Searcharxiv⌕ Search

arXiv subjects

Jinlong Peng

Publications and source records attributed to Jinlong Peng.

At least 19 recordsLinked to original sources
arXiv2026

PiT: Progressive Diffusion Transformer

Diffusion Transformers (DiTs) achieve remarkable performance within image generation via the transformer architecture. Conventionally, DiTs are constructed by stacking serial isotropic global modeling transformers, which face significant quadratic computational cost. However, through empirical analysis, we find that DiTs do not rely as heavily on global information as previously believed. In fact, most layers exhibit significant redundancy in global computation. Additionally, conventional attention mechanisms suffer from low-frequency inertia, limiting their efficiency. To address these issues, we propose Pseudo Shifted Window Attention (PSWA), which fundamentally mitigates global attention redundancy. PSWA achieves moderate global-local information through window attention. It further utilizes a high-frequency bridging branch to simulate shifted window operations, which both enrich the high-frequency information and strengthen inter-window connections. Furthermore, we propose the Progressive Coverage Channel Allocation (PCCA) strategy that captures high-order attention without additional computational cost. Based on these innovations, we propose a series of Pseudo Progressive Diffusion Transformer (PiT). Our extensive experiments show their superior performance; for example, our proposed PiT-L achieves 54% FID improvement over DiT-XL/2 while using less computation.

cs.CV↗
arXiv2026

YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family

Generic parameter-efficient fine-tuning (PEFT) methods transferred from language models can fail silently on real-time detectors, whose heterogeneous operators and detection-specific components impose placement constraints absent from regular Transformer stacks. We propose YOLO-PEFT, a structure-aware framework that formulates adapter placement as an auditable constraint-planning problem. Given a detector graph, a PEFT request, and a resource budget, YOLO-PEFT assigns operator and semantic roles, evaluates explicit operator-validity, detector-semantic, graph-interface, and deployment predicates, records a reason code for each excluded module, and either emits a budgeted target-module plan or returns Refuse before training. Under the official VOC07+12 trainval-to-VOC07 test protocol, planner-selected RS-LoRA reaches 0.7138 and 0.7307 mAP50-95 on YOLO11s and YOLO12s, respectively, compared with 0.6428 and 0.6662 for Full-SFT. On RT-DETR-L, all seven evaluated LoRA-family configurations cross the predefined catastrophic threshold, supporting a calibrated Refuse-to-Full-SFT decision within the evaluated coverage. A controlled YOLO11 audit further shows that LoRA reduces peak training memory by 43.9 percent, although training takes 1.72 times longer. Within the evaluated detector families, placement policies, and calibration coverage, YOLO-PEFT replaces manual target-module trial and error with explicit, inspectable planning while preserving verified train-save-merge-export paths; refusal on unseen detector architectures remains an open validation problem. Project Page: github.com/Tencent/YOLO-Master

cs.CV↗
arXiv2026

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning

Video understanding is moving beyond closed-context perception toward open-world evidence exploration, a paradigm formalized as Video Deep Research (VDR). However, existing multimodal search agents primarily target static images, and the current VDR benchmark relies on text-centric retrieval that discards crucial visual information. To address these limitations, we propose VideoSearcher, a closed-loop agentic framework that empowers Vision-Language Models with multi-tool reasoning for VDR. VideoSearcher unifies temporal localization, spatial focusing, and multimodal search within a single reasoning trajectory, enabling agents to progressively ground visual clues, retrieve relevant evidence, and synthesize answers. To optimize knowledge-intensive reasoning trajectories, we propose Bi-branch Sequence Policy Optimization (BiSPO), a reinforcement learning algorithm that decouples tool-invocation optimization from answer-accuracy optimization. This design provides stable learning signals for both evidence-grounded reasoning and purposeful tool use. Furthermore, we construct VideoSearch-QA, the first benchmark designed to evaluate open-world video information grounding and multimodal search-based reasoning. Extensive experiments demonstrate that VideoSearcher significantly outperforms prior open-source agentic baselines across various search-oriented and multimodal understanding benchmarks.

cs.CV↗
arXiv2026

SCL: Towards Domain Generalization via Single-Temporal Multimodal Contrastive Learning for Remote Sensing Change Detection

In recent years, change detection and anomaly detection models based on CNN and transformer have achieved remarkable success across various datasets based on paired data. However, most such methods exhibit limited crossdataset generalization due to domain-specific designs and typically rely on large amounts of paired labeled data. In this paper, based on visual-language pre-training model, we introduce a Single-temporal multimodal Contrastive Learning (SCL) foundation models for change detection without training on the target dataset. To further improve the model's ability to learn context of textual and visual information, we propose a Dynamic Text-vision Context Optimization (DTCO) module for prompt learning. Meanwhile, to address the data dependency issue of existing methods, we introduce a controllable generation and Single-temporal trAINing strategy (SAIN). This allows us to train the model using a large number of existing single-temporal images without the need for paired label. Extensive experiments on various realworld change detection datasets demonstrate the superior performance and generalization of SCL, outperforming state-of-the-art methods under the evaluated settings. Code is available at https://github.com/Kane-Du/scl-cd.git.

cs.CV↗
arXiv2026

IRPO: Boosting Image Restoration via Post-training GRPO

Post-training has become effective for high-level generation, but its role in low-level vision remains underexplored. Existing image restoration methods often rely on fixed pixel-wise fitting to ground-truth images, which can lead to over-smoothing and weak generalization. We propose IRPO, a GRPO-based post-training framework for deterministic restoration models. IRPO is built around two axes: data formulation and reward modeling. For data formulation, we select the 30% underperforming samples from the pre-training stage, which improves both accuracy and training efficiency. For reward modeling, we combine fidelity-oriented and quality-aware feedback with three components: a General Reward for structural fidelity, an Expert Reward that uses a Vision-Language Model as a coarse visual-quality judge, and a Restoration Reward for task-specific low-level cues. Experiments on six in-domain and five out-of-domain (OOD) benchmarks show that IRPO improves the AdaIR baseline by 0.93 dB on in-domain tasks and 3.43 dB on OOD settings. Our code can be shown in https://github.com/HaoxuanXU1024/IRPO.

cs.CV↗
arXiv2026

PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation

Recent advances in diffusion-based text-to-image generation have demonstrated promising results through visual condition control. However, existing ControlNet-like methods struggle with compositional visual conditioning - simultaneously preserving semantic fidelity across multiple heterogeneous control signals while maintaining high visual quality, where they employ separate control branches that often introduce conflicting guidance during the denoising process, leading to structural distortions and artifacts in generated images. To address this issue, we present PixelPonder, a novel unified control framework, which allows for effective control of multiple visual conditions under a single control structure. Specifically, we design a patch-level adaptive condition selection mechanism that dynamically prioritizes spatially relevant control signals at the sub-region level, enabling precise local guidance without global interference. Additionally, a time-aware control injection scheme is deployed to modulate condition influence according to denoising timesteps, progressively transitioning from structural preservation to texture refinement and fully utilizing the control information from different categories to promote more harmonious image generation. Extensive experiments demonstrate that PixelPonder surpasses previous methods across different benchmark datasets, showing superior improvement in spatial alignment accuracy while maintaining high textual semantic consistency.

cs.CV↗
arXiv2026

ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning

Reinforcement Fine-Tuning (RFT) on flow-based models is crucial for preference alignment. However, they often introduce visual hallucinations like over-optimized details and semantic misalignment. This work preliminarily explores why visual hallucinations arise and how to reduce them. We first investigate RFT methods from a unified perspective, and reveal the core problems stemming from two aspects, exploration and exploitation: (1) limited exploration during stochastic differential equation (SDE) rollouts, leading to an over-emphasis on local details at the expense of global semantics, and (2) trajectory imitation process inherent in policy gradient methods, distorting the model's foundational vector field and its cross-step consistency. Building on this, we propose ConsistentRFT, a general framework to mitigate these hallucinations. Specifically, we design a Dynamic Granularity Rollout (DGR) mechanism to balance exploration between global semantics and local details by dynamically scheduling different noise sources. We then introduce a Consistent Policy Gradient Optimization (CPGO) that preserves the model's consistency by aligning the current policy with a more stable prior. Extensive experiments demonstrate that ConsistentRFT significantly mitigates visual hallucinations, achieving average reductions of 49\% for low-level and 38\% for high-level perceptual hallucinations. Furthermore, ConsistentRFT outperforms other RFT methods on out-of-domain metrics, showing an improvement of 5.1\% (v.s. the baseline's decrease of -0.4\%) over FLUX1.dev. This is \href{https://xiaofeng-tan.github.io/projects/ConsistentRFT}{Project Page}.

cs.CV↗
arXiv2025

YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection

Existing Real-Time Object Detection (RTOD) methods commonly adopt YOLO-like architectures for their favorable trade-off between accuracy and speed. However, these models rely on static dense computation that applies uniform processing to all inputs, misallocating representational capacity and computational resources such as over-allocating on trivial scenes while under-serving complex ones. This mismatch results in both computational redundancy and suboptimal detection performance. To overcome this limitation, we propose YOLO-Master, a novel YOLO-like framework that introduces instance-conditional adaptive computation for RTOD. This is achieved through a Efficient Sparse Mixture-of-Experts (ES-MoE) block that dynamically allocates computational resources to each input according to its scene complexity. At its core, a lightweight dynamic routing network guides expert specialization during training through a diversity enhancing objective, encouraging complementary expertise among experts. Additionally, the routing network adaptively learns to activate only the most relevant experts, thereby improving detection performance while minimizing computational overhead during inference. Comprehensive experiments on five large-scale benchmarks demonstrate the superiority of YOLO-Master. On MS COCO, our model achieves 42.4% AP with 1.62ms latency, outperforming YOLOv13-N by +0.8% mAP and 17.8% faster inference. Notably, the gains are most pronounced on challenging dense scenes, while the model preserves efficiency on typical inputs and maintains real-time inference speed. Code will be available.

cs.CV↗
arXiv2025

CareCom: Generative Image Composition with Calibrated Reference Features

Image composition aims to seamlessly insert foreground object into background. Despite the huge progress in generative image composition, the existing methods are still struggling with simultaneous detail preservation and foreground pose/view adjustment. To address this issue, we extend the existing generative composition model to multi-reference version, which allows using arbitrary number of foreground reference images. Furthermore, we propose to calibrate the global and local features of foreground reference images to make them compatible with the background information. The calibrated reference features can supplement the original reference features with useful global and local information of proper pose/view. Extensive experiments on MVImgNet and MureCom demonstrate that the generative model can greatly benefit from the calibrated reference features.

cs.CV↗
arXiv2025

Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detection

Few-shot anomaly detection (FSAD) methods identify anomalous regions with few known normal samples. Most existing methods rely on the generalization ability of pre-trained vision-language models (VLMs) to recognize potentially anomalous regions through feature similarity between text descriptions and images. However, due to the lack of detailed textual descriptions, these methods can only pre-define image-level descriptions to match each visual patch token to identify potential anomalous regions, which leads to the semantic misalignment between image descriptions and patch-level visual anomalies, achieving sub-optimal localization performance. To address the above issues, we propose the Multi-Level Fine-Grained Semantic Caption (MFSC) to provide multi-level and fine-grained textual descriptions for existing anomaly detection datasets with automatic construction pipeline. Based on the MFSC, we propose a novel framework named FineGrainedAD to improve anomaly localization performance, which consists of two components: Multi-Level Learnable Prompt (MLLP) and Multi-Level Semantic Alignment (MLSA). MLLP introduces fine-grained semantics into multi-level learnable prompts through automatic replacement and concatenation mechanism, while MLSA designs region aggregation strategy and multi-level alignment training to facilitate learnable prompts better align with corresponding visual regions. Experiments demonstrate that the proposed FineGrainedAD achieves superior overall performance in few-shot settings on MVTec-AD and VisA datasets.

cs.CV↗
arXiv2025

VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model

With the growing requirement for natural human-computer interaction, speech-based systems receive increasing attention as speech is one of the most common forms of daily communication. However, the existing speech models still experience high latency when generating the first audio token during streaming, which poses a significant bottleneck for deployment. To address this issue, we propose VITA-Audio, an end-to-end large speech model with fast audio-text token generation. Specifically, we introduce a lightweight Multiple Cross-modal Token Prediction (MCTP) module that efficiently generates multiple audio tokens within a single model forward pass, which not only accelerates the inference but also significantly reduces the latency for generating the first audio in streaming scenarios. In addition, a four-stage progressive training strategy is explored to achieve model acceleration with minimal loss of speech quality. To our knowledge, VITA-Audio is the first multi-modal large language model capable of generating audio output during the first forward pass, enabling real-time conversational capabilities with minimal latency. VITA-Audio is fully reproducible and is trained on open-source data only. Experimental results demonstrate that our model achieves an inference speedup of 3~5x at the 7B parameter scale, but also significantly outperforms open-source models of similar model size on multiple benchmarks for automatic speech recognition (ASR), text-to-speech (TTS), and spoken question answering (SQA) tasks.

cs.CL↗
arXiv2025

TokenAR: Multiple Subject Generation via Autoregressive Token-level enhancement

Autoregressive Model (AR) has shown remarkable success in conditional image generation. However, these approaches for multiple reference generation struggle with decoupling different reference identities. In this work, we propose the TokenAR framework, specifically focused on a simple but effective token-level enhancement mechanism to address reference identity confusion problem. Such token-level enhancement consists of three parts, 1). Token Index Embedding clusters the tokens index for better representing the same reference images; 2). Instruct Token Injection plays as a role of extra visual feature container to inject detailed and complementary priors for reference tokens; 3). The identity-token disentanglement strategy (ITD) explicitly guides the token representations toward independently representing the features of each identity.This token-enhancement framework significantly augments the capabilities of existing AR based methods in conditional image generation, enabling good identity consistency while preserving high quality background reconstruction. Driven by the goal of high-quality and high-diversity in multi-subject generation, we introduce the InstructAR Dataset, the first open-source, large-scale, multi-reference input, open domain image generation dataset that includes 28K training pairs, each example has two reference subjects, a relative prompt and a background with mask annotation, curated for multiple reference image generation training and evaluating. Comprehensive experiments validate that our approach surpasses current state-of-the-art models in multiple reference image generation task. The implementation code and datasets will be made publicly. Codes are available, see https://github.com/lyrig/TokenAR

cs.CV↗
arXiv2025

Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have demonstrated significant advances in visual understanding tasks. However, their capacity to comprehend human-centric scenes has rarely been explored, primarily due to the absence of comprehensive evaluation benchmarks that take into account both the human-oriented granular level and higher-dimensional causal reasoning ability. Such high-quality evaluation benchmarks face tough obstacles, given the physical complexity of the human body and the difficulty of annotating granular structures. In this paper, we propose Human-MME, a curated benchmark designed to provide a more holistic evaluation of MLLMs in human-centric scene understanding. Compared with other existing benchmarks, our work provides three key features: 1. Diversity in human scene, spanning 4 primary visual domains with 15 secondary domains and 43 sub-fields to ensure broad scenario coverage. 2. Progressive and diverse evaluation dimensions, evaluating the human-based activities progressively from the human-oriented granular perception to the higher-dimensional reasoning, consisting of eight dimensions with 19,945 real-world image question pairs and an evaluation suite. 3. High-quality annotations with rich data paradigms, constructing the automated annotation pipeline and human-annotation platform, supporting rigorous manual labeling to facilitate precise and reliable model assessment. Our benchmark extends the single-target understanding to the multi-person and multi-image mutual understanding by constructing the choice, short-answer, grounding, ranking and judgment question components, and complex questions of their combination. The extensive experiments on 17 state-of-the-art MLLMs effectively expose the limitations and guide future MLLMs research toward better human-centric image understanding. All data and code are available at https://github.com/Yuan-Hou/Human-MME.

cs.CV↗
arXiv2025

DRL: Discriminative Representation Learning with Parallel Adapters for Class Incremental Learning

With the excellent representation capabilities of Pre-Trained Models (PTMs), remarkable progress has been made in non-rehearsal Class-Incremental Learning (CIL) research. However, it remains an extremely challenging task due to three conundrums: increasingly large model complexity, non-smooth representation shift during incremental learning and inconsistency between stage-wise sub-problem optimization and global inference. In this work, we propose the Discriminative Representation Learning (DRL) framework to specifically address these challenges. To conduct incremental learning effectively and yet efficiently, the DRL's network, called Incremental Parallel Adapter (IPA) network, is built upon a PTM and increasingly augments the model by learning a lightweight adapter with a small amount of parameter learning overhead in each incremental stage. The adapter is responsible for adapting the model to new classes, it can inherit and propagate the representation capability from the current model through parallel connection between them by a transfer gate. As a result, this design guarantees a smooth representation shift between different incremental stages. Furthermore, to alleviate inconsistency and enable comparable feature representations across incremental stages, we design the Decoupled Anchor Supervision (DAS). It decouples constraints of positive and negative samples by respectively comparing them with the virtual anchor. This decoupling promotes discriminative representation learning and aligns the feature spaces learned at different stages, thereby narrowing the gap between stage-wise local optimization over a subset of data and global inference across all classes. Extensive experiments on six benchmarks reveal that our DRL consistently outperforms other state-of-the-art methods throughout the entire CIL period while maintaining high efficiency in both training and inference phases.

cs.CV↗
arXiv2025

DynamicControl: Adaptive Condition Selection for Improved Text-to-Image Generation

To enhance the controllability of text-to-image diffusion models, current ControlNet-like models have explored various control signals to dictate image attributes. However, existing methods either handle conditions inefficiently or use a fixed number of conditions, which does not fully address the complexity of multiple conditions and their potential conflicts. This underscores the need for innovative approaches to manage multiple conditions effectively for more reliable and detailed image synthesis. To address this issue, we propose a novel framework, DynamicControl, which supports dynamic combinations of diverse control signals, allowing adaptive selection of different numbers and types of conditions. Our approach begins with a double-cycle controller that generates an initial real score sorting for all input conditions by leveraging pre-trained conditional generation models and discriminative models. This controller evaluates the similarity between extracted conditions and input conditions, as well as the pixel-level similarity with the source image. Then, we integrate a Multimodal Large Language Model (MLLM) to build an efficient condition evaluator. This evaluator optimizes the ordering of conditions based on the double-cycle controller's score ranking. Our method jointly optimizes MLLMs and diffusion models, utilizing MLLMs' reasoning capabilities to facilitate multi-condition text-to-image (T2I) tasks. The final sorted conditions are fed into a parallel multi-control adapter, which learns feature maps from dynamic visual conditions and integrates them to modulate ControlNet, thereby enhancing control over generated images. Through both quantitative and qualitative comparisons, DynamicControl demonstrates its superiority over existing methods in terms of controllability, generation quality and composability under various conditional controls.

cs.CV↗
arXiv2025

PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Models

Recent success of vision foundation models have shown promising performance for the 2D perception tasks. However, it is difficult to train a 3D foundation network directly due to the limited dataset and it remains under explored whether existing foundation models can be lifted to 3D space seamlessly. In this paper, we present PointSeg, a novel training-free paradigm that leverages off-the-shelf vision foundation models to address 3D scene perception tasks. PointSeg can segment anything in 3D scene by acquiring accurate 3D prompts to align their corresponding pixels across frames. Concretely, we design a two-branch prompts learning structure to construct the 3D point-box prompts pairs, combining with the bidirectional matching strategy for accurate point and proposal prompts generation. Then, we perform the iterative post-refinement adaptively when cooperated with different vision foundation models. Moreover, we design a affinity-aware merging algorithm to improve the final ensemble masks. PointSeg demonstrates impressive segmentation performance across various datasets, all without training. Specifically, our approach significantly surpasses the state-of-the-art specialist training-free model by 14.1$\%$, 12.3$\%$, and 12.6$\%$ mAP on ScanNet, ScanNet++, and KITTI-360 datasets, respectively. On top of that, PointSeg can incorporate with various foundation models and even surpasses the specialist training-based methods by 3.4$\%$-5.4$\%$ mAP across various datasets, serving as an effective generalist model.

cs.CV↗
arXiv2025

UniCombine: Unified Multi-Conditional Combination with Diffusion Transformer

With the rapid development of diffusion models in image generation, the demand for more powerful and flexible controllable frameworks is increasing. Although existing methods can guide generation beyond text prompts, the challenge of effectively combining multiple conditional inputs while maintaining consistency with all of them remains unsolved. To address this, we introduce UniCombine, a DiT-based multi-conditional controllable generative framework capable of handling any combination of conditions, including but not limited to text prompts, spatial maps, and subject images. Specifically, we introduce a novel Conditional MMDiT Attention mechanism and incorporate a trainable LoRA module to build both the training-free and training-based versions. Additionally, we propose a new pipeline to construct SubjectSpatial200K, the first dataset designed for multi-conditional generative tasks covering both the subject-driven and spatially-aligned conditions. Extensive experimental results on multi-conditional generation demonstrate the outstanding universality and powerful capability of our approach with state-of-the-art performance.

cs.CV↗
arXiv2025

Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation

The performance of anomaly inspection in industrial manufacturing is constrained by the scarcity of anomaly data. To overcome this challenge, researchers have started employing anomaly generation approaches to augment the anomaly dataset. However, existing anomaly generation methods suffer from limited diversity in the generated anomalies and struggle to achieve a seamless blending of this anomaly with the original image. Moreover, the generated mask is usually not aligned with the generated anomaly. In this paper, we overcome these challenges from a new perspective, simultaneously generating a pair of the overall image and the corresponding anomaly part. We propose DualAnoDiff, a novel diffusion-based few-shot anomaly image generation model, which can generate diverse and realistic anomaly images by using a dual-interrelated diffusion model, where one of them is employed to generate the whole image while the other one generates the anomaly part. Moreover, we extract background and shape information to mitigate the distortion and blurriness phenomenon in few-shot image generation. Extensive experiments demonstrate the superiority of our proposed model over state-of-the-art methods in terms of diversity, realism and the accuracy of mask. Overall, our approach significantly improves the performance of downstream anomaly inspection tasks, including anomaly detection, anomaly localization, and anomaly classification tasks.

cs.CV↗