arXiv subjects

Han Feng

Publications and source records attributed to Han Feng.

At least 19 recordsLinked to original sources

arXiv2026

PersonaShot: Benchmarking Person-Centric Narrative Continuity in Multi-Shot Video Generation

Video generation is rapidly evolving from single-shot clips to multi-shot narratives, where the human character serves as the core narrative anchor. However, existing benchmarks mainly assess character appearance or individual-shot quality, without measuring whether physical and emotional states remain coherent across cuts. They also rarely provide criterion-specific evaluation methods, although physical continuity, facial dynamics, and cinematic relations require different visual, temporal, and relational evidence. To address these limitations, we introduce PersonaShot, the first person-centric benchmark for narrative continuity in multi-shot video generation. PersonaShot contains approximately 1,000 multi-shot segments and 16 metrics spanning physical continuity, affective dynamics, and cinematic grammar. \textbf{\textit{1)} Narrative Continuity Benchmark:} We evaluate character coherence across three temporal levels: within-shot states, cross-shot transitions, and sequence-level trajectories. \textbf{\textit{2)} Human-Aligned Specialist Evaluators:} We distill reasoning from a large multimodal teacher into lightweight criterion-specific evaluators, each grounded in the visual, temporal, or relational evidence required by its metric, and align them with expert human judgments. \textbf{\textit{3)} Systematic Evaluation and Insights:} Our evaluation reveals distinct capability profiles across state-of-the-art models and a clear gap between perceptual quality and cross-shot narrative continuity. Even visually compelling videos frequently exhibit physical-state resets, abrupt affective shifts, and broken cinematic relations across shots. Human studies further demonstrate strong agreement between our evaluators and expert judgments.

cs.CV↗

arXiv2026

VicEdit: Learning to Edit Videos from Visual In-Context Examples

Despite progress in instruction-based video editing, unimodal textual instructions inherently struggle to convey fine-grained textures and complex dynamics. To bridge this perceptual gap, we propose Visual In-context Editing, a new paradigm elevating video editing from textual instructions to multi-modal visual guidance encompassing single image, image pair, and video pair. To facilitate this paradigm, we curate VicEdit-400K, the first large-scale dataset for visual in-context video editing. We develop an automated pipeline to generate 400K high-quality samples across ten task types, ensuring superior visual fidelity and semantic consistency through multi-dimensional filtering. Leveraging this foundation, we introduce VicEdit, a unified framework to bridge visual and textual contexts. To adaptively extract editing semantics from heterogeneous references, we design Modality-Adaptive Semantic Distillation, which produces modality-specific semantic tokens from visual references. These tokens are then synergistically integrated with textual instructions through Dual-Context Injection, enabling the generation process to benefit from both visual and textual signals. Extensive evaluations on VicEditBench demonstrate that VicEdit achieves state-of-the-art performance across both basic instruction editing and visual in-context editing tasks, establishing visual in-context learning as a powerful and controllable paradigm for video editing.

cs.CV↗

arXiv2026

Intervention-Aware Clinical World Model for Post-Op Outcome Forecasting in Cardiology

Many clinical prediction models treat post-intervention outcomes as a one-step mapping from baseline measurements to a future endpoint. However, recovery after a procedure often unfolds as an irregular trajectory: clinical observations, medication changes, repeat interventions, and physiological measurements are recorded asynchronously and can change risk assessment over time. We propose an intervention-aware clinical world model that represents each patient with a structured latent state and evolves it through time-ordered post-intervention events. The model first encodes baseline imaging into a 3D spatial latent state. It then updates this state using procedural context, static covariates, elapsed time, and peri-event physiological embeddings. Follow-up imaging provides training-only supervision through a latent forecasting objective. We apply the framework to atrial fibrillation ablation. During the 90-day recovery window, irregular post-procedure records provide clinically meaningful evidence for long-term recurrence risk. In repeated internal cross-validation on DECAAF-II, our model achieves AUROC 0.756 and AUPRC 0.777 for recurrence prediction. It also achieves a scar-extent MAE of 2.971 percentage points without requiring follow-up MRI intensities at inference. The learned state supports recurrence-risk queries at different horizons and retrospective input editing of blanking-period records.

cs.LG↗

arXiv2026

In-Context Forcing: Uncovering Context Effects in Autoregressive Video Diffusion

Current few-step autoregressive video diffusion models depend on previous fully denoised clean frames as context for all denoising steps of the current frame. However, these clean frames leak excessive local details, which causes the model to take shortcuts, resulting in compromised temporal semantics and dynamics. Inspired by the perspective of diffusion as masking, we explore the impact of noisy contexts on few-step autoregressive generation. Yet, simply applying contexts with the same noise levels provides insufficient guidance, leading to poor temporal consistency. To resolve this dilemma, we introduce In-Context Forcing, a progressive autoregressive paradigm that utilizes contexts with decreasing noise levels. By applying less masking to distant frames and more masking to adjacent ones, this approach provides adaptive guidance, effectively ensuring both robust temporal consistency and high inter-frame dynamics. Furthermore, by decoupling the strict dependence on previous clean frames, our paradigm enables cross-frame parallel denoising, achieving substantial inference acceleration without sacrificing performance. Extensive experiments on VBench demonstrate that our method significantly outperforms state-of-the-art approaches in both visual fidelity and inference speed.

cs.CV↗

arXiv2026

When and Why Na\"ive Diversification Works: A Simple Diagnostic Strategy

We explain the long-standing puzzle of na\"ive diversification with a simple, testable condition: equal weighting is minimum-variance optimal when the forecast-error covariance matrix has a uniform eigenstructure. This "Golden Criterion" drives a two-stage adaptive strategy that dynamically blends naive and optimized weights based on the empirical distance from this condition. Applied to U.S. equity premium forecasting, the method delivers consistent out-of-sample gains in forecast accuracy, utility, and Sharpe ratios. Diversity-driven shrinkage dominates at short horizons, while optimized weights regain their edge at longer horizons, offering clear horizon-dependent guidance for portfolio construction.

econ.GN↗

arXiv2026

CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesis

Foundation diffusion models can generate photorealistic natural images, but adapting them to medical imaging remains challenging. In medical adaptation, limited labeled data can exacerbate hallucination-like and clinically implausible synthesis, while existing metrics such as FID or Inception Score do not quantify per-image alignment with pathology-relevant criteria. We introduce the Clinical Alignment Score (CAS), a foundation-model-based proxy for clinical alignment that evaluates generated images along four complementary dimensions beyond visual fidelity. Building on CAS, we propose Clinical Reward-Aligned Finetuning (CRAFT), a reward-based adaptation framework that transfers medical knowledge from multimodal large language models and vision-language models through label-conditioned prompt enrichment, clinical checklists, and differentiable reward optimization. Across four diverse modalities, CRAFT improves CAS and downstream classification performance over strong adaptation baselines. Beyond average CAS gains, CRAFT reduces the empirical low-alignment tail below a real-image reference threshold by 5.5-34.7% points relative to the strongest baseline, corresponding to a 20.4% average relative reduction across datasets. These results indicate fewer hallucination-like generations under CAS, and are corroborated by out-of-family evaluator evaluation, structured checklist auditing, memorization analysis, and a blinded physician preference study on CheXpert.

cs.CV↗

arXiv2026

Isotropic Positive Definite Functions on Spheres

In this paper, we investigate the relationship between positive definite functions on the unit sphere $\sph$ and on the Euclidean space $\RR^d$. For the dimension $d$ to be odd, a new technique is developed to establish the inheritance of positive (semi-)definite property from $\RR^d$ to $\sph$ and the converse. For $d=2$, it is proved that a function defined by $$f_{\t,\delta}(t)=(\t-t)_+^\delta, \quad \delta\geq \f{d+1}2 $$ is positive definite on the unit sphere $\mathbb{S}^2$ by restricting $\t$ in an absolute range. Our results can verify a conjecture proposed by R.K. Beatson, W. zu Castell, Y. Xu and a sharp P\'{o}lya type criterion for positive definite functions on spheres.

math.CA↗

arXiv2026

Sparse-Aware Neural Networks for Nonlinear Functionals: Mitigating the Exponential Dependence on Dimension

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited interpretability. This work investigates how sparsity can help address these challenges in functional learning, a central ingredient in operator learning. We propose a framework that employs convolutional architectures to extract sparse features from a finite number of samples, together with deep fully connected networks to effectively approximate nonlinear functionals. Using universal discretization methods, we show that sparse approximators enable stable recovery from discrete samples. In addition, both the deterministic and the random sampling schemes are sufficient for our analysis. These findings lead to improved approximation rates and reduced sample sizes in various function spaces, including those with fast frequency decay and mixed smoothness. They also provide new theoretical insights into how sparsity can alleviate the curse of dimensionality in functional learning.

cs.LG↗

arXiv2026

Weighted Temporal Decay Loss for Learning Wearable PPG Data with Sparse Clinical Labels

Advances in wearable computing and AI have increased interest in leveraging PPG for health monitoring over the past decade. One of the biggest challenges in developing health algorithms based on such biosignals is the sparsity of clinical labels, which makes biosignals temporally distant from lab draws less reliable for supervision. To address this problem, we introduce a simple training strategy that learns a biomarker-specific decay of sample weight over the time gap between a segment and its ground truth label and uses this weight in the loss with a regularizer to prevent trivial solutions. On smartwatch PPG from 450 participants across 10 biomarkers, the approach improves over baselines. In the subject-wise setting, the proposed approach averages 0.715 AUPRC, compared to 0.674 for a fine-tuned self-supervised baseline and 0.626 for a feature-based Random Forest. A comparison of four decay families shows that a simple linear decay function is most robust on average. Beyond accuracy, the learned decay rates summarize how quickly each biomarker's PPG evidence becomes stale, providing an interpretable view of temporal sensitivity.

cs.LG↗

arXiv2026

Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks

Motivated by challenges in conditional generative modeling, where the target conditional density takes the form of a ratio f1 over f2, this paper develops a theoretical framework for approximating such ratio-type functionals. Here, f1 and f2 are kernel-based marginal densities that capture structured interactions, a setting central to diffusion-based generative models. We provide a concise proof for approximating these ratio-type functionals using deep neural networks with the SignReLU activation function, leveraging the activation's piecewise structure. Under standard regularity assumptions, we establish L^p(Omega) approximation bounds and convergence rates. Specializing to Denoising Diffusion Probabilistic Models (DDPMs), we construct a SignReLU-based neural estimator for the reverse process and derive bounds on the excess Kullback-Leibler (KL) risk between the generated and true data distributions. Our analysis decomposes this excess risk into approximation and estimation error components. These results provide generalization guarantees for finite-sample training of diffusion-based generative models.

cs.LG↗

arXiv2025

Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation

We propose a multimodal-driven framework for high-fidelity long-term digital human animation termed $\textbf{Soul}$, which generates semantically coherent videos from a single-frame portrait image, text prompts, and audio, achieving precise lip synchronization, vivid facial expressions, and robust identity preservation. We construct Soul-1M, containing 1 million finely annotated samples with a precise automated annotation pipeline (covering portrait, upper-body, full-body, and multi-person scenes) to mitigate data scarcity, and we carefully curate Soul-Bench for comprehensive and fair evaluation of audio-/text-guided animation methods. The model is built on the Wan2.2-5B backbone, integrating audio-injection layers and multiple training strategies together with threshold-aware codebook replacement to ensure long-term generation consistency. Meanwhile, step/CFG distillation and a lightweight VAE are used to optimize inference efficiency, achieving an 11.4$\times$ speedup with negligible quality loss. Extensive experiments show that Soul significantly outperforms current leading open-source and commercial models on video quality, video-text alignment, identity preservation, and lip-synchronization accuracy, demonstrating broad applicability in real-world scenarios such as virtual anchors and film production. Project page at https://zhangzjn.github.io/projects/Soul/

cs.CV↗

arXiv2025

Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model

Recent strides in video generation have paved the way for unified audio-visual generation. In this work, we present Seedance 1.5 pro, a foundational model engineered specifically for native, joint audio-video generation. Leveraging a dual-branch Diffusion Transformer architecture, the model integrates a cross-modal joint module with a specialized multi-stage data pipeline, achieving exceptional audio-visual synchronization and superior generation quality. To ensure practical utility, we implement meticulous post-training optimizations, including Supervised Fine-Tuning (SFT) on high-quality datasets and Reinforcement Learning from Human Feedback (RLHF) with multi-dimensional reward models. Furthermore, we introduce an acceleration framework that boosts inference speed by over 10X. Seedance 1.5 pro distinguishes itself through precise multilingual and dialect lip-syncing, dynamic cinematic camera control, and enhanced narrative coherence, positioning it as a robust engine for professional-grade content creation. Seedance 1.5 pro is now accessible on Volcano Engine at https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?type=GenVideo.

cs.CV↗

arXiv2025

StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

Realistic hair strand generation is crucial for applications like computer graphics and virtual reality. While diffusion models can generate hairstyles from text or images, these inputs lack precision and user-friendliness. Instead, we propose the first sketch-based strand generation model, which offers finer control while remaining user-friendly. Our framework tackles key challenges, such as modeling complex strand interactions and diverse sketch patterns, through two main innovations: a learnable strand upsampling strategy that encodes 3D strands into multi-scale latent spaces, and a multi-scale adaptive conditioning mechanism using a transformer with diffusion heads to ensure consistency across granularity levels. Experiments on several benchmark datasets show our method outperforms existing approaches in realism and precision. Qualitative results further confirm its effectiveness. Code will be released at [GitHub](https://github.com/fighting-Zhang/StrandDesigner).

cs.CV↗

arXiv2025

Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations

Identity-preserving text-to-video (IPT2V) generation, which aims to create high-fidelity videos with consistent human identity, has become crucial for downstream applications. However, current end-to-end frameworks suffer a critical spatial-temporal trade-off: optimizing for spatially coherent layouts of key elements (e.g., character identity preservation) often compromises instruction-compliant temporal smoothness, while prioritizing dynamic realism risks disrupting the spatial coherence of visual structures. To tackle this issue, we propose a simple yet effective spatial-temporal decoupled framework that decomposes representations into spatial features for layouts and temporal features for motion dynamics. Specifically, our paper proposes a semantic prompt optimization mechanism and stage-wise decoupled generation paradigm. The former module decouples the prompt into spatial and temporal components. Aligned with the subsequent stage-wise decoupled approach, the spatial prompts guide the text-to-image (T2I) stage to generate coherent spatial features, while the temporal prompts direct the sequential image-to-video (I2V) stage to ensure motion consistency. Experimental results validate that our approach achieves excellent spatiotemporal consistency, demonstrating outstanding performance in identity preservation, text relevance, and video quality. By leveraging this simple yet robust mechanism, our algorithm secures the runner-up position in 2025 ACM MultiMedia Challenge. Our code is available at https://github.com/rain152/IPVG.

cs.CV↗

arXiv2025

HOPS: High-order Polynomials with Self-supervised Dimension Reduction for Load Forecasting

Load forecasting is a fundamental task in smart grid. Many techniques have been applied to developing load forecasting models. Due to the challenges such as the Curse of Dimensionality, overfitting, and limited computing resources, multivariate higher-order polynomial models have received limited attention in load forecasting, despite their desirable mathematical foundations and optimization properties. In this paper, we propose low rank approximation and self-supervised dimension reduction to address the aforementioned issues. To further improve computational efficiency, we also utilize a fast Conjugate Gradient based algorithm for the proposed polynomial models. Based on the load datasets from the ISO New England, the proposed method high-order polynomials with self-supervised dimension reduction (HOPS) demonstrates higher forecasting accuracy over several competitive models. Additionally, experimental results indicate that our approach alleviates redundant variable construction, achieving better forecasts with fewer input variables.

cs.LG↗

arXiv2024

Deeper Insights into Deep Graph Convolutional Networks: Stability and Generalization

Graph convolutional networks (GCNs) have emerged as powerful models for graph learning tasks, exhibiting promising performance in various domains. While their empirical success is evident, there is a growing need to understand their essential ability from a theoretical perspective. Existing theoretical research has primarily focused on the analysis of single-layer GCNs, while a comprehensive theoretical exploration of the stability and generalization of deep GCNs remains limited. In this paper, we bridge this gap by delving into the stability and generalization properties of deep GCNs, aiming to provide valuable insights by characterizing rigorously the associated upper bounds. Our theoretical results reveal that the stability and generalization of deep GCNs are influenced by certain key factors, such as the maximum absolute eigenvalue of the graph filter operators and the depth of the network. Our theoretical studies contribute to a deeper understanding of the stability and generalization properties of deep GCNs, potentially paving the way for developing more reliable and well-performing models.

cs.LG↗

arXiv2024

Spherical Analysis of Learning Nonlinear Functionals

In recent years, there has been growing interest in the field of functional neural networks. They have been proposed and studied with the aim of approximating continuous functionals defined on sets of functions on Euclidean domains. In this paper, we consider functionals defined on sets of functions on spheres. The approximation ability of deep ReLU neural networks is investigated by novel spherical analysis using an encoder-decoder framework. An encoder comes up first to accommodate the infinite-dimensional nature of the domain of functionals. It utilizes spherical harmonics to help us extract the latent finite-dimensional information of functions, which in turn facilitates in the next step of approximation analysis using fully connected neural networks. Moreover, real-world objects are frequently sampled discretely and are often corrupted by noise. Therefore, encoders with discrete input and those with discrete and random noise input are constructed, respectively. The approximation rates with different encoder structures are provided therein.

cs.LG↗

arXiv2024

Computing the Proximal Operator of the $q$-th Power of the $\ell_{1,q}$-norm for Group Sparsity

In this note, we comprehensively characterize the proximal operator of the $q$-th power of the $\ell_{1,q}$-norm (denoted by $\ell_{1,q}^{q}$) with $0\!<\!q\!<\!1$ by exploiting the well-known proximal operator of $|\cdot|^q$ on the real line. In particular, much more explicit characterizations can be obtained whenever $q\!=\!1/2$ and $q\!=\!2/3$ due to the existence of closed-form expressions for the proximal operators of $|\cdot|^{1/2}$ and $|\cdot|^{2/3}$. Numerical experiments demonstrate potential advantages of the $\ell_{1,q}^{q}$ regularization in the }inter-group and intra-group sparse vector recovery.

math.NA↗