Search arXiv⌕ Search

arXiv subjects

Yuan Gao

Publications and source records attributed to Yuan Gao.

At least 109 records · Page 6Linked to original sources
arXiv2026

Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agents

Prior research on memory mechanism in RAG-based conversational system has emphasized how memory is stored and retrieved. However, far less is known about how memories with different functional roles influence response quality. Specifically, how they shape an agent's responses under varying conversational contexts and whether they lead to substantively different response behaviors. Existing evaluations in conversational system are also largely reference-based, insufficiently capturing the nuances in responses that may address users' preferences differently. In this work, we probe the impact of different memory types in shaping agents' responses. We present a fine-grained taxonomy of conversational memory, classify retrieved memories into different role types, and design a user-centric evaluation framework that simulates user perspectives. Through comparative experiments on long-term datasets and frontier LLMs, our analysis reveal many differentiated effects of memories: e.g., clarifying memory improves responses' factual accuracy and constraint awareness, making them more correct and personalized; irrelevant memory reduces topic relevance and degrades constraint awareness. Despite the power of frontier LLMs, these findings shed light on how different memory types can be leveraged to produce more personalized responses and inspire further research in this direction.

cs.CL↗
arXiv2026

Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis

While large language model (LLM)-based text-to-speech (TTS) systems have achieved high-quality speech synthesis, most existing systems focus on English and Chinese. Japanese, however, remains under-explored, and its unique linguistic challenges, such as widespread context-dependent kanji polyphony, have yet to be adequately tackled. Here we introduce Sarashina2.2-TTS (https://github.com/sbintuitions/sarashina2.2-tts), a Japanese-centric LLM-TTS system that tackles these challenges through a dual approach: data strategy and evaluation methodology. First, we scale training to approximately 361k hours of speech, incorporating a balanced mix of Japanese and English data. Furthermore, we design a targeted data augmentation pipeline covering all 2,136 Joyo (regular-use) kanji designated by Japan's Agency for Cultural Affairs to efficiently address kanji polyphony disambiguation. Second, we introduce the Joyo Kanji Yomi Benchmark (https://github.com/sbintuitions/JoyoKanji-Yomi-Benchmark), covering all 2,136 Joyo kanji and their 4,378 readings. Alongside this benchmark, we propose Kana-CER, a metric that compares synthesized speech against reference readings in the kana space, eliminating orthographic variations to directly measure pronunciation correctness. Experiments demonstrate that our targeted data augmentation significantly improves reading accuracy. Overall, Sarashina2.2-TTS achieves state-of-the-art kanji-level reading accuracy and matches top baselines on general sentence-level pronunciation, while delivering the highest speaker similarity in zero-shot Japanese speech synthesis. Furthermore, cross-lingual evaluation reveals that Sarashina2.2-TTS is the only system that maintains stable Japanese pronunciation regardless of the prompt language, confirming that our balanced training approach improves cross-lingual robustness.

cs.SD↗
arXiv2026

CSI-CLIP++: A Scalable Channel Foundation Model for Wireless Communication via CIR-CSI Consistency

Self-supervised learning can exploit large-scale unlabeled channel data to improve the transferability of wireless AI models. Existing channel foundation models are often built on single-domain representations or reconstruction-oriented objectives, which may not explicitly capture the physical correspondence between frequency- and delay-domain channel views. This paper proposes CSI-CLIP++, a scalable channel foundation model for MIMO wireless channels. CSI-CLIP++ treats frequency-domain channel state information (CSI) and delay-domain channel impulse response (CIR) as paired views of the same propagation process and learns transferable representations through CSI-CIR contrastive alignment. The pretrained CSI encoder is adapted to channel identification, beam prediction, and positioning, representing PHY, RAN, and ISAC applications. Experiments on large-scale DeepMIMO scenarios show consistent gains over supervised baselines across environments, carrier frequencies, and data scales. CSI-CLIP++ improves beam prediction Top-1 accuracy by up to 19.31 percentage points and achieves competitive positioning performance, including cross-simulator transfer on a Sionna RT dataset. Backbone scaling results further show that the proposed objective remains effective across encoder architectures and benefits from larger model capacity.

eess.SP↗
arXiv2026

6G Native AI and Channel Foundation Models

The integration of artificial intelligence (AI) and wireless communications is widely regarded as a core objective of sixth-generation (6G) systems. However, both the meaning of native AI and the type of AI capability that should be embedded into future wireless systems remain open to interpretation. This paper discusses 6G native AI from a system-design perspective and argues that native AI should be co-designed, optimized, and deployed as an intrinsic component of the wireless system rather than as a removable post-deployment add-on. From this perspective, conventional task-specific supervised models are difficult to use as the main technical basis of native AI because they depend heavily on labeled data, generalize poorly across propagation conditions, and require fragmented designs for different channel-related tasks. Motivated by these limitations, we position channel foundation models (CFMs) as a channel-centric foundation-model paradigm for 6G native AI. We define the scope of CFMs, clarify their differences from task-specific wireless AI models and large language models, and summarize three pretraining families: generative, discriminative, and hybrid pretraining. We further discuss how CFMs may support physical-layer processing, radio access network intelligence, and integrated sensing and communications. Preliminary CSI-CLIP-based results are included as bounded evidence that CFM-style pretraining can improve positioning and beam prediction when task-specific labels are limited.

eess.SP↗
arXiv2026

World Value Models for Robotic Manipulation

Generalist value models play a pivotal role in scaling robotic policy learning from large-scale, mixed-quality data. Mathematically, accurate value estimation demands deep temporal understanding, requiring models to both ground the current belief using historical context and plan over future outcomes. However, most existing robotic value models are built on Vision-Language Model (VLM) backbones that are pretrained primarily on static or temporally sparse visual observations, lacking the requisite temporal modeling capabilities for value estimation. Unlike VLMs, world models naturally excel at temporal modeling and future planning, making them ideal foundations for learning generalizable value functions. Driven by this insight, we marry world models with value estimation to construct a new generalist robotic value model, World Value Model (WVM), that offers accurate task progressions to assess data quality. On standard benchmarks, WVM delivers state-of-the-art (SOTA) Value-Order Correlation (VOC) results. Complementing standard evaluation suites that contains only expert data, we further introduce Suboptimal-Value-Bench, a multi-embodiment benchmark consisting of 800 suboptimal trajectories with high-fidelity, human-labeled frame annotations. Our evaluations show that WVM maintains its SOTA performance on Suboptimal-Value-Bench, establishing its robustness in handling both expert and suboptimal data. When deployed for policy learning, WVM improves manipulation performance across various policy extraction approaches in both simulated and real-world deployment, providing robust guidance for learning from mixed-quality data.

cs.RO↗
arXiv2026

Artificial Intelligence for Power-Converter-Rich Electrical Systems: A Review

Power-converter-rich electrical systems, formed by renewable generation, electrified transportation, and inverter-based resources, exhibit strongly nonlinear dynamics, multi-physics design tradeoffs, fast control requirements, and growing reliability and cybersecurity constraints. These characteristics strain workflows that rely only on physics-based modeling, sequential optimization, and rule-based operation. This paper reviews artificial intelligence (AI) for power-converter-rich electrical systems through a life-cycle and deployment-readiness perspective. The literature is organized across converter design, real-time control, system-level operation, and compliance-oriented governance. For design, we examine surrogate modeling, topology and parameter synthesis, EMI/EMC-aware optimization, reliability-oriented design, and knowledge-assisted workflows. For control, we compare supervised learning, reinforcement learning, learning-augmented predictive control, and safety-constrained learning according to their role in closed-loop implementation. For operations, we focus on microgrid coordination, forecasting, distribution-system observability, privacy-preserving coordination, and cyber-resilient operation where converter-interfaced resources shape the operating problem. Across these stages, the review emphasizes deployment-critical gaps, including stability certification, constraint satisfaction, interpretability, extrapolation, data efficiency, sim-to-real transfer, embedded latency, cybersecurity, privacy, and standards alignment. The resulting taxonomy is intended to clarify where AI is already useful as an engineering support tool and where further validation is needed before autonomous or safety-critical deployment.

eess.SY↗
arXiv2026

A Digital Twin Framework for Adaptive Treatment Planning in Radiotherapy

The development of a digital twin (DT) framework for fast online adaptive proton therapy planning in prostate stereotactic body radiation therapy (SBRT) with dominant intraprostatic lesion (DIL) boost represents a significant advancement in personalized radiotherapy. This framework integrates deep learning-based multi-atlas deformable image registration, daily patient anatomy updates via cone-beam CT (CBCT), and knowledge-based plan quality evaluation using the ProKnow scoring system to achieve clinical-equivalent plan quality with substantially reduced reoptimization times compared to traditional clinical workflows. Drawing on a database of 43 prior prostate SBRT cases, the DT framework predicts interfractional anatomical variations for new patients and pre-generates multiple probabilistic treatment plans. Upon acquiring daily CBCT, it enables rapid plan reoptimization, achieving an average reoptimization time of 5.5 [2.8, 8.2] minutes, compared to 19.8 [7.9, 31.7] minutes for clinical plans. The DT-based plans yielded a plan quality score of 157.2 [151.6, 162.8], surpassing or matching clinical plans, with superior dose coverage for the DIL (V100: 99.5%) and clinical target volume (CTV V100: 99.8%). Additionally, the framework minimized doses to organs at risk (OARs), achieving bladder V20.8Gy of 11.4 [7.2, 15.6] cc, rectum V23Gy of 0.7 [0.3, 1.1] cc, and urethra D10 of 90.9% [88.6%, 93.2%], aligning with clinical standards. By addressing interfractional variations efficiently, the DT framework enhances treatment precision, reduces OAR toxicity, and supports real-time adaptive radiotherapy. This transformative approach not only streamlines the planning process but also improves clinical outcomes, offering a scalable solution for prostate SBRT with DIL boost and paving the way for broader applications in adaptive proton therapy.

physics.med-ph↗
arXiv2026

The Dual Averaging Power-Prox Method with Application to Heavy-Tail Incremental Gradient

We study finite-sum composite optimization under two departures from classical stochastic gradient descent theory that are central in practice: incremental gradient access and heavy-tailed gradient noise. Specifically, we consider fixed cyclic passes over component gradients and assume that, at the optimum, component gradients have a bounded $q$-th centralized moment for some $q\in(1,2]$. This setting is much closer to modern ML training practice than the assumptions used in classical SGD theory, yet its theoretical understanding remains limited. We propose a Dual Averaging Power-Prox method for incremental gradients and establish, to the best of our knowledge, the first convergence analysis in this regime. We further show that our method achieves a better asymptotic convergence rate than the corresponding SGD method with i.i.d. (with-replacement) sampling.

math.OC↗
arXiv2026

Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking

Deep research agents have attracted increasing attention for their ability to collect large-scale online information to acquire target knowledge, with recent efforts shifting from purely text-based information seeking to multimodal settings. However, existing agentic workflows are largely aligned with evidence accumulation models, which linearly aggregate evidence and lack principled mechanisms for handling contradictory information across heterogeneous modalities. Towards this end, we propose Struct-Searcher, a structural agentic workflow grounded in belief revision theory that explicitly maintains an evolving multimodal structural graph throughout the reasoning process, enabling effective conflict-aware multimodal deep information seeking. Extensive experiments across multiple benchmark datasets and backbone models demonstrate that Struct-Searcher is (1) plug-and-play and model-agnostic, yielding an average relative accuracy improvement of 17.2% on BrowseComp-VL across five different backbones. (2) top-performing, consistently outperforming state-of-the-art vision-language models (VLMs) and deep research agents, with relative accuracy improvements of 3.7% on MM-BrowseComp, 1.5% on HLE-VL, and 0.7% on BrowseComp-VL over the second-best competing approach.

cs.CV↗
arXiv2026

Large-Scale Regularized Matching on GPU Clusters

Production decision systems such as ad allocation or content matching involve millions of users and thousands of items, reducing to large-scale linear programs with sparse block-diagonal structure across users. These LPs are solved repeatedly on recurring cadences over slowly evolving inputs. Three system gaps stand out. Scale: production instances routinely exceed the memory capacity of GPU solvers such as cuPDLP and D-PDLP under fixed hardware budgets. Temporal instability: solution variability across runs induces downstream churn and complicates SLAs, yet existing solvers provide no explicit control. Extensibility: CPU-based solvers such as DuaLip-Scala converge slowly and couple problem formulation to fixed schemas, making new constraint families difficult to express. We present a distributed multi-GPU LP solver built natively in PyTorch with systems-algorithm co-design for this structure. It adopts column-sharded parallelism with fused Triton kernels and batched operations to reduce per-iteration overhead. As users grow, only local computation increases, while communication is limited to a reduction of item-level dual variables, yielding near-linear scaling with GPU count at fixed item size. We also adopt ridge-regularized LPs to improve stability, a control absent from existing GPU solvers. A continuation schedule over the regularization parameter balances convergence speed and solution fidelity. Finally, we introduce an operator-centric programming model that replaces DuaLip-Scala's schema-bound interface with composable primitives, enabling new formulations without modifying the solve loop or distributed infrastructure. On synthetic workloads, our system achieves order-of-magnitude wall-clock speedup over DuaLip-Scala, near-linear multi-GPU scaling (3.86x on 4 GPUs), and scales beyond the reach of existing GPU solvers.

cs.DC↗
arXiv2026

PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting

Coupled spatiotemporal forecasting is important for predicting the future evolution of multiple interacting dynamical systems, such as in climate models. However, existing methods are severely constrained by the persistent bottleneck of compounding errors. In coupled systems, errors from each subsystem simulator propagate and amplify one another, a phenomenon we term Reciprocal Error Amplification, leading to a rapid collapse of long-range predictions. To address this challenge, we propose a universal framework called PnP-Corrector (Plug-and-Play Corrector). The core idea of our framework is to decouple the physical simulation from the error correction process: it freezes pre-trained physics simulation engines and exclusively trains a correction agent to proactively counteract the systematic biases emerging from the coupled system. Furthermore, we design an efficient predictive model architecture, DSLCast, to serve as the backbone of this framework. Extensive experiments demonstrate that our method significantly enhances the long-term stability and accuracy of coupled forecasting systems. For instance, in the challenging task of a 300-day global ocean-atmosphere coupled forecast, our PnP-Corrector framework reduces the prediction error of the baseline model by 28% and surpasses state-of-the-art models on several key metrics.

cs.AI↗
arXiv2026

DiBS: Diffusion-Informed Branch Selection

Sudoku is a representative constraint satisfaction problem that requires global structural reasoning under strict discrete constraints. The existing works of solving Sudoku mainly focus on two dominant approaches, i.e., traditional heuristic and deep learning solver. However, they suffer from two complementary limitations: learning-based solvers lack hard correctness guarantees, while complete symbolic solvers are still prone to long-tail search. To address these shortcomings, we propose a novel diffusion model-guided approach, termed as DiBS, for the branch selection search process. Specifically, DiBS keeps the symbolic solver complete and uses the diffusion model as a branch-ordering guide. The core method is ranking candidate values under the current partial assignment and lightweight consistency signal. Furthermore, we provide an in-depth theoretical proof to reveal how it works and why it works. Experiments on the challenging Royle 17-clue Sudoku benchmark show that our DiBS substantially reduces search cost relative to strong heuristic baselines, especially in nodes, backtracks, and long-tail percentiles. Besides, these results confirm that learned global guidance is effective on hard instances where branch-order mistakes are most expensive. All codes are available at https://github.com/shanxierdan/DiBS.

cs.AI↗
arXiv2026

Consistent Diffusion Language Models

Diffusion language models (DLMs) are an attractive alternative to autoregressive models because they promise sublinear-time, parallel generation, yet practical gains remain elusive as high-quality samples still demand hundreds of refinement steps. In continuous domains, consistency training along the probability-flow ODE is a popular recipe to accelerate diffusion. For discrete diffusion, no analogous sample-space ODE exists, making direct adaptation ill-defined. We argue that the right discrete substitute is the exact posterior bridge, the closed-form conditional law linking any two noise levels, which is available for broad corruptions including masked and uniform diffusion. Building on this observation, we introduce Multi-Path Discrete Consistency (MPDC), a new principle that trains a denoiser to be path-invariant in expectation across these stochastic bridges, and instantiate it as the Consistent Diffusion Language Model (CDLM), a single-stage training framework that does not require an already trained teacher model. Our CDLM objective recovers masked diffusion, continuous consistency models, and progressive or discrete distillation as analytic limits or empirical approximations of one common view. Empirically, CDLM establishes a new state of the art on both conditional and unconditional text-generation, consistently outperforming strong base discrete diffusion models and often even multi-stage distilled baselines across sampling budgets, with the largest gains in the few-step regime. Together, these results position CDLM as a principled and scalable foundation for the next generation of fast, high-fidelity discrete generative modeling.

cs.LG↗
arXiv2026

Apple Intelligence Foundation Language Models

We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute. These models are designed to perform a wide range of tasks efficiently, accurately, and responsibly. This report describes the model architecture, the data used to train the model, the training process, how the models are optimized for inference, and the evaluation results. We highlight our focus on Responsible AI and how the principles are applied throughout the model development.

cs.AI↗
arXiv2026

Source-Free Domain Adaptation for Geospatial Point Cloud Semantic Segmentation

Semantic segmentation of 3D geospatial point clouds is fundamental to remote sensing applications, yet domain shifts caused by regional and acquisition-related variations often degrade model performance. Although domain adaptation can mitigate such shifts, existing methods typically require access to source-domain data, which is often infeasible due to privacy concerns and regulatory policies. To address this, we propose LoGo (Local-Global Dual-Consensus), a novel source-free unsupervised domain adaptation (SFUDA) framework requiring only a pretrained model and unlabeled target data. At the local level, we introduce a class-balanced prototype estimation module that ensures that robust feature prototypes can be generated even for sample-scarce tail classes, effectively mitigating the feature collapse caused by long-tailed distributions. At the global level, we introduce an optimal transport-based global distribution alignment module that formulates pseudo-label assignment as a global optimization problem, effectively correcting the over-dominance of head classes inherent in local greedy assignments, and thereby preventing model predictions from being severely biased towards majority classes. Finally, we propose a dual-consistency pseudo-label filtering mechanism that retains only high-confidence pseudo-labels where local multi-augmented ensemble predictions align with global optimal transport assignments for self-training. Extensive experiments on two challenging benchmarks, encompassing cross-scene and cross-sensor settings, demonstrate that LoGo consistently outperforms existing state-of-the-art methods. The source code is available at https://github.com/GYproject/LoGo-SFUDA.

cs.CV↗
arXiv2026

Universal CT Representations from Anatomy to Disease Phenotype through Agglomerative Pretraining

Computed tomography (CT) is a central to three-dimensional medical imaging, yet CT-based artificial intelligence remains fragmented across task-specific models for segmentation, classification, registration, and report analysis. Here we present FlexiCT, a family of CT foundation models trained by agglomerative continual pretraining on 266,227 CT volumes from 56 publicly available datasets, forming a large-scale public resource for CT representation learning. FlexiCT uses agglomerative pretraining across three stages: two-dimensional axial pretraining, three-dimensional anatomical pretraining and report-guided semantic alignment. This training strategy supports slice-level, volume-level and vision-language analysis. Across five downstream task families (segmentation, classification, registration, vision-language understanding and clinical retrieval), FlexiCT matches or exceeds prior task-specific approaches on multiple benchmarks. Its embeddings further organize CT scans along gradients associated with various tumor stages, suggesting that CT foundation models can capture imaging features relevant to disease phenotype characterization. Project page and code are available at: https://ricklisz.github.io/flexict.github.io and https://github.com/ricklisz/FlexiCT.

cs.CV↗
arXiv2026

A European Multi-Center Breast Cancer MRI Dataset

Early detection of breast cancer is critical for improving patient outcomes. While mammography remains the primary screening modality, magnetic resonance imaging (MRI) is increasingly recommended as a supplemental tool for women with dense breast tissue and those at elevated risk. However, the acquisition and interpretation of multiparametric breast MRI are time-consuming and require specialized expertise, limiting scalability in clinical practice. Artificial intelligence (AI) methods have shown promise in supporting breast MRI interpretation, but their development is hindered by the limited availability of large, diverse, and publicly accessible datasets. To address this gap, we present a publicly available, multi-centre breast MRI dataset collected across six clinical institutions in five European countries. The dataset comprises 741 examinations from women undergoing screening or diagnostic breast MRI and includes malignant, benign, and non-lesion cases. Data were acquired using heterogeneous scanners, field strengths, and acquisition protocols, reflecting real-world clinical variability. In addition, we report baseline benchmark experiments using a transformer-based model to illustrate potential use cases of the dataset and to provide reference performance for future methodological comparisons.

eess.IV↗