arXiv subjects

Chaofan Ma

Publications and source records attributed to Chaofan Ma.

At least 19 recordsLinked to original sources

arXiv2026

TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation

Despite recent advances in unified multimodal models for multi-reference image generation, existing benchmarks remain organized around predefined task types (e.g., "subject composition"), which are ill-suited to this combinatorial setting and lead to fragmented coverage, uncontrolled complexity, and little diagnostic value. Recognizing that diverse multi-reference tasks share a common set of atomic operations, we adopt a capability-oriented perspective and formalize four operators: Anchor ($f$), Disentangle ($g$), Apply ($\oplus$), and Compose ($C$). Any multi-reference prompt can then be represented as a compositional formula over these operators, whose structural complexity is quantified by the number of operator slots. Building on this formulation, we construct TRACE-Bench, comprising approximately 1,600 evaluation cases across slot counts 1--8, built from 631 formula templates and around 4,000 reference images spanning diverse artistic styles and real-world subjects. The formula structure directly drives an operator-aligned evaluation protocol for per-capability scoring and a diagnostic tree analysis for recursive failure localization. Evaluating 9 leading models reveals insights invisible to holistic scoring: the primary bottleneck lies in disentanglement ($g$) and attribute binding ($\oplus$) rather than scene-level composition ($C$), with even the best model scoring only 0.74 on attribute fidelity. Project page: https://amuseum-whr.github.io/TraceBench

cs.CV↗

arXiv2026

H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models

Large-scale manipulation data is essential for robot learning, yet collecting robot demonstrations remains expensive and difficult to scale. Meanwhile, abundant egocentric human manipulation videos provide rich behavioral experiences, but transferring them across embodiments remains challenging due to differences between human hands and robotic end-effectors. Recent advances in video world models offer a promising pathway to synthesize robot-centric manipulation videos from human observations, while their cross-embodiment transfer capability remains largely unexplored. Therefore, we introduce H2R-Bench, a benchmark for evaluating cross-embodiment human-to-robot manipulation video generation, where models transform egocentric human demonstrations into robot manipulation videos under specified embodiments. Each benchmark instance contains a human demonstration video, target embodiment constraints, and source-grounded annotations covering task goals, action events, functional contacts, and object responses. H2R-Bench evaluates generated videos through five dimensions, including goal-state completion, action-event completion, functional contact transfer, embodiment correctness, and general video quality. We benchmark eleven state-of-the-art video generation models across six manipulation families and two robot embodiments. Our evaluation reveals that current video world models remain limited in human-to-robot manipulation transfer: even leading models often fail in embodiment consistency, functional interaction, and task execution. H2R-Bench provides a systematic diagnostic framework for evaluating whether video world models can bridge the human-to-robot embodiment gap and convert human manipulation observations into robot-centric training resources.

cs.RO↗

arXiv2026

RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation

Vision-language models (VLMs) are increasingly explored as visual critics, reward generators, and failure detectors in robotic manipulation. These roles implicitly require models to judge not only final task success, but also how a manipulation execution is physically and temporally progressing. However, existing evaluations fail to test whether VLMs possess fine-grained process understanding. To address this gap, we present RoboProcessBench, a benchmark for process-aware understanding in vision-language robotic manipulation. RoboProcessBench decomposes such capability into two complementary dimensions, \emph{static monitoring} and \emph{dynamic reasoning}, instantiated as 12 diagnostic question families covering phase, contact, motion, coordination, primitive-local progress, temporal order, outcome, and primitive-level transitions. Built from physically grounded execution traces, the curated benchmark corpus ProcessData contains \textasciitilde 58k question-answer pairs across 260 manipulation tasks, which is further split into ProcessData-SFT and ProcessData-Eval for post-training and evaluation purposes. Extensive evaluation of various VLMs on ProcessData-Eval reveals broad limitations across 12 diagnostic task families, suggesting current models still lack robust process-aware understanding of manipulation executions. But with ProcessData-SFT, the post-trained \textit{Qwen2.5-VL-7B} and \textit{InternVL-3-8B} exhibit consistent gains on local state, motion, progress, and primitive-aware cues. These results demonstrate that RoboProcessBench serves as both an evaluation benchmark and a learnable supervision source for developing VLMs capable of monitoring and evaluating robotic manipulation processes. Project webpage: \href{https://processbench-2026.github.io/RoboProcessBench-Web/}{https://processbench-2026.github.io}.

cs.RO↗

arXiv2026

Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning

Spatial reasoning from egocentric videos is inherently challenging because the observable evidence is constrained by the camera trajectory. Existing methods rely on single-turn inference, forcing models to resolve geometric ambiguity through semantic priors rather than verifiable evidence. We argue that spatial reasoning should be revisitable: conclusions formed under limited evidence should remain open to revision when complementary viewpoints become available. Building on this insight, we propose Reason, then Re-reason (ReRe), a training-free, inference-time framework with two phases: in the Reason Phase, an MLLM forms a spatial hypothesis from the original video; in the Re-reason Phase, it verifies or revises the hypothesis by observing a synthesized novel-view video. To enable effective cross-view revisiting, we design a Geometry-to-Video pipeline that renders strategically complementary novel views from predicted 3D geometry. These views feature an elevated, oblique perspective with scene-spanning coverage, while preserving the MLLM's native video interface without architectural modifications. Extensive evaluations on VSI-Bench and STI-Bench demonstrate that ReRe substantially boosts open-source MLLMs to rival proprietary state-of-the-art performance. Project page: https://zhenjiemao.github.io/ReRe/

cs.CV↗

arXiv2026

GenMask: Adapting DiT for Segmentation via Direct Mask Generation

Recent approaches for segmentation have leveraged pretrained generative models as feature extractors, treating segmentation as a downstream adaptation task via indirect feature retrieval. This implicit use suffers from a fundamental misalignment in representation. It also depends heavily on indirect feature extraction pipelines, which complicate the workflow and limit adaptation. In this paper, we argue that instead of indirect adaptation, segmentation tasks should be trained directly in a generative manner. We identify a key obstacle to this unified formulation: VAE latents of binary masks are sharply distributed, noise robust, and linearly separable, distinct from natural image latents. To bridge this gap, we introduce timesteps sampling strategy for binary masks that emphasizes extreme noise levels for segmentation and moderate noise for image generation, enabling harmonious joint training. We present GenMask, a DiT trains to generate black-and-white segmentation masks as well as colorful images in RGB space under the original generative objective. GenMask preserves the original DiT architecture while removing the need of feature extraction pipelines tailored for segmentation tasks. Empirically, GenMask attains state-of-the-art performance on referring and reasoning segmentation benchmarks and ablations quantify the contribution of each component.

cs.CV↗

arXiv2026

DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

Current unified multimodal models for image generation and editing typically rely on massive parameter scales (e.g., >10B), entailing prohibitive training costs and deployment footprints. In this work, we present DeepGen 1.0, a lightweight 5B unified model that achieves comprehensive capabilities competitive with or surpassing much larger counterparts. To overcome the limitations of compact models in semantic understanding and fine-grained control, we introduce Stacked Channel Bridging (SCB), a deep alignment framework that extracts hierarchical features from multiple VLM layers and fuses them with learnable 'think tokens' to provide the generative backbone with structured, reasoning-rich guidance. We further design a data-centric training strategy spanning three progressive stages: (1) Alignment Pre-training on large-scale image-text pairs and editing triplets to synchronize VLM and DiT representations, (2) Joint Supervised Fine-tuning on a high-quality mixture of generation, editing, and reasoning tasks to foster omni-capabilities, and (3) Reinforcement Learning with MR-GRPO, which leverages a mixture of reward functions and supervision signals, resulting in substantial gains in generation quality and alignment with human preferences, while maintaining stable training progress and avoiding visual artifacts. Despite being trained on only ~50M samples, DeepGen 1.0 achieves leading performance across diverse benchmarks, surpassing the 80B HunyuanImage by 28% on WISE and the 27B Qwen-Image-Edit by 37% on UniREditBench. By open-sourcing our training code, weights, and datasets, we provide an efficient, high-performance alternative to democratize unified multimodal research.

cs.CV↗

arXiv2026

UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabilities rather than interconnected reasoning steps. To address this, we propose UniReason, a unified framework that harmonizes these two tasks through two complementary reasoning paradigms. We incorporate world knowledge-enhanced textual reasoning into generation to infer implicit knowledge, and leverage editing capabilities for fine-grained editing-like visual refinement to further correct visual errors via self-reflection. This approach unifies generation and editing within a shared architecture, mirroring the human cognitive process of planning followed by refinement. We support this framework by systematically constructing a large-scale reasoning-centric dataset (~300k samples) covering five major knowledge domains (e.g., cultural commonsense, physics, etc.) for textual reasoning, alongside an agent-generated corpus for visual refinement. Extensive experiments demonstrate that UniReason achieves advanced performance on reasoning-intensive benchmarks such as WISE, KrisBench and UniREditBench, while maintaining superior general synthesis capabilities.

cs.CV↗

arXiv2025

Unsupervised Domain Adaptation via Similarity-based Prototypes for Cross-Modality Segmentation

Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Since the model is sensitive to domain shift, unsupervised domain adaptation attempts to reduce the domain gap and avoid costly annotation of unseen domains. This paper proposes a novel framework for cross-modality segmentation via similarity-based prototypes. In specific, we learn class-wise prototypes within an embedding space, then introduce a similarity constraint to make these prototypes representative for each semantic class while separable from different classes. Moreover, we use dictionaries to store prototypes extracted from different images, which prevents the class-missing problem and enables the contrastive learning of prototypes, and further improves performance. Extensive experiments show that our method achieves better results than other state-of-the-art methods.

cs.CV↗

arXiv2025

SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation

Referring Image Segmentation (RIS) aims to segment the target object in an image given a natural language expression. While recent methods leverage pre-trained vision backbones and more training corpus to achieve impressive results, they predominantly focus on simple expressions--short, clear noun phrases like "red car" or "left girl". This simplification often reduces RIS to a key word/concept matching problem, limiting the model's ability to handle referential ambiguity in expressions. In this work, we identify two challenging real-world scenarios: object-distracting expressions, which involve multiple entities with contextual cues, and category-implicit expressions, where the object class is not explicitly stated. To address the challenges, we propose a novel framework, SaFiRe, which mimics the human two-phase cognitive process--first forming a global understanding, then refining it through detail-oriented inspection. This is naturally supported by Mamba's scan-then-update property, which aligns with our phased design and enables efficient multi-cycle refinement with linear complexity. We further introduce aRefCOCO, a new benchmark designed to evaluate RIS models under ambiguous referring expressions. Extensive experiments on both standard and proposed datasets demonstrate the superiority of SaFiRe over state-of-the-art baselines.

cs.CV↗

arXiv2025

MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition

Video understanding is a complex challenge that requires effective modeling of spatial-temporal dynamics. With the success of image foundation models (IFMs) in image understanding, recent approaches have explored parameter-efficient fine-tuning (PEFT) to adapt IFMs for video. However, most of these methods tend to process spatial and temporal information separately, which may fail to capture the full intricacy of video dynamics. In this paper, we propose MoMa, an efficient adapter framework that achieves full spatial-temporal modeling by integrating Mamba's selective state space modeling into IFMs. We propose a novel SeqMod operation to inject spatial-temporal information into pre-trained IFMs, without disrupting their original features. By incorporating SeqMod into a Divide-and-Modulate architecture, MoMa enhances video understanding while maintaining computational efficiency. Extensive experiments on multiple video benchmarks demonstrate the effectiveness of MoMa, achieving superior performance with reduced computational cost.

cs.CV↗

arXiv2025

Modeling and Optimizing Latency for Delayed Hit Caching with Stochastic Miss Latency

Caching is crucial for system performance, but the delayed hit phenomenon, where requests queue during lengthy fetches after a cache miss, significantly degrades user-perceived latency in modern high-throughput systems. While prior works address delayed hits by estimating aggregate delay, they universally assume deterministic fetch latencies. This paper tackles the more realistic, yet unexplored, scenario where fetch latencies are stochastic. We present, to our knowledge, the first theoretical analysis of delayed hits under this condition, deriving analytical expressions for both the mean and variance of the aggregate delay assuming exponentially distributed fetch latency. Leveraging these insights, we develop a novel variance-aware ranking function tailored for this stochastic setting to guide cache eviction decisions more effectively. The simulations on synthetic and real-world datasets demonstrate that our proposed algorithm significantly reduces overall latency compared to state-of-the-art delayed-hit strategies, achieving a $3\%-30\%$ reduction on synthetic datasets and approximately $1\%-7\%$ reduction on real-world traces.

cs.NI↗

arXiv2025

VA-CDH: A Variance-Aware Method to Optimize Latency for Caching with Delayed Hits

Caches are fundamental to latency-sensitive systems like Content Delivery Networks (CDNs) and Mobile Edge Computing (MEC). However, the delayed hit phenomenon where multiple requests for an object occur during its fetch from the remote server after a miss significantly inflates user-perceived latency. While recent algorithms acknowledge delayed hits by estimating the resulting aggregate delay, they predominantly focus on its mean value. We identify and demonstrate that such approaches are insufficient, as the real aggregate delay frequently exhibits substantial variance in the true production system, leading to suboptimal latency performance when ignored. Thus, we propose VA-CDH, a variance-aware method to optimize latency for caching with delayed hits. It employs a novel ranking function that explicitly incorporates both the empirically estimated mean and standard deviation of aggregate delay, allowing caching decisions to account for its variation. We derive the analytical distribution of aggregate delay under Poisson arrivals as a theoretical contribution, offering more statistical insight beyond the mean value. Through the simulations conducted on synthetic and real-world datasets, we show that VA-CDH reduces the total latency by 1%-6% approximately compared to state-of-the-art algorithms.

cs.NI↗

arXiv2025

Contrast-Unity for Partially-Supervised Temporal Sentence Grounding

Temporal sentence grounding aims to detect event timestamps described by the natural language query from given untrimmed videos. The existing fully-supervised setting achieves great results but requires expensive annotation costs; while the weakly-supervised setting adopts cheap labels but performs poorly. To pursue high performance with less annotation costs, this paper introduces an intermediate partially-supervised setting, i.e., only short-clip is available during training. To make full use of partial labels, we specially design one contrast-unity framework, with the two-stage goal of implicit-explicit progressive grounding. In the implicit stage, we align event-query representations at fine granularity using comprehensive quadruple contrastive learning: event-query gather, event-background separation, intra-cluster compactness and inter-cluster separability. Then, high-quality representations bring acceptable grounding pseudo-labels. In the explicit stage, to explicitly optimize grounding objectives, we train one fully-supervised model using obtained pseudo-labels for grounding refinement and denoising. Extensive experiments and thoroughly ablations on Charades-STA and ActivityNet Captions demonstrate the significance of partial supervision, as well as our superior performance.

cs.CV↗

arXiv2024

Multi-Modal Prototypes for Open-World Semantic Segmentation

In semantic segmentation, generalizing a visual system to both seen categories and novel categories at inference time has always been practically valuable yet challenging. To enable such functionality, existing methods mainly rely on either providing several support demonstrations from the visual aspect or characterizing the informative clues from the textual aspect (e.g., the class names). Nevertheless, both two lines neglect the complementary intrinsic of low-level visual and high-level language information, while the explorations that consider visual and textual modalities as a whole to promote predictions are still limited. To close this gap, we propose to encompass textual and visual clues as multi-modal prototypes to allow more comprehensive support for open-world semantic segmentation, and build a novel prototype-based segmentation framework to realize this promise. To be specific, unlike the straightforward combination of bi-modal clues, we decompose the high-level language information as multi-aspect prototypes and aggregate the low-level visual information as more semantic prototypes, on basis of which, a fine-grained complementary fusion makes the multi-modal prototypes more powerful and accurate to promote the prediction. Based on an elastic mask prediction module that permits any number and form of prototype inputs, we are able to solve the zero-shot, few-shot and generalized counterpart tasks in one architecture. Extensive experiments on both PASCAL-$5^i$ and COCO-$20^i$ datasets show the consistent superiority of the proposed method compared with the previous state-of-the-art approaches, and a range of ablation studies thoroughly dissects each component in our framework both quantitatively and qualitatively that verify their effectiveness.

cs.CV↗

arXiv2024

ReMamber: Referring Image Segmentation with Mamba Twister

Referring Image Segmentation~(RIS) leveraging transformers has achieved great success on the interpretation of complex visual-language tasks. However, the quadratic computation cost makes it resource-consuming in capturing long-range visual-language dependencies. Fortunately, Mamba addresses this with efficient linear complexity in processing. However, directly applying Mamba to multi-modal interactions presents challenges, primarily due to inadequate channel interactions for the effective fusion of multi-modal data. In this paper, we propose ReMamber, a novel RIS architecture that integrates the power of Mamba with a multi-modal Mamba Twister block. The Mamba Twister explicitly models image-text interaction, and fuses textual and visual features through its unique channel and spatial twisting mechanism. We achieve competitive results on three challenging benchmarks with a simple and efficient architecture. Moreover, we conduct thorough analyses of ReMamber and discuss other fusion designs using Mamba. These provide valuable perspectives for future research. The code has been released at: https://github.com/yyh-rain-song/ReMamber.

cs.CV↗

arXiv2024

AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation

Open-vocabulary semantic segmentation is a challenging task that requires segmenting novel object categories at inference time. Recent studies have explored vision-language pre-training to handle this task, but suffer from unrealistic assumptions in practical scenarios, i.e., low-quality textual category names. For example, this paradigm assumes that new textual categories will be accurately and completely provided, and exist in lexicons during pre-training. However, exceptions often happen when encountering ambiguity for brief or incomplete names, new words that are not present in the pre-trained lexicons, and difficult-to-describe categories for users. To address these issues, this work proposes a novel attribute decomposition-aggregation framework, AttrSeg, inspired by human cognition in understanding new concepts. Specifically, in the decomposition stage, we decouple class names into diverse attribute descriptions to complement semantic contexts from multiple perspectives. Two attribute construction strategies are designed: using large language models for common categories, and involving manually labeling for human-invented categories. In the aggregation stage, we group diverse attributes into an integrated global description, to form a discriminative classifier that distinguishes the target object from others. One hierarchical aggregation architecture is further proposed to achieve multi-level aggregations, leveraging the meticulously designed clustering module. The final results are obtained by computing the similarity between aggregated attributes and images embeddings. To evaluate the effectiveness, we annotate three types of datasets with attribute descriptions, and conduct extensive experiments and ablation studies. The results show the superior performance of attribute decomposition-aggregation.

cs.CV↗

arXiv2023

Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation

This paper studies the problem of weakly open-vocabulary semantic segmentation (WOVSS), which learns to segment objects of arbitrary classes using mere image-text pairs. Existing works turn to enhance the vanilla vision transformer by introducing explicit grouping recognition, i.e., employing several group tokens/centroids to cluster the image tokens and perform the group-text alignment. Nevertheless, these methods suffer from a granularity inconsistency regarding the usage of group tokens, which are aligned in the all-to-one v.s. one-to-one manners during the training and inference phases, respectively. We argue that this discrepancy arises from the lack of elaborate supervision for each group token. To bridge this granularity gap, this paper explores explicit supervision for the group tokens from the prototypical knowledge. To this end, this paper proposes the non-learnable prototypical regularization (NPR) where non-learnable prototypes are estimated from source features to serve as supervision and enable contrastive matching of the group tokens. This regularization encourages the group tokens to segment objects with less redundancy and capture more comprehensive semantic regions, leading to increased compactness and richness. Based on NPR, we propose the prototypical guidance segmentation network (PGSeg) that incorporates multi-modal regularization by leveraging prototypical sources from both images and texts at different levels, progressively enhancing the segmentation capability with diverse prototypical patterns. Experimental results show that our proposed method achieves state-of-the-art performance on several benchmark datasets. The source code is available at https://github.com/Ferenas/PGSeg.

cs.CV↗

arXiv2023

Annotation-free Audio-Visual Segmentation

The objective of Audio-Visual Segmentation (AVS) is to localise the sounding objects within visual scenes by accurately predicting pixel-wise segmentation masks. To tackle the task, it involves a comprehensive consideration of both the data and model aspects. In this paper, first, we initiate a novel pipeline for generating artificial data for the AVS task without extra manual annotations. We leverage existing image segmentation and audio datasets and match the image-mask pairs with its corresponding audio samples using category labels in segmentation datasets, that allows us to effortlessly compose (image, audio, mask) triplets for training AVS models. The pipeline is annotation-free and scalable to cover a large number of categories. Additionally, we introduce a lightweight model SAMA-AVS which adapts the pre-trained segment anything model~(SAM) to the AVS task. By introducing only a small number of trainable parameters with adapters, the proposed model can effectively achieve adequate audio-visual fusion and interaction in the encoding stage with vast majority of parameters fixed. We conduct extensive experiments, and the results show our proposed model remarkably surpasses other competing methods. Moreover, by using the proposed model pretrained with our synthetic data, the performance on real AVSBench data is further improved, achieving 83.17 mIoU on S4 subset and 66.95 mIoU on MS3 set. The project page is https://jinxiang-liu.github.io/anno-free-AVS/.

cs.CV↗