arXiv subjects

Ruitao Wu

Publications and source records attributed to Ruitao Wu.

7 recordsLinked to original sources

arXiv2026

Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL

Few-Shot Class-Incremental Learning (FSCIL) challenges models to sequentially learn new classes from minimal examples without forgetting prior knowledge, a task complicated by the stability-plasticity dilemma and data scarcity. Current FSCIL methods often struggle with generalization due to their reliance on limited datasets. While diffusion models offer a path for data augmentation, their direct application can lead to semantic misalignment or ineffective guidance. This paper introduces Diffusion-Classifier Synergy (DCS), a novel framework that establishes a mutual boosting loop between diffusion model and FSCIL classifier. DCS utilizes a reward-aligned learning strategy, where a dynamic, multi-faceted reward function derived from the classifier's state directs the diffusion model. This reward system operates at two levels: the feature level ensures semantic coherence and diversity using prototype-anchored maximum mean discrepancy and dimension-wise variance matching, while the logits level promotes exploratory image generation and enhances inter-class discriminability through confidence recalibration and cross-session confusion-aware mechanisms. This co-evolutionary process, where generated images refine the classifier and an improved classifier state yields better reward signals, demonstrably achieves state-of-the-art performance on FSCIL benchmarks, significantly enhancing both knowledge retention and new class learning.

cs.CV↗

arXiv2025

SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning

Recent advances in large language models have enabled AI systems to achieve expert-level performance on domain-specific scientific tasks, yet these systems remain narrow and handcrafted. We introduce SciAgent, a unified multi-agent system designed for generalistic scientific reasoning-the ability to adapt reasoning strategies across disciplines and difficulty levels. SciAgent organizes problem solving as a hierarchical process: a Coordinator Agent interprets each problem's domain and complexity, dynamically orchestrating specialized Worker Systems, each composed of interacting reasoning Sub-agents for symbolic deduction, conceptual modeling, numerical computation, and verification. These agents collaboratively assemble and refine reasoning pipelines tailored to each task. Across mathematics and physics Olympiads (IMO, IMC, IPhO, CPhO), SciAgent consistently attains or surpasses human gold-medalist performance, demonstrating both domain generality and reasoning adaptability. Additionally, SciAgent has been tested on the International Chemistry Olympiad (IChO) and selected problems from the Humanity's Last Exam (HLE) benchmark, further confirming the system's ability to generalize across diverse scientific domains. This work establishes SciAgent as a concrete step toward generalistic scientific intelligence-AI systems capable of coherent, cross-disciplinary reasoning at expert levels.

cs.AI↗

arXiv2025

Scalable and Programmable Topological Transitions in Plasmonic Moire Superlattices

Topological transitions are fundamental phenomena in electronics, photonics, and quantum technologies. However, the scalability and tunability of Topological transitions in these systems have still been constrained by their material properties or structural rigidities. Here, we demonstrate that plasmonic Moire superlattices offer a platform for large-range and programmable topological transitions via wavefront engineering. By tailoring the phases of elementary evanescent waves in hexagonal systems, we create Moire-structured optical skyrmion lattices whose topological invariants evolve programmably and scalably. Theoretical calculations indicate that the topological invariants span from -58 to +58 and are extendable by tuning the Moire angle. Remarkably, their values are constrained by symmetry to exclude integer multiples of 3/2, revealing an intrinsic link between symmetry and topological quantization. Our work establishes a versatile real-space topology control platform for exploring topological transitions mechanisms and studying topologically critical phenomena, and further promoting breakthroughs in structured light, photonic computing, and condensed matter physics.

physics.optics↗

arXiv2025

MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning

With the advancement of powerful large-scale reasoning models, effectively evaluating the reasoning capabilities of these models has become increasingly important. However, existing benchmarks designed to assess the reasoning abilities of large models tend to be limited in scope and lack the flexibility to adapt their difficulty according to the evolving reasoning capacities of the models. To address this, we propose MorphoBench, a benchmark that incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models. Specifically, we curate the benchmark by selecting and collecting complex reasoning questions from existing benchmarks and sources such as Olympiad-level competitions. Additionally, MorphoBench adaptively modifies the analytical challenge of questions by leveraging key statements generated during the model's reasoning process. Furthermore, it includes questions generated using simulation software, enabling dynamic adjustment of benchmark difficulty with minimal resource consumption. We have gathered over 1,300 test questions and iteratively adjusted the difficulty of MorphoBench based on the reasoning capabilities of models such as o3 and GPT-5. MorphoBench enhances the comprehensiveness and validity of model reasoning evaluation, providing reliable guidance for improving both the reasoning abilities and scientific robustness of large models. The code has been released in https://github.com/OpenDCAI/MorphoBench.

cs.AI↗

arXiv2025

Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge

Multimodal reasoning remains a fundamental challenge in artificial intelligence. Despite substantial advances in text-based reasoning, even state-of-the-art models such as GPT-o3 struggle to maintain strong performance in multimodal scenarios. To address this gap, we introduce a caption-assisted reasoning framework that effectively bridges visual and textual modalities. Our approach achieved 1st place in the ICML 2025 AI for Math Workshop \& Challenge 2: SeePhys, highlighting its effectiveness and robustness. Furthermore, we validate its generalization on the MathVerse benchmark for geometric reasoning, demonstrating the versatility of our method. Our code is publicly available at https://github.com/OpenDCAI/SciReasoner.

cs.CL↗

arXiv2025

Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement

Class-Incremental Semantic Segmentation (CISS) requires continuous learning of newly introduced classes while retaining knowledge of past classes. By abstracting mainstream methods into two stages (visual feature extraction and prototype-feature matching), we identify a more fundamental challenge termed catastrophic semantic entanglement. This phenomenon involves Prototype-Feature Entanglement caused by semantic misalignment during the incremental process, and Background-Increment Entanglement due to dynamic data evolution. Existing techniques, which rely on visual feature learning without sufficient cues to distinguish targets, introduce significant noise and errors. To address these issues, we introduce a Language-inspired Bootstrapped Disentanglement framework (LBD). We leverage the prior class semantics of pre-trained visual-language models (e.g., CLIP) to guide the model in autonomously disentangling features through Language-guided Prototypical Disentanglement and Manifold Mutual Background Disentanglement. The former guides the disentangling of new prototypes by treating hand-crafted text features as topological templates, while the latter employs multiple learnable prototypes and mask-pooling-based supervision for background-incremental class disentanglement. By incorporating soft prompt tuning and encoder adaptation modifications, we further bridge the capability gap of CLIP between dense and sparse tasks, achieving state-of-the-art performance on both Pascal VOC and ADE20k, particularly in multi-step scenarios.

cs.CV↗

arXiv2025

Physically interpretable diffractive optical networks for high-dimensional vortex mode sorting

Despite the significant progress achieved by diffractive optical networks in diverse computing tasks, such as mode multiplexing and demultiplexing, investigations into the physical meanings behind complex diffractive networks at the layer level have been quite limited. Here, for highdimensional vortex mode sorting tasks, we show how various physical transformation rules for each layer within trained diffractive networks can be revealed under properly defined input/output mode relations. An intriguing physical transformation division phenomenon, associated with the saturated sorting performance of the system, has been observed with an increasing number of masks. In addition, we have also demonstrated the use of physical interpretation for efficiently designing parameter-varying networks with high performance. These physically interpretable optical networks resolve the contradiction between rigorous physical theorems and operationally vague network structures, paving the way for designing and understanding systems for various mode conversion tasks, and inspiring further interpretation of diffractive networks in advanced tasks and other network structures.

physics.optics↗