence Trap: Evolutionary Decoding for Mathematical Reasoning in Diffusion LLMs

Diffusion large language models (dLLMs) have emerged as a promising alternative to autoregressive LLMs, offering efficient generation through block-wise progressive unmasking. However, their strong general-purpose performance does not necessarily translate into reliable mathematical reasoning, where correctness depends on preserving coherent numerical-symbolic reasoning trajectories. In this work, we analyze the decoding trajectories of LLaDA 2.0 and identify a recurring diffusion confidence trap: local token confidence can become misaligned with global reasoning correctness during progressive block decoding. Our analysis reveals two representative failure regimes: sampling-sensitive failures, where correct paths exist but are unstable, and sampling-consistent failures, where repeated sampling converges to repetitive high-confidence but incorrect continuations. Motivated by this observation, we propose Evolutionary Decoding, a training-free test-time scaling framework that views diffusion decoding as an evolutionary process over candidate reasoning states. The framework combines step-wise selection, which preserves useful numerical-symbolic signals and suppresses repetitive patterns, with block-wise mutation, which introduces structured alternatives to escape incorrect high-confidence basins. Experiments on multiple benchmarks show that Evolutionary Decoding improves LLaDA 2.0 over confidence-based decoding, leading to more reliable mathematical reasoning.

cs.AI↗

arXiv2026

Mural: Transferring LLM knowledge to image generation via Mixture-of-Transformers

Leveraging capabilities of large language models (LLMs) in text-to-image (T2I) synthesis is an important research direction. In this work we investigate whether the knowledge of a frozen LLM can be effectively utilized in T2I generation when trained exclusively on standard text-image pairs. We integrate a frozen, reasoning-capable LLM with a diffusion-based image generator via shared attention within the Mixture-of-Transformers (MoT) architecture. Our experiments span two critical questions: (1) what degree of the LLM's intrinsic knowledge remains accessible during T2I training, and (2) what novel capabilities emerge in the resulting system. Across established benchmarks, our models achieve strong performance among unified understanding-generation systems: 0.85 on GenEval, 86.75 on DPG-Bench, and 0.66 on WISE with inference-time reasoning, using only text-image data. Remarkably, we uncover emergent behaviors absent from training data, including cross-lingual image generation, color-guided composition, emoji / ASCII scene construction, and generation directed by world knowledge. These results demonstrate that pretrained LLM knowledge can guide image synthesis under standard text-to-image training paradigms, without interleaved multimodal signals or explicit reasoning supervision. Our findings open new avenues for harnessing frozen model capabilities in resource-constrained multimodal learning.

cs.CV↗

arXiv2026

Visual Reasoning through Tool-supervised Reinforcement Learning

In this paper, we investigate the problem of how to effectively master tool-use to solve complex visual reasoning tasks for Multimodal Large Language Models. To achieve that, we propose a novel Tool-supervised Reinforcement Learning (ToolsRL) framework, with direct tool supervision for more effective tool-use learning. We focus on a series of simple, native, and interpretable visual tools, including zoom-in, rotate, flip, and draw point/line, whose tool supervision is easy to collect. A reinforcement learning curriculum is developed, where the first stage is solely optimized by a set of well motivated tool-specific rewards, and the second stage is trained with the accuracy targeted rewards while allowing calling tools. In this way, tool calling capability is mastered before using tools to complete visual reasoning tasks, avoiding the potential optimization conflict among those heterogeneous tasks. Our experiments have shown that the tool-supervised curriculum training is efficient and ToolsRL can achieve strong tool-use capabilities for complex visual reasoning tasks.

cs.CV↗

arXiv2026

STORM: End-to-End Referring Multi-Object Tracking in Videos

Referring multi-object tracking (RMOT) is a task of associating all the objects in a video that semantically match with given textual queries or referring expressions. Existing RMOT approaches decompose object grounding and tracking into separated modules and exhibit limited performance due to the scarcity of training videos, ambiguous annotations, and restricted domains. In this work, we introduce STORM, an end-to-end MLLM that jointly performs grounding and tracking within a unified framework, eliminating external detectors and enabling coherent reasoning over appearance, motion, and language. To improve data efficiency, we propose a task-composition learning (TCL) strategy that decomposes RMOT into image grounding and object tracking, allowing STORM to leverage data-rich sub-tasks and learn structured spatial--temporal reasoning. We further construct STORM-Bench, a new RMOT dataset with accurate trajectories and diverse, unambiguous referring expressions generated through a bottom-up annotation pipeline. Extensive experiments show that STORM achieves state-of-the-art performance on image grounding, single-object tracking, and RMOT benchmarks, demonstrating strong generalization and robust spatial--temporal grounding in complex real-world scenarios. STORM-Bench is released at https://github.com/amazon-science/storm-referring-multi-object-grounding.

cs.CV↗

arXiv2026

MM-ReCoder: Advancing Chart-to-Code Generation with Reinforcement Learning and Self-Correction

Multimodal Large Language Models (MLLMs) have recently demonstrated promising capabilities in multimodal coding tasks such as chart-to-code generation. However, existing methods primarily rely on supervised fine-tuning (SFT), which requires the model to learn code patterns through chart-code pairs but does not expose the model to a code execution environment. Moreover, while self-correction through execution feedback offers a potential route to improve coding quality, even state-of-the-art MLLMs have been shown to struggle with effective self-correction. In this work, we introduce MM-ReCoder, a chart-to-code generation model trained with reinforcement learning (RL) and equipped with self-correction ability. We propose a two-stage multi-turn self-correction RL strategy based on Group Relative Policy Optimization (GRPO). The first stage enhances the model's self-correction ability via rolling out a shared first turn, while the second stage improves the coding capability with full-trajectory optimization. MM-ReCoder learns to produce more accurate and executable code through the interaction with the environment and by iteratively correcting its own outputs. Our results on three chart-to-code benchmarks demonstrate the state-of-the-art performance of MM-ReCoder.

cs.AI↗

arXiv2026

Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models

With recent advancements in video backbone architectures, combined with the remarkable achievements of large language models (LLMs), the analysis of long-form videos spanning tens of minutes has become both feasible and increasingly prevalent. However, the inherently redundant nature of video sequences poses significant challenges for contemporary state-of-the-art models. These challenges stem from two primary aspects: 1) efficiently incorporating a larger number of frames within memory constraints, and 2) extracting discriminative information from the vast volume of input data. In this paper, we introduce a novel end-to-end schema for long-form video understanding, which includes an information-density-based adaptive video sampler (AVS) and an autoencoder-based spatiotemporal video compressor (SVC) integrated with a multimodal large language model (MLLM). Our proposed system offers two major advantages: it adaptively and effectively captures essential information from video sequences of varying durations, and it achieves high compression rates while preserving crucial discriminative information. The proposed framework demonstrates promising performance across various benchmarks, excelling in both long-form video understanding tasks and standard video understanding benchmarks. These results underscore the versatility and efficacy of our approach, particularly in managing the complexities of prolonged video sequences.

cs.CV↗

arXiv2024

Self-Supervised Multi-Object Tracking with Path Consistency

In this paper, we propose a novel concept of path consistency to learn robust object matching without using manual object identity supervision. Our key idea is that, to track a object through frames, we can obtain multiple different association results from a model by varying the frames it can observe, i.e., skipping frames in observation. As the differences in observations do not alter the identities of objects, the obtained association results should be consistent. Based on this rationale, we generate multiple observation paths, each specifying a different set of frames to be skipped, and formulate the Path Consistency Loss that enforces the association results are consistent across different observation paths. We use the proposed loss to train our object matching model with only self-supervision. By extensive experiments on three tracking datasets (MOT17, PersonPath22, KITTI), we demonstrate that our method outperforms existing unsupervised methods with consistent margins on various evaluation metrics, and even achieves performance close to supervised methods.

cs.CV↗

arXiv2024

Hyperbolic Learning with Synthetic Captions for Open-World Detection

Open-world detection poses significant challenges, as it requires the detection of any object using either object class labels or free-form texts. Existing related works often use large-scale manual annotated caption datasets for training, which are extremely expensive to collect. Instead, we propose to transfer knowledge from vision-language models (VLMs) to enrich the open-vocabulary descriptions automatically. Specifically, we bootstrap dense synthetic captions using pre-trained VLMs to provide rich descriptions on different regions in images, and incorporate these captions to train a novel detector that generalizes to novel concepts. To mitigate the noise caused by hallucination in synthetic captions, we also propose a novel hyperbolic vision-language learning approach to impose a hierarchy between visual and caption embeddings. We call our detector ``HyperLearner''. We conduct extensive experiments on a wide variety of open-world detection benchmarks (COCO, LVIS, Object Detection in the Wild, RefCOCO) and our results show that our model consistently outperforms existing state-of-the-art methods, such as GLIP, GLIPv2 and Grounding DINO, when using the same backbone.

cs.CV↗

arXiv2023

Early Action Recognition with Action Prototypes

Early action recognition is an important and challenging problem that enables the recognition of an action from a partially observed video stream where the activity is potentially unfinished or even not started. In this work, we propose a novel model that learns a prototypical representation of the full action for each class and uses it to regularize the architecture and the visual representations of the partial observations. Our model is very simple in design and also efficient. We decompose the video into short clips, where a visual encoder extracts features from each clip independently. Later, a decoder aggregates together in an online fashion features from all the clips for the final class prediction. During training, for each partial observation, the model is jointly trained to both predict the label as well as the action prototypical representation which acts as a regularizer. We evaluate our method on multiple challenging real-world datasets and outperform the current state-of-the-art by a significant margin. For example, on early recognition observing only the first 10% of each video, our method improves the SOTA by +2.23 Top-1 accuracy on Something-Something-v2, +3.55 on UCF-101, +3.68 on SSsub21, and +5.03 on EPIC-Kitchens-55, where prior work used either multi-modal inputs (e.g. optical-flow) or batched inference. Finally, we also present exhaustive ablation studies to motivate the design choices we made, as well as gather insights regarding what our model is learning semantically.

cs.CV↗

arXiv2023

SemiGPC: Distribution-Aware Label Refinement for Imbalanced Semi-Supervised Learning Using Gaussian Processes

In this paper we introduce SemiGPC, a distribution-aware label refinement strategy based on Gaussian Processes where the predictions of the model are derived from the labels posterior distribution. Differently from other buffer-based semi-supervised methods such as CoMatch and SimMatch, our SemiGPC includes a normalization term that addresses imbalances in the global data distribution while maintaining local sensitivity. This explicit control allows SemiGPC to be more robust to confirmation bias especially under class imbalance. We show that SemiGPC improves performance when paired with different Semi-Supervised methods such as FixMatch, ReMixMatch, SimMatch and FreeMatch and different pre-training strategies including MSN and Dino. We also show that SemiGPC achieves state of the art results under different degrees of class imbalance on standard CIFAR10-LT/CIFAR100-LT especially in the low data-regime. Using SemiGPC also results in about 2% avg.accuracy increase compared to a new competitive baseline on the more challenging benchmarks SemiAves, SemiCUB, SemiFungi and Semi-iNat.

cs.CV↗

arXiv2023

Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation

We propose a new semi-supervised learning design for human pose estimation that revisits the popular dual-student framework and enhances it two ways. First, we introduce a denoising scheme to generate reliable pseudo-heatmaps as targets for learning from unlabeled data. This uses multi-view augmentations and a threshold-and-refine procedure to produce a pool of pseudo-heatmaps. Second, we select the learning targets from these pseudo-heatmaps guided by the estimated cross-student uncertainty. We evaluate our proposed method on multiple evaluation setups on the COCO benchmark. Our results show that our model outperforms previous state-of-the-art semi-supervised pose estimators, especially in extreme low-data regime. For example with only 0.5K labeled images our method is capable of surpassing the best competitor by 7.22 mAP (+25% absolute improvement). We also demonstrate that our model can learn effectively from unlabeled data in the wild to further boost its generalization and performance.

cs.CV↗

arXiv2023

SkeleTR: Towrads Skeleton-based Action Recognition in the Wild

We present SkeleTR, a new framework for skeleton-based action recognition. In contrast to prior work, which focuses mainly on controlled environments, we target more general scenarios that typically involve a variable number of people and various forms of interaction between people. SkeleTR works with a two-stage paradigm. It first models the intra-person skeleton dynamics for each skeleton sequence with graph convolutions, and then uses stacked Transformer encoders to capture person interactions that are important for action recognition in general scenarios. To mitigate the negative impact of inaccurate skeleton associations, SkeleTR takes relative short skeleton sequences as input and increases the number of sequences. As a unified solution, SkeleTR can be directly applied to multiple skeleton-based action tasks, including video-level action classification, instance-level action detection, and group-level activity recognition. It also enables transfer learning and joint training across different action tasks and datasets, which result in performance improvement. When evaluated on various skeleton-based action recognition benchmarks, SkeleTR achieves the state-of-the-art performance.

cs.CV↗

arXiv2023

Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity

This paper presents novel benchmarks for evaluating vision-language models (VLMs) in zero-shot recognition, focusing on granularity and specificity. Although VLMs excel in tasks like image captioning, they face challenges in open-world settings. Our benchmarks test VLMs' consistency in understanding concepts across semantic granularity levels and their response to varying text specificity. Findings show that VLMs favor moderately fine-grained concepts and struggle with specificity, often misjudging texts that differ from their training data. Extensive evaluations reveal limitations in current VLMs, particularly in distinguishing between correct and subtly incorrect descriptions. While fine-tuning offers some improvements, it doesn't fully address these issues, highlighting the need for VLMs with enhanced generalization capabilities for real-world applications. This study provides insights into VLM limitations and suggests directions for developing more robust models.

cs.CV↗

arXiv2023

ScaleDet: A Scalable Multi-Dataset Object Detector

Multi-dataset training provides a viable solution for exploiting heterogeneous large-scale datasets without extra annotation cost. In this work, we propose a scalable multi-dataset detector (ScaleDet) that can scale up its generalization across datasets when increasing the number of training datasets. Unlike existing multi-dataset learners that mostly rely on manual relabelling efforts or sophisticated optimizations to unify labels across datasets, we introduce a simple yet scalable formulation to derive a unified semantic label space for multi-dataset training. ScaleDet is trained by visual-textual alignment to learn the label assignment with label semantic similarities across datasets. Once trained, ScaleDet can generalize well on any given upstream and downstream datasets with seen and unseen classes. We conduct extensive experiments using LVIS, COCO, Objects365, OpenImages as upstream datasets, and 13 datasets from Object Detection in the Wild (ODinW) as downstream datasets. Our results show that ScaleDet achieves compelling strong model performance with an mAP of 50.7 on LVIS, 58.8 on COCO, 46.8 on Objects365, 76.2 on OpenImages, and 71.8 on ODinW, surpassing state-of-the-art detectors with the same backbone.

cs.CV↗

arXiv2023

Musketeer: Joint Training for Multi-task Vision Language Model with Task Explanation Prompts

We present a vision-language model whose parameters are jointly trained on all tasks and fully shared among multiple heterogeneous tasks which may interfere with each other, resulting in a single model which we named Musketeer. The integration of knowledge across heterogeneous tasks is enabled by a novel feature called Task Explanation Prompt (TEP). With rich and structured information such as task input/output format, TEP reduces interference among tasks, allowing the model to focus on their shared structure. With a single model, Musketeer achieves results comparable to or better than strong baselines trained on single tasks, almost uniformly across multiple tasks.

cs.CV↗

arXiv2022

Semi-supervised Vision Transformers at Scale

We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored topic despite the wide adoption of the ViT architectures to different tasks. To tackle this problem, we propose a new SSL pipeline, consisting of first un/self-supervised pre-training, followed by supervised fine-tuning, and finally semi-supervised fine-tuning. At the semi-supervised fine-tuning stage, we adopt an exponential moving average (EMA)-Teacher framework instead of the popular FixMatch, since the former is more stable and delivers higher accuracy for semi-supervised vision transformers. In addition, we propose a probabilistic pseudo mixup mechanism to interpolate unlabeled samples and their pseudo labels for improved regularization, which is important for training ViTs with weak inductive bias. Our proposed method, dubbed Semi-ViT, achieves comparable or better performance than the CNN counterparts in the semi-supervised classification setting. Semi-ViT also enjoys the scalability benefits of ViTs that can be readily scaled up to large-size models with increasing accuracies. For example, Semi-ViT-Huge achieves an impressive 80% top-1 accuracy on ImageNet using only 1% labels, which is comparable with Inception-v4 using 100% ImageNet labels.

cs.CV↗

arXiv2022

SCVRL: Shuffled Contrastive Video Representation Learning

We propose SCVRL, a novel contrastive-based framework for self-supervised learning for videos. Differently from previous contrast learning based methods that mostly focus on learning visual semantics (e.g., CVRL), SCVRL is capable of learning both semantic and motion patterns. For that, we reformulate the popular shuffling pretext task within a modern contrastive learning paradigm. We show that our transformer-based network has a natural capacity to learn motion in self-supervised settings and achieves strong performance, outperforming CVRL on four benchmarks.

cs.CV↗

arXiv2022

Hierarchical Self-supervised Representation Learning for Movie Understanding

Most self-supervised video representation learning approaches focus on action recognition. In contrast, in this paper we focus on self-supervised video learning for movie understanding and propose a novel hierarchical self-supervised pretraining strategy that separately pretrains each level of our hierarchical movie understanding model (based on [37]). Specifically, we propose to pretrain the low-level video backbone using a contrastive learning objective, while pretrain the higher-level video contextualizer using an event mask prediction task, which enables the usage of different data sources for pretraining different levels of the hierarchy. We first show that our self-supervised pretraining strategies are effective and lead to improved performance on all tasks and metrics on VidSitu benchmark [37] (e.g., improving on semantic role prediction from 47% to 61% CIDEr scores). We further demonstrate the effectiveness of our contextualized event features on LVU tasks [54], both when used alone and when combined with instance features, showing their complementarity.

cs.CV↗