Searcharxiv⌕ Search

arXiv subjects

Wei Zeng

Publications and source records attributed to Wei Zeng.

At least 19 recordsLinked to original sources
arXiv2026

ColorConceptBench: A Benchmark for Probabilistic Color-Concept Understanding in Text-to-Image Models

Text-to-image (T2I) models have advanced considerably in generating high-quality images from textual descriptions. However, their ability to associate colors with concepts remains largely constrained to explicit color names or codes, while their capacity to handle \emph{implicit concepts}, such as emotions and visual states, remains underexplored. To address this gap, we introduce ColorConceptBench, an expert-annotated benchmark that systematically evaluates color-concept associations through probabilistic color distributions. ColorConceptBench moves beyond explicit color specifications by examining how models interpret 1,281 implicit color concepts, grounded in 6,584 human annotations. Our evaluation of nine leading T2I models reveals that performance varies substantially across semantic categories, and models exhibit a significant lack of sensitivity to abstract semantics. These limitations persist even when applying classifier-free guidance scaling at inference time, suggesting that achieving human-like color understanding demands a shift in how models learn and represent implicit semantic meaning.

cs.CV↗
arXiv2026

Gangqinpu: A Multi-Genre, Multi-Task Piano Dataset with Aligned Audio, MIDI, and Musical Scores

Aligned audio, performance MIDI, and musical scores provide valuable supervision for music analysis and performance modeling, yet datasets that jointly align all three modalities remain scarce and limited in scale and genre diversity. We introduce Gangqinpu, a multi-genre piano dataset containing 18,786 score-performance pairs and 1,007.1 hours of source audio, with automatic note-level alignments and derived beat/downbeat annotations. It spans diverse genres, including pop, classical, jazz, folk/traditional, rock, and blues. Our automated pipeline transcribes piano audio, aligns the resulting MIDI with musical scores, assigns genre labels, and filters out non-expressive performances with a score-informed binary classifier. We further construct joint splits with ASAP using conservative score-similarity grouping to reduce data leakage. We evaluate Gangqinpu on performance MIDI-to-score transcription, expressive performance rendering, and beat tracking. Downstream experiments demonstrate the value of Gangqinpu as complementary training data, with cross-dataset gains in beat tracking and primarily in-domain benefits for transcription and expressive performance rendering. The code and dataset are publicly available at https://github.com/wei-zeng98/gangqinpu.

cs.SD↗
arXiv2026

DragonMoCap: Monocular Video-based Motion Capture for Diverse Dragon Topologies

This work explores monocular motion capture for dragon-type characters, which currently relies on manual keyframing due to the lack of high-quality datasets and parametric models. The primary obstacle lies in the extreme topological diversity across dragon rigs, where varying joint counts and naming conventions render traditional fixed-template regressors inapplicable. To address this, we introduce DragonMoCap, a novel framework that treats the target rig as a dynamic input rather than a fixed prior. By deliberately scoping the framework to the most prevalent production topologies, we ensure high-fidelity results across diverse morphologies. The core of our approach is the design of language-grounded joint query tokens, which establish a dual-property representation: ensuring intra-rig discriminability while maintaining cross-rig similarity. We further propose a non-parametric query-token retrieval mechanism to enable zero-shot adaptation to unseen rigs without retraining. Extensive evaluations demonstrate that DragonMoCap consistently outperforms HMR-style baselines across diverse dragon topologies. The practical utility of our framework is further evidenced by its integration into professional animation workflows, highlighting its potential for real-time industrial applications.

cs.CV↗
arXiv2026

DuET: Note-Frame Dual Encoding for Piano Performance-to-Score Transcription

Transcribing expressive piano performances into scores requires interpreting individual note timings within an underlying metrical structure. However, score attributes are associated with notes, whereas beats may occur without coincident note onsets. We introduce DuET, a Dual-Encoder Transformer that jointly learns note-level performance MIDI-to-score (PM2S) transcription and frame-level beat and downbeat tracking. Bidirectional cross-attention connects note and frame encoders, while an autoregressive decoder alternates between their representations to predict structured score attributes. We further introduce TimeRoPE and Time-Pitch Rotary Positional Encoding (TPRoPE) to establish a shared performance-time reference and explicitly encode relative temporal and pitch relationships. Evaluations on ASAP, a classical piano dataset, and our curated Gangqinpu dataset, which spans multiple genres with a focus on popular piano music, demonstrate improvements in score timing and notated duration. Compared with the strongest baseline on each dataset, DuET reduces MUSTER mean error from 6.56% to 3.64% on Gangqinpu and from 11.30% to 11.22% on ASAP. Ablations support the benefits of frame-level context, time-based positional encoding, and decoder-history masking. Code, weights, and demos are available at https://github.com/wei-zeng98/DuET.

cs.SD↗
arXiv2026

Edit Who Speaks, Control How They Speak: Global Timbre Editing and Local Instruction Control for TTS

Instruction-based text-to-speech (TTS) offers control over voice characteristics and speech expression through interfaces including voice cloning and text-based voice design. Voice cloning reproduces a reference voice, whereas text-based voice design creates a voice from a natural-language description. However, neither interface directly enables users to modify the timbre of a given reference and synthesize speech with the modified voice. Meanwhile, utterance-level expressive instructions leave changes across individual text segments underspecified. We introduce \textbf{EDICT}, a framework that unifies global timbre editing and local expressive control by using an edited acoustic reference to anchor voice identity across segments. To enable synthesis with an instruction-edited voice, EDICT combines reference audio with structured timbre edits to generate an edited reference in codec-token space. This representation serves as a shared voice anchor for a frozen TTS backbone, allowing segment-specific natural-language instructions to guide expression. To accommodate instruction changes while supporting acoustic continuity, EDICT rebuilds the KV cache at each segment boundary, refreshing instruction conditioning while retaining bounded acoustic context from previously generated speech. Evaluations on our proposed TimbreEdit-Bench and IntraTTS-Bench demonstrate improved timbre editing and a favorable balance between local instruction adherence, speaker consistency, and transition quality. Audio demos are available.

cs.SD↗
arXiv2026

MarvisNav: Making Memory Visible on Route Choices for Zero-Shot Object Navigation

When searching for an object, people choose their next move by considering both likely target locations and places already explored. The current view can cue place-associated memories, bringing target relevance and prior exploration into the same spatial context. In many zero-shot object navigation (ZSON) methods, however, vision-language models (VLMs) infer promising search areas from egocentric images, while exploration history is represented separately, e.g., as text or maps. This separation either requires an additional fusion step or leaves the correspondence between memory and route choices implicit for the VLM to recover. We instead make exploration memory directly visible on visual route choices. We propose MarvisNav, a ZSON framework that maintains a topological graph and projects candidate nodes together with their exploration states onto egocentric views as memory-bearing visual route choices. These states capture local exploration progress beyond binary visitation. By binding exploration state directly to each visual candidate, MarvisNav enables the VLM to jointly evaluate target relevance and exploration state without a separate post-hoc fusion or reranking stage. Without policy training, MarvisNav achieves state-of-the-art performance on HM3D (81.2% SR and 42.5% SPL), while remaining competitive on MP3D. It also outperforms representative VLM-based methods with far fewer VLM calls (e.g., 7.5% of WMNav). Real-robot experiments across diverse scenes further validate its practical deployability. Beyond MarvisNav, our study shows that memory representation shapes VLM decisions and ZSON performance, highlighting that effective memory use depends not only on its availability, but also on how it is represented. Code and project page will be available at \url{https://wangjincheng1998.github.io/MarvisNav/}.

cs.RO↗
arXiv2026

Algebraic and Topological Study of Bell States and Quantum Teleportation

Bell states and quantum teleportation play crucial roles in quantum information and computation. However, a comprehensive theoretical study of both topics remains to be carried out. This work aims to investigate key algebraic properties of generalized Bell states and explore the topological features of quantum teleportation. First, the basis theorem and the basis group are introduced to show that the extension of a generalized Bell basis by a unitary matrix still forms an orthonormal basis. Then, a twist operator is defined to establish a connection between a generalized multi-qubit Bell state and a tensor product of two-qubit Bell states. In addition, the Temperley--Lieb algebra, the braid group relations, and the Yang--Baxter equation are employed to provide a topological description of generalized Bell states and quantum teleportation. The results demonstrate that our approach not only offers a clear illustration of relevant quantum information protocols but also reveals the topological nature of quantum entanglement and teleportation.

quant-ph↗
arXiv2026

RAGE-Vis:A Relation-Aware Generative Editing Interface for Natural Language-Based Chart Editing

Natural language offers an easy way for users to express chart editing intents, which are often composite and cross-component (e.g., adjusting style, extending categories, highlighting values). However, existing methods typically map instructions to a single operation or widget, limiting their ability to handle high-level requests and often producing locally plausible but globally inconsistent results due to a lack of awareness of relationships between chart components. To address these challenges, we introduce RAGE-Vis, a Relation-Aware Generative Editing interface for natural language-based chart editing. The system supports bitmap chart images as input and converts them into an editable parameterized intermediate representation. Instead of mapping instructions to a single edit or widget, RAGE-Vis parses composite intents, identifies targets and scopes, and generates hierarchical editing panels for underspecified requests, enabling users to adjust both global settings and local parameters. Furthermore, RAGE-Vis identifies potentially affected fields based on visual encoding relations, structural relationships, and expressive consistency relations, and organizes them into actionable widgets to support cross-component coordinated controls. Through two case studies, we demonstrate the applicability of RAGE-Vis in complex editing tasks, including style adjustment, data extension, order rearrangement, legend layout, and color mapping. A user study further shows that participants can effectively handle underspecified requests, explore candidate alternatives, and maintain cross-component consistency with RAGE-Vis.

cs.HC↗
arXiv2026

REChart: Reasoning-Efficient Chart Editing with Large Reasoning Models

Chart editing requires inferring and modifying visualization code from a reference chart image based on an editing instruction, challenging fine-grained visual reasoning, instruction following, and executable code synthesis capabilities of MLLMs. Large reasoning models (LRMs) with extended Chain-of-Thought (CoT) reasoning are suitable for tackling such complex multimodal tasks. However, our preliminary study reveals an ``inverted-U'' relationship between reasoning length and chart-editing performance: Excessive reasoning often leads to ``overthinking,'' where models drift toward hallucinated visual details or get stuck in redundant reasoning loops. To address the gap, we introduce REChart, a two-stage training framework that provides process-level supervision over intermediate reasoning steps, improving both editing fidelity and reasoning efficiency. First, we synthesize 200k high-quality reasoning trajectories for supervised fine-tuning from a large image-instruction-code pool, using a role-specialized agentic Reason-Score-Refine workflow that iteratively refine the chart code toward higher quality. Second, we optimize the model via reinforcement learning with two complementary rewards: a \emph{fidelity} reward evaluating code correctness, visual fidelity, and structural consistency, and an \emph{efficiency} reward that assigns each rollout a random thinking budget, truncates the reasoning process, and credits the final reasoning segment according to its contribution to the output. On the ChartEdit and ChartMIMIC benchmarks, our model achieves state-of-the-art chart-editing performance among open-source models of comparable scale, while mitigating overthinking and reducing average reasoning token usage by 79.0\% under a maximum thinking budget of 16,384 tokens compared with the base model.

cs.CV↗
arXiv2026

HAM-RAG: Hierarchy-Aware Multimodal RAG for Structure-Faithful Interleaved Generation

Existing multimodal RAG methods often flatten structured documents into isolated text and image units, weakening the source organization and local text-image logic needed for faithful evidence selection and placement. We propose HAM-RAG, a Hierarchy-Aware Multimodal RAG framework for structure-faithful interleaved generation. HAM-RAG uses document hierarchy as a grounding signal across retrieval and generation, contextualizing textual and visual evidence and preserving source position and local text-image relations in the prompt. We further introduce HAM-Bench, covering Wukong, Wiki, arXiv, and Recipe across game walkthroughs, web pages, scientific papers, and step-wise recipe documents. Across multiple backbones, HAM-RAG improves the main multimodal average by 17.3% over the strongest non-hierarchical baseline. On Wukong, HAM-RAG improves Img-CBS by 24.2% over the strongest non-hierarchical baseline, demonstrating substantially better local text-image alignment. The main experiments and ablation study together demonstrate that document hierarchy is a key grounding signal for faithful image selection, placement, and local text-image alignment. These findings highlight the value of hierarchy-aware grounding for reliable multimodal assistants that generate answers faithful to the source organization, procedural structure, and local text-image evidence of structured documents, such as technical manuals, maintenance guides, and industrial SOPs. The code is available at https://github.com/MCCodeAI/HAM-RAG.git.

cs.IR↗
arXiv2026

Walking through Discussions: A Mobile Visual Analytics System for In-Situ Group Discussion Analysis

Group discussion-based teaching is widely used to foster collaborative learning, yet teachers in physical classrooms often struggle to simultaneously monitor multiple groups and quickly diagnose a target group before intervening. Existing visual analytics tools primarily support post-hoc analysis on desktop, providing limited support for in-situ walk-around teaching. To address this gap, we present MobileGroupVis, a mobile visual analytics system for in-situ analysis of classroom group discussions. MobileGroupVis integrates multi-group monitoring, single-group diagnosis, and instructional intervention into a concise analytical workflow tailored for small-screen touch interaction. The system is powered by a lightweight streaming analysis pipeline that converts group audio into structured discussion data and further extracts interaction patterns, topic progression, and topic deviation through a dialogue analysis module. To enable both glanceable overview and traceable diagnosis, we design six coordinated views, including a compact glyph that visually encodes word count, interaction intensity, and topic deviation for efficient cross-group comparison and anomaly localization, along with detailed views for opinion evolution, interaction dynamics, topic coverage, and dialogue records. We evaluate MobileGroupVis through two case studies and expert interviews. The results provide preliminary evidence that MobileGroupVis supports teachers in understanding discussion processes, identifying groups in need of attention, and facilitating in-class intervention.

cs.AI↗
arXiv2026

402Pilot: An x402 Decision Layer for Autonomous Agent Micropayments

Programmable-payment protocols such as x402 enable per-request micropayments, but they do not determine which payable service an autonomous agent should buy under a finite wallet. We formulate this buyer-side problem as agent-native payment decision-making: contextual provider selection under wallet pressure, chosen-only paid feedback, and changing market conditions. We propose 402Pilot, a protocol-agnostic buyer-side decision layer between autonomous agents and payment execution that implements purchasing policies for selecting among payable providers. We instantiate it with PA-DCT, a payment-aware discounted contextual Thompson-sampling policy that adapts purchasing decisions under wallet pressure while learning from post-payment feedback. To evaluate buyer-side payment policies, we introduce 402Pilot-Bench, a frozen-replay benchmark spanning 823 tasks, five heterogeneous provider pipelines, and three market regimes, each evaluated over 30 paired seeds. PA-DCT achieves the strongest fixed-wallet adaptive trade-off among non-oracle policies: it maintains competitive service quality while spending only 39 to 43 percent of the wallet and reallocates spending as market conditions change. It attains the best non-oracle PA-gap/T under the price shock and the best mean and worst-case ranks across the nine scenario-metric combinations of quality, ROI, and PA-gap/T. Comparisons with learning baselines and component ablations further support the effectiveness and design of the proposed decision policy. These results suggest that programmable payment must be complemented by buyer-side decision-making capable of learning service value and adapting purchasing decisions accordingly.

cs.AI↗
arXiv2026

Keypoint-Guided Optimal Transport: Models, Algorithms, and Applications

Existing Optimal Transport (OT) methods mainly derive the optimal transport plan/matching under the criterion of transport cost/distance minimization, which may cause incorrect matching in some cases. In real applications, annotating a few matched keypoints across domains is reasonable or even efortless in annotation burden. It is valuable to investigate how to leverage the annotated keypoints to guide the correct matching in OT. In this paper, we propose a novel KeyPoint-Guided model by ReLation preservation (KPG-RL)that searches for the optimal matching (i.e., transport plan) guided by the keypoints in OT.KPG-RL exploits a mask-based constraint of the transport plan to preserve the matching of keypoint pairs in transport, and guides the matching by relation of each data point to the keypoints. The KPG-RL is developed in both balanced and unbalanced/partial transport settings in Kantorovich and Gromov-Wasserstein formulations. Moreover, we deduce the dual formulation of $χ^2$-regularized KPG-RL model, from which we learn the transport based on deep learning techniques, scaling better to larger numbers of data. With the learned transport plan, two novel neural transport strategies, named manifold barycentric projection and manifold sampling, are developed to transport source data to the target domain data manifold. As applications, we apply the proposed approach to the heterogeneous domain adaptation, multi-omic single-cell alignment, and image-to-image translation. Experiments verifed the efectiveness of our approach.

cs.CV↗
arXiv2026

VisTR: Visualizations as Representations for Time-series Table Reasoning

Time-series table reasoning interprets temporal patterns and relationships in data to answer user queries. Despite recent advancements leveraging large language models (LLMs), existing methods often struggle with pattern recognition, context lost in long time-series data, and the lack of visual-based reasoning capabilities. To address these challenges, we propose VisTR, a framework that places visualizations at the core of the reasoning process. Specifically, VisTR leverages visualizations as representations to bridge raw time-series data and human cognitive processes. By transforming tables into fixed-size visualization references, it captures key trends, anomalies, and temporal relationships, facilitating intuitive and interpretable reasoning. These visualizations are aligned with user input, i.e., charts, text, and sketches, through a fine-tuned multimodal LLM, ensuring robust cross-modal alignment. To handle large-scale data, VisTR integrates pruning and indexing mechanisms for scalable and efficient retrieval. Finally, an interactive visualization interface supports seamless multimodal exploration, enabling users to interact with data through both textual and visual modalities. Quantitative evaluations demonstrate the effectiveness of VisTR in aligning multimodal inputs and improving reasoning accuracy. Case studies further illustrate its applicability to various time-series reasoning and exploration tasks.

cs.HC↗
arXiv2026

MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills

AI coding agents such as Claude Code and Gemini CLI increasingly extend themselves with third-party skills: markdown packages bundling natural-language instructions, executable scripts, and tool permissions. Because a skill is at once code and agent-facing instruction, it introduces a supply chain dependency whose risk is neither pure code nor pure prompt. Detection tools have never been measured against verified ground truth spanning this hybrid space, leaving their effectiveness unknown and wild-only evaluations biased. We present MalSkillBench, the first runtime-verified benchmark of malicious agent skills: 3,944 malicious skills labeled along a three-dimensional taxonomy of 108 cells. Of these, 3,214 come from a closed-loop Generate-Verify-Feedback pipeline admitting only samples whose malicious behavior fires inside a Docker sandbox under system-call monitoring and an LLM judge; we add 703 in-the-wild and 4,000 matched benign skills. Our measurements are consistent: code injection reaches 94.5% verification yield but prompt injection only 75.8%, the same fragility that later makes it hard to detect; the wild sample is narrow, dominated by one cryptocurrency-theft campaign (86.6% one behavior, 81% from two accounts) with a small but architecturally new tail attacking the agent control plane; the strongest skill-specific detector reaches 98.4% recall on code injection yet collapses on prompt-injection and agent-control attacks, and wild-only scoring swings the ranking by up to 66 recall points; supply-chain scanners and prompt-injection defenses each see only half of a skill, and no combination recovers the code-instruction relationship. Detecting malicious skills therefore requires reasoning jointly over task intent, code, and instructions. We release the dataset, pipeline, baselines, and results.

cs.CR↗
arXiv2026

Uncertainty-Guided Dual-Domain Learning for Reliable Skin Lesion Segmentation

Accurate skin lesion segmentation is vital for dermoscopic Computer-Aided Diagnosis. However, visual ambiguity and morphological irregularity often defeat spatial modeling, necessitating multi-domain architectures. Existing paradigms frequently overlook the active use of prediction uncertainty, leading to deterministic frameworks that suffer from blind cross-domain fusion and overfit to label noise. To address these issues, we propose the Uncertainty-Guided Dual-Domain Network (UGDD-Net). UGDD-Net introduces a novel "Glance-and-Gaze" mechanism to transform uncertainty into an active guiding signal. Specifically, the Uncertainty-Guided Bi-directional Feature Fusion (UGBFF) module uses pixel-level uncertainty to modulate spatial-spectral interactions. The Uncertainty-Guided Graph Refinement (UGGR) module constructs a topology-aware graph to propagate reliable semantic consensus and refine uncertain nodes. Finally, the Uncertainty-Guided Margin-Adaptive Loss (UGML) enforces strict constraints on confident pixels while relaxing penalties on uncertain ones to improve statistical calibration. Extensive experiments on ISIC2017, ISIC2018, PH2, and HAM10000 datasets demonstrate that UGDD-Net achieves state-of-the-art performance, especially on "Hard Samples". Our uncertainty maps align with expert inter-observer variability, providing robust interpretability for human-machine collaborative diagnosis.

eess.IV↗
arXiv2026

BizCompass: Benchmarking the Reasoning Capabilities of LLMs in Business Knowledge and Applications

Large language models (LLMs) hold great promise for business applications, yet business analysis remains inherently complex, demanding rigorous reasoning and the integration of diverse knowledge sources. Existing benchmarks typically target narrow tasks and thus leave a fundamental question unanswered: how can LLMs be reliably applied in business, and how are these applications grounded in underlying theoretical capabilities? To address this gap, we introduce BizCompass, a benchmark explicitly designed to connect theoretical foundations with practical business knowledge and applications. At the knowledge level, BizCompass covers four core domains--finance, economics, statistics, and operations management. At the application level, it structures tasks around three representative roles: the analyst, the trader, and the consultant. This dual-axis design not only exposes performance differences across realistic scenarios but also diagnoses which foundational capabilities enable or constrain success. We systematically evaluate both open-source and commercial LLMs, revealing how theoretical knowledge translates into practical performance in business. The results provide actionable insights for model selection and training optimization in real-world business contexts. All datasets and evaluation code are publicly released to support reproducibility and future research: https://bizcompass.dev.ypemc.com.

cs.CE↗
arXiv2026

CoMelSinger: Discrete Token-Based Zero-Shot Singing Synthesis With Structured Melody Control and Guidance

Singing Voice Synthesis (SVS) aims to generate expressive vocal performances from structured musical inputs such as lyrics and pitch sequences. While recent progress in discrete codec-based speech synthesis has enabled zero-shot generation via in-context learning, directly extending these techniques to SVS remains non-trivial due to the requirement for precise melody control. In particular, prompt-based generation often introduces prosody leakage, where pitch information is inadvertently entangled within the timbre prompt, compromising controllability. We present CoMelSinger, a zero-shot SVS framework that enables structured and disentangled melody control within a discrete codec modeling paradigm. Built on the non-autoregressive MaskGCT architecture, CoMelSinger replaces conventional text inputs with lyric and pitch tokens, preserving in-context generalization while enhancing melody conditioning. To suppress prosody leakage, we propose a coarse-to-fine contrastive learning strategy that explicitly regularizes pitch redundancy between the acoustic prompt and melody input. Furthermore, we incorporate a lightweight encoder-only Singing Voice Transcription (SVT) module to align acoustic tokens with pitch and duration, offering fine-grained frame-level supervision. Experimental results demonstrate that CoMelSinger achieves notable improvements in pitch accuracy, timbre consistency, and zero-shot transferability over competitive baselines. Audio samples are available at https://danny-nus.github.io/CoMelSinger/.

cs.SD↗