arXiv subjects

Yicheng Pan

Publications and source records attributed to Yicheng Pan.

At least 19 recordsLinked to original sources

arXiv2026

SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer

Real-time streaming video-to-video editing (V2V) is critical for interactive applications such as live broadcasting and gaming, yet it remains a formidable challenge due to the stringent requirements for temporal consistency and inference throughput. In this paper, we present SANA-Streaming, a system-algorithm co-designed framework for high-resolution, real-time streaming video editing on consumer GPUs, with the following three core designs: (1) Hybrid Diffusion Transformer architecture introduces softmax attention in part of the blocks to improve local modeling capabilities while preserving the efficiency of linear layers. (2) Cycle-Reverse Regularization is a novel training strategy that enforces semantic consistency by predicting source frames from generated content via flow matching, improving temporal consistency without requiring paired long edited videos. (3) Efficient System Co-design combines fused GDN kernels and Mixed-Precision Quantization (MPQ) optimized for the NVIDIA Blackwell (RTX 5090) architecture. By profiling real-world throughput, our MPQ maximizes Tensor Core utilization while maintaining generation quality. The resulting system achieves real-time 1280 x 704 resolution editing at 24 end-to-end FPS on a single RTX 5090 GPU, with the DiT core running at 58 FPS. Experimental results demonstrate that our co-design approach significantly outperforms existing SOTA methods in both temporal coherence and system throughput.

cs.CV↗

arXiv2026

Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning

Despite rapid advancements, current text-to-image (T2I) models predominantly rely on a single-step generation paradigm, which struggles with complex semantics and faces diminishing returns from parameter scaling. While recent multi-step reasoning approaches show promise, they are hindered by ungrounded planning hallucinations lacking verification, monolithic post-hoc reflection, long-context optimization instabilities, and prohibitive inference latency. To overcome these bottlenecks, we propose the Closed-Loop Visual Reasoning (CLVR) framework, a comprehensive system that deeply couples visual-language logical planning with pixel-level diffusion generation. CLVR introduces an automated data engine with step-level visual verification to synthesize reliable reasoning trajectories, and proposes Proxy Prompt Reinforcement Learning (PPRL) to resolve long-context optimization instabilities by distilling interleaved multimodal histories into explicit reward signals for accurate causal attribution. Furthermore, to mitigate the severe latency bottleneck caused by iterative denoising, we propose $\Delta$-Space Weight Merge (DSWM), a theoretically grounded method that fuses alignment weights with off-the-shelf distillation priors, reducing the per-step inference cost to just 4 NFEs without requiring expensive re-distillation. Extensive experiments demonstrate that CLVR outperforms existing open-source baselines across multiple benchmarks and approaches the performance of proprietary commercial models, unlocking general test-time scaling capabilities for complex visual generation.

cs.CV↗

arXiv2026

Learning to Solve the Quadratic Assignment Problem with Warm-Started MCMC Finetuning

The quadratic assignment problem (QAP) is a fundamental NP-hard task that poses significant challenges for both traditional heuristics and modern learning-based solvers. Existing QAP solvers still struggle to achieve consistently competitive performance across structurally diverse real-world instances. To bridge this performance gap, we propose PLMA, an innovative permutation learning framework. PLMA features an efficient warm-started MCMC finetuning procedure to enhance deployment-time performance, leveraging short Markov chains to anchor the adaptation to the promising regions previously explored. For rapid exploration via MCMC over the permutation space, we design an additive energy-based model (EBM) that enables an $O(1)$-time 2-swap Metropolis-Hastings sampling step. Moreover, the neural network used to parameterize the EBM incorporates a scalable and flexible cross-graph attention mechanism to model interactions between facilities and locations in the QAP. Extensive experiments demonstrate that PLMA consistently outperforms state-of-the-art baselines across various benchmarks. In particular, PLMA achieves a near-zero average optimality gap on QAPLIB, exhibits remarkably superior robustness on the notoriously difficult Taixxeyy instances, and also serves as an effective QAP solver in bandwidth minimization.

cs.LG↗

arXiv2026

Classical counterparts of shortcuts to adiabaticity in nonlinear dissipative Lagrangian systems

Shortcuts to adiabaticity (STA) were first developed in quantum dynamics to realize rapid transformations with suppressed residual excitations. Here we show how the same idea can be implemented in classical nonlinear dissipative Lagrangian systems. Using a coupled $r$-$\theta$ manipulator as an illustrative model, we perform inverse engineering on the Euler-Lagrange equations with Rayleigh dissipation by prescribing endpoint-stationary trajectories, obtaining the corresponding force and torque profiles and quantifying how geometric coupling amplifies errors and residual energy. We further compare smooth STA protocols with actuator-bounded time-optimal solutions and with proportional-integral-derivative tracking, which highlights a trade-off among smoothness, speed, and robustness. Finally, we introduce a single-shot correction based on one mid-course measurement to reduce the effect of early deviations while keeping the inputs nearly smooth. These results provide a practical bridge between quantum STA concepts and their classical counterparts.

quant-ph↗

arXiv2026

Beyond Paper-to-Paper: Structured Profiling and Rubric Scoring for Paper-Reviewer Matching

As conference submission volumes continue to grow, accurately recommending suitable reviewers has become a challenge. Most existing methods follow a ``Paper-to-Paper'' matching paradigm, implicitly representing a reviewer by their publication history. However, effective reviewer matching requires capturing multi-dimensional expertise, and textual similarity to past papers alone is often insufficient. To address this gap, we propose P2R, a training-free framework that shifts from implicit paper-to-paper matching to explicit profile-based matching. P2R uses general-purpose LLMs to construct structured profiles for both submissions and reviewers, disentangling them into Topics, Methodologies, and Applications. Building on these profiles, P2R adopts a coarse-to-fine pipeline to balance efficiency and depth. It first performs hybrid retrieval that combines semantic and aspect-level signals to form a high-recall candidate pool, and then applies an LLM-based committee to evaluate candidates under strict rubrics, integrating both multi-dimensional expert views and a holistic Area Chair perspective. Experiments on NeurIPS, SIGIR, and SciRepEval show that P2R consistently outperforms state-of-the-art baselines. Ablation studies further verify the necessity of each component. Overall, P2R highlights the value of explicit, structured expertise modeling and offers practical guidance for applying LLMs to reviewer matching.

cs.IR↗

arXiv2025

Structure-Guided Allocation of 2D Gaussians for Image Representation and Compression

Recent advances in 2D Gaussian Splatting (2DGS) have demonstrated its potential as a compact image representation with millisecond-level decoding. However, existing 2DGS-based pipelines allocate representation capacity and parameter precision largely oblivious to image structure, limiting their rate-distortion (RD) efficiency at low bitrates. To address this, we propose a structure-guided allocation principle for 2DGS, which explicitly couples image structure with both representation capacity and quantization precision, while preserving native decoding speed. First, we introduce a structure-guided initialization that assigns 2D Gaussians according to spatial structural priors inherent in natural images, yielding a localized and semantically meaningful distribution. Second, during quantization-aware fine-tuning, we propose adaptive bitwidth quantization of covariance parameters, which grants higher precision to small-scale Gaussians in complex regions and lower precision elsewhere, enabling RD-aware optimization, thereby reducing redundancy without degrading edge quality. Third, we impose a geometry-consistent regularization that aligns Gaussian orientations with local gradient directions to better preserve structural details. Extensive experiments demonstrate that our approach substantially improves both the representational power and the RD performance of 2DGS while maintaining over 1000 FPS decoding. Compared with the baseline GSImage, we reduce BD-rate by 43.44% on Kodak and 29.91% on DIV2K.

cs.CV↗

arXiv2025

Hyperbolic Continuous Structural Entropy for Hierarchical Clustering

Hierarchical clustering is a fundamental machine-learning technique for grouping data points into dendrograms. However, existing hierarchical clustering methods encounter two primary challenges: 1) Most methods specify dendrograms without a global objective. 2) Graph-based methods often neglect the significance of graph structure, optimizing objectives on complete or static predefined graphs. In this work, we propose Hyperbolic Continuous Structural Entropy neural networks, namely HypCSE, for structure-enhanced continuous hierarchical clustering. Our key idea is to map data points in the hyperbolic space and minimize the relaxed continuous structural entropy (SE) on structure-enhanced graphs. Specifically, we encode graph vertices in hyperbolic space using hyperbolic graph neural networks and minimize approximate SE defined on graph embeddings. To make the SE objective differentiable for optimization, we reformulate it into a function using the lowest common ancestor (LCA) on trees and then relax it into continuous SE (CSE) by the analogy of hyperbolic graph embeddings and partitioning trees. To ensure a graph structure that effectively captures the hierarchy of data points for CSE calculation, we employ a graph structure learning (GSL) strategy that updates the graph structure during training. Extensive experiments on seven datasets demonstrate the superior performance of HypCSE.

cs.LG↗

arXiv2025

UnCLe: Towards Scalable Dynamic Causal Discovery in Non-linear Temporal Systems

Uncovering cause-effect relationships from observational time series is fundamental to understanding complex systems. While many methods infer static causal graphs, real-world systems often exhibit dynamic causality-where relationships evolve over time. Accurately capturing these temporal dynamics requires time-resolved causal graphs. We propose UnCLe, a novel deep learning method for scalable dynamic causal discovery. UnCLe employs a pair of Uncoupler and Recoupler networks to disentangle input time series into semantic representations and learns inter-variable dependencies via auto-regressive Dependency Matrices. It estimates dynamic causal influences by analyzing datapoint-wise prediction errors induced by temporal perturbations. Extensive experiments demonstrate that UnCLe not only outperforms state-of-the-art baselines on static causal discovery benchmarks but, more importantly, exhibits a unique capability to accurately capture and represent evolving temporal causality in both synthetic and real-world dynamic systems (e.g., human motion). UnCLe offers a promising approach for revealing the underlying, time-varying mechanisms of complex phenomena.

cs.LG↗

arXiv2025

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer

We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution, high-quality and long videos with strong text-video alignment at a remarkably fast speed, deployable on RTX 5090 GPU. Two core designs ensure our efficient, effective and long video generation: (1) Linear DiT: We leverage linear attention as the core operation, which is more efficient than vanilla attention given the large number of tokens processed in video generation. (2) Constant-Memory KV cache for Block Linear Attention: we design block-wise autoregressive approach for long video generation by employing a constant-memory state, derived from the cumulative properties of linear attention. This KV cache provides the Linear DiT with global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient, minute-long video generation. In addition, we explore effective data filters and model training strategies, narrowing the training cost to 12 days on 64 H100 GPUs, which is only 1% of the cost of MovieGen. Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1-1.3B and SkyReel-V2-1.3B) while being 16x faster in measured latency. Moreover, SANA-Video can be deployed on RTX 5090 GPUs with NVFP4 precision, accelerating the inference speed of generating a 5-second 720p video from 71s to 29s (2.4x speedup). In summary, SANA-Video enables low-cost, high-quality video generation.

cs.CV↗

arXiv2025

Structural Information-based Hierarchical Diffusion for Offline Reinforcement Learning

Diffusion-based generative methods have shown promising potential for modeling trajectories from offline reinforcement learning (RL) datasets, and hierarchical diffusion has been introduced to mitigate variance accumulation and computational challenges in long-horizon planning tasks. However, existing approaches typically assume a fixed two-layer diffusion hierarchy with a single predefined temporal scale, which limits adaptability to diverse downstream tasks and reduces flexibility in decision making. In this work, we propose SIHD, a novel Structural Information-based Hierarchical Diffusion framework for effective and stable offline policy learning in long-horizon environments with sparse rewards. Specifically, we analyze structural information embedded in offline trajectories to construct the diffusion hierarchy adaptively, enabling flexible trajectory modeling across multiple temporal scales. Rather than relying on reward predictions from localized sub-trajectories, we quantify the structural information gain of each state community and use it as a conditioning signal within the corresponding diffusion layer. To reduce overreliance on offline datasets, we introduce a structural entropy regularizer that encourages exploration of underrepresented states while avoiding extrapolation errors from distributional shifts. Extensive evaluations on challenging offline RL tasks show that SIHD significantly outperforms state-of-the-art baselines in decision-making performance and demonstrates superior generalization across diverse scenarios.

cs.LG↗

arXiv2025

THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning

Large Language Models (LLMs) have made remarkable progress in mathematical reasoning, but still continue to struggle with high-precision tasks like numerical computation and formal symbolic manipulation. Integrating external tools has emerged as a promising approach to bridge this gap. Despite recent advances, existing methods struggle with three key challenges: constructing tool-integrated reasoning data, performing fine-grained optimization, and enhancing inference. To overcome these limitations, we propose THOR (Tool-Integrated Hierarchical Optimization via RL). First, we introduce TIRGen, a multi-agent based pipeline for constructing high-quality datasets of tool-integrated reasoning paths, aligning with the policy and generalizing well across diverse models. Second, to perform fine-grained hierarchical optimization, we introduce an RL strategy that jointly optimizes for both episode-level problem solving and step-level code generation. This is motivated by our key insight that the success of an intermediate tool call is a strong predictor of the final answer's correctness. Finally, THOR incorporates a self-correction mechanism that leverages immediate tool feedback to dynamically revise erroneous reasoning paths during inference. Our approach demonstrates strong generalization across diverse models, performing effectively in both reasoning and non-reasoning models. It further achieves state-of-the-art performance for models of a similar scale on multiple mathematical benchmarks, while also delivering consistent improvements on code benchmarks. Our code will be publicly available at https://github.com/JingMog/THOR.

cs.AI↗

arXiv2025

Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integration

Recent advances in Multimodal Large Language Models (MLLMs) have achieved remarkable progress in general domains and demonstrated promise in multimodal mathematical reasoning. However, applying MLLMs to geometry problem solving (GPS) remains challenging due to lack of accurate step-by-step solution data and severe hallucinations during reasoning. In this paper, we propose GeoGen, a pipeline that can automatically generates step-wise reasoning paths for geometry diagrams. By leveraging the precise symbolic reasoning, \textbf{GeoGen} produces large-scale, high-quality question-answer pairs. To further enhance the logical reasoning ability of MLLMs, we train \textbf{GeoLogic}, a Large Language Model (LLM) using synthetic data generated by GeoGen. Serving as a bridge between natural language and symbolic systems, GeoLogic enables symbolic tools to help verifying MLLM outputs, making the reasoning process more rigorous and alleviating hallucinations. Experimental results show that our approach consistently improves the performance of MLLMs, achieving remarkable results on benchmarks for geometric reasoning tasks. This improvement stems from our integration of the strengths of LLMs and symbolic systems, which enables a more reliable and interpretable approach for the GPS task. Codes are available at https://github.com/ycpNotFound/GeoGen.

cs.CL↗

arXiv2025

Dichotomies for \#CSP on graphs that forbid a clique as a minor

We prove complexity dichotomies for \#CSP problems (not necessarily symmetric) with Boolean domain and complex range on several typical minor-closed graph classes. These dichotomies give a complete characterization of the complexity of \#CSP on graph classes that forbid a complete graph as a minor. In particular, we also demonstrate that, whether the maximum degree of vertices is bounded may influence the complexity on specific minor-closed graph classes, and this phenomenon has never been observed in the previous related studies. Furthermore, our proofs integrate the properties of each graph class with the techniques from counting complexity, and develop a systematic approach for analyzing the complexity of \#CSP on these graph classes.

cs.CC↗

arXiv2025

Matchgate signatures under variable permutations

In this article, we give a sufficient and necessary condition for determining whether a matchgate signature retains its property under a certain variable permutation, which can be checked in polynomial time. We also define the concept of permutable matchgate signatures, and use it to erase the gap between Pl-\#CSP and \#CSP on planar graphs in the previous study. We provide a detailed characterization of permutable matchgate signatures as well, by presenting their relation to symmetric matchgate signatures. In addition, we prove a dichotomy for Pl-$\#R_D$-CSP where $D\ge 3$ is an integer.

math.CO↗

arXiv2024

HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification

Existing self-supervised methods in natural language processing (NLP), especially hierarchical text classification (HTC), mainly focus on self-supervised contrastive learning, extremely relying on human-designed augmentation rules to generate contrastive samples, which can potentially corrupt or distort the original information. In this paper, we tend to investigate the feasibility of a contrastive learning scheme in which the semantic and syntactic information inherent in the input sample is adequately reserved in the contrastive samples and fused during the learning process. Specifically, we propose an information lossless contrastive learning strategy for HTC, namely \textbf{H}ierarchy-aware \textbf{I}nformation \textbf{L}ossless contrastive \textbf{L}earning (HILL), which consists of a text encoder representing the input document, and a structure encoder directly generating the positive sample. The structure encoder takes the document embedding as input, extracts the essential syntactic information inherent in the label hierarchy with the principle of structural entropy minimization, and injects the syntactic information into the text representation via hierarchical representation learning. Experiments on three common datasets are conducted to verify the superiority of HILL.

cs.CL↗

arXiv2022

A Simple yet Effective Method for Graph Classification

In deep neural networks, better results can often be obtained by increasing the complexity of previously developed basic models. However, it is unclear whether there is a way to boost performance by decreasing the complexity of such models. Intuitively, given a problem, a simpler data structure comes with a simpler algorithm. Here, we investigate the feasibility of improving graph classification performance while simplifying the learning process. Inspired by structural entropy on graphs, we transform the data sample from graphs to coding trees, which is a simpler but essential structure for graph data. Furthermore, we propose a novel message passing scheme, termed hierarchical reporting, in which features are transferred from leaf nodes to root nodes by following the hierarchical structure of coding trees. We then present a tree kernel and a convolutional network to implement our scheme for graph classification. With the designed message passing scheme, the tree kernel and convolutional network have a lower runtime complexity of $O(n)$ than Weisfeiler-Lehman subtree kernel and other graph neural networks of at least $O(hm)$. We empirically validate our methods with several graph classification benchmarks and demonstrate that they achieve better performance and lower computational consumption than competing approaches.

cs.LG↗

arXiv2021

Structural Optimization Makes Graph Classification Simpler and Better

In deep neural networks, better results can often be obtained by increasing the complexity of previously developed basic models. However, it is unclear whether there is a way to boost performance by decreasing the complexity of such models. Here, based on an optimization method, we investigate the feasibility of improving graph classification performance while simplifying the model learning process. Inspired by progress in structural information assessment, we optimize the given data sample from graphs to encoding trees. In particular, we minimize the structural entropy of the transformed encoding tree to decode the key structure underlying a graph. This transformation is denoted as structural optimization. Furthermore, we propose a novel feature combination scheme, termed hierarchical reporting, for encoding trees. In this scheme, features are transferred from leaf nodes to root nodes by following the hierarchical structures of encoding trees. We then present an implementation of the scheme in a tree kernel and a convolutional network to perform graph classification. The tree kernel follows label propagation in the Weisfeiler-Lehman (WL) subtree kernel, but it has a lower runtime complexity $O(n)$. The convolutional network is a special implementation of our tree kernel in the deep learning field and is called Encoding Tree Learning (ETL). We empirically validate our tree kernel and convolutional network with several graph classification benchmarks and demonstrate that our methods achieve better performance and lower computational consumption than competing approaches.

cs.LG↗

arXiv2021

An Information-theoretic Perspective of Hierarchical Clustering

A combinatorial cost function for hierarchical clustering was introduced by Dasgupta \cite{dasgupta2016cost}. It has been generalized by Cohen-Addad et al. \cite{cohen2019hierarchical} to a general form named admissible function. In this paper, we investigate hierarchical clustering from the \emph{information-theoretic} perspective and formulate a new objective function. We also establish the relationship between these two perspectives. In algorithmic aspect, we get rid of the traditional top-down and bottom-up frameworks, and propose a new one to stratify the \emph{sparsest} level of a cluster tree recursively in guide with our objective function. For practical use, our resulting cluster tree is not binary. Our algorithm called HCSE outputs a $k$-level cluster tree by a novel and interpretable mechanism to choose $k$ automatically without any hyper-parameter. Our experimental results on synthetic datasets show that HCSE has a great advantage in finding the intrinsic number of hierarchies, and the results on real datasets show that HCSE also achieves competitive costs over the popular algorithms LOUVAIN and HLP.

cs.LG↗