Searcharxiv⌕ Search

arXiv subjects

Yichen Xu

Publications and source records attributed to Yichen Xu.

At least 37 records · Page 2Linked to original sources
arXiv2026

Residual Feature Integration is Sufficient to Prevent Negative Transfer

Transfer learning has become a central paradigm in modern machine learning, yet it suffers from the long-standing problem of negative transfer, where leveraging source representations can harm rather than help performance on the target task. Although empirical remedies have been proposed, there remains little theoretical understanding of how to reliably avoid negative transfer. In this paper, we investigate a simple yet remarkably effective strategy: augmenting frozen, pretrained source-side features with a trainable target-side encoder that adapts target features to capture residual signals overlooked by models pretrained on the source data. We show this residual feature integration strategy is sufficient to provably prevent negative transfer, by establishing theoretical guarantees that it has no worse convergence rate than training from scratch under the informative class of target distributions up to logarithmic factors, and that the convergence rate can transition seamlessly from nonparametric to near-parametric when source representations are informative. To our knowledge, this is the first theoretical work that ensures protection against negative transfer. We carry out extensive numerical experiments across image, text and tabular benchmarks, and empirically verify that the method consistently safeguards performance under distribution shift, label noise, semantic perturbation, and class imbalance. We additionally demonstrate that this residual integration mechanism uniquely supports adapt-time multimodality extension, enabling a pretrained single-cell foundation model to incorporate spatial signals for lymph-node anatomical classification despite the source model being trained without them. Our study thus advances the theory of safe transfer learning, and provides a principled approach that is simple, robust, architecture-agnostic, and broadly applicable.

cs.LG↗
arXiv2026

Synthetic Oversampling: Theory and A Practical Approach Using LLMs to Address Data Imbalance

Imbalanced classification and spurious correlation are common challenges in data science and machine learning. Both issues are linked to data imbalance, with certain groups of data samples significantly underrepresented, which in turn would compromise the accuracy, robustness and generalizability of the learned models. Recent advances have proposed leveraging the flexibility and generative capabilities of large language models (LLMs), typically built on transformer architectures, to generate synthetic samples and to augment the observed data. In the context of imbalanced data, LLMs are used to oversample underrepresented groups and have shown promising improvements. However, there is a clear lack of theoretical understanding of such synthetic data approaches. In this article, we develop novel theoretical foundations to systematically study the roles of synthetic samples in addressing imbalanced classification and spurious correlation. Specifically, we first explicitly quantify the benefits of synthetic oversampling. Next, we analyze the scaling dynamics in synthetic data augmentation, and derive the corresponding scaling law. Finally, we demonstrate the capacity of transformer models to generate high-quality synthetic samples. We further conduct extensive numerical experiments to validate the efficacy of the LLM-based synthetic oversampling and augmentation.

stat.ML↗
arXiv2026

Understanding and Guiding Layer Placement in Parameter-Efficient Fine-Tuning of Large Language Models

As large language models (LLMs) continue to grow, the cost of full-parameter fine-tuning has made parameter-efficient fine-tuning (PEFT) the default strategy for downstream adaptation. Constraints from inference latency in scalable serving and fine-tuning cost in edge or rapid-deployment settings make the choice of which layers to fine-tune unavoidable. Yet current practice typically applies PEFT uniformly across all layers, with limited understanding or leverage of layer selection. This paper develops a unified projected residual view of PEFT on top of a frozen base model. Under a local quadratic approximation, layerwise adaptation is governed by three quantities: (i) the projected residual norm (resnorm), which measures how much correctable bias a layer can capture; (ii) the activation energy, which determines feature conditioning; and (iii) layer coupling, which quantifies how strongly residuals interact across layers. We show that, for squared loss and linear adapters, the resnorm equals a normalized gradient norm, activation energy controls ill-conditioning and noise amplification, and weak coupling yields approximately additive layerwise contributions. Building on these insights, we introduce the Layer Card, a reusable diagnostic that summarizes residual signal strength, compute cost, and performance for each layer of a given model. With an identical model and LoRA configuration, Layer Card-guided placement refines the choice of adapted layers to flexibly prioritize different objectives, such as maximizing performance or reducing fine-tuning cost. Moreover, on Qwen3-8B, we show that selectively adapting a subset of layers can achieve performance close to full-layer LoRA while substantially reducing fine-tuning cost and the number of adapter-augmented layers during inference, offering a more cost-performance-aware alternative to full-layer insertion.

cs.LG↗
arXiv2026

Fault-tolerant protocols through spacetime concatenation

We introduce a framework called spacetime concatenation for fault-tolerant compilation of syndrome extraction circuits of stabilizer codes. Spacetime concatenation enables efficient compilation of syndrome extraction circuits into dynamical codes through structured gadget layouts and encoding matrices, facilitating low-weight measurements while preserving logical information. Our framework uses conditions that are sufficient for fault-tolerance of the dynamical code, including not measuring logical operators and preserving the spacetime distance. We construct explicit examples of dynamical codes using this framework, including the dynamical bivariate bicycle code and a dynamical Haah code, while illustrating their fault-tolerant properties. Furthermore, we analyze the classification and resource trade-offs of dynamical codes, demonstrating their adaptability to hardware constraints, including fabrication defects and qubit dropout scenarios.

quant-ph↗
arXiv2026

POLYCHARTQA: Benchmarking Large Vision-Language Models with Multilingual Chart Question Answering

Charts are a universally adopted medium for data communication, yet existing chart understanding benchmarks are overwhelmingly English-centric, limiting their accessibility and relevance to global audiences. To address this limitation, we introduce PolyChartQA, the first large-scale multilingual benchmark for chart question answering, comprising 22,606 charts and 26,151 QA pairs across 10 diverse languages. PolyChartQA is constructed through a scalable pipeline that enables efficient multilingual chart generation via data translation and code reuse, supported by LLM-based translation and rigorous quality control. We systematically evaluate multilingual chart understanding with PolyChartQA on state-of-the-art LVLMs and reveal a significant performance gap between English and other languages, particularly low-resource ones. Additionally, we introduce a companion multilingual chart question answering training set, PolyChartQA-Train, on which fine-tuning LVLMs yields substantial gains in multilingual chart understanding across diverse model sizes and architectures. Together, our benchmark provides a foundation for developing globally inclusive vision-language models capable of understanding charts across diverse linguistic contexts.

cs.CL↗
arXiv2026

Agentic Proof Automation: A Case Study

Proof engineering is notoriously labor-intensive: proofs that are straightforward on paper often require lengthy scripts in theorem provers. Recent advances in large language models (LLMs) create new opportunities for proof automation: modern LLMs not only generate proof scripts, but also support agentic behavior, exploring codebases and iteratively refining their outputs against prover feedback. These advances enable an emerging scheme where LLM-based agents undertake most proof engineering under human guidance. Humans provide mathematical insight (definitions, theorems, proof strategies); agents handle the mechanical work of proof development. We call this scheme agentic proof automation. We present this scheme through a case study: mechanizing the semantic type soundness of a sophisticated formal system, System Capless, in Lean 4, comprising over 14,000 lines of code. Using off-the-shelf LLM agents with a single lightweight proof-checking tool, the agents completed 189 proof engineering tasks with an 87% success rate, only 16% requiring human intervention. The case study demonstrates that agents are capable proof engineers that substantially boost productivity, though they fall short in creative reasoning and still require human guidance in certain cases. We release an interactive explorer where readers can examine all agent interactions; the mechanization is open-sourced for experiments and extensions.

cs.PL↗
arXiv2025

MHR: Momentum Human Rig

We present MHR, a parametric human body model that combines the decoupled skeleton/shape paradigm of ATLAS with a flexible, modern rig and pose corrective system inspired by the Momentum library. Our model enables expressive, anatomically plausible human animation, supporting non-linear pose correctives, and is designed for robust integration in AR/VR and graphics pipelines.

cs.GR↗
arXiv2025

ChartEditor: A Reinforcement Learning Framework for Robust Chart Editing

Chart editing reduces manual effort in visualization design. Typical benchmarks limited in data diversity and assume access to complete chart code, which is seldom in real-world scenarios. To address this gap, we present ChartEditVista, a comprehensive benchmark consisting of 7,964 samples spanning 31 chart categories. It encompasses diverse editing instructions and covers nearly all editable chart elements. The inputs in ChartEditVista include only the original chart image and natural language editing instructions, without the original chart codes. ChartEditVista is generated through a fully automated pipeline that produces, edits, and verifies charts, ensuring high-quality chart editing data. Besides, we introduce two novel fine-grained, rule-based evaluation metrics: the layout metric, which evaluates the position, size and color of graphical components; and the text metric, which jointly assesses textual content and font styling. Building on top of ChartEditVista, we present ChartEditor, a model trained using a reinforcement learning framework that incorporates a novel rendering reward to simultaneously enforce code executability and visual fidelity. Through extensive experiments and human evaluations, we demonstrate that ChartEditVista provides a robust evaluation, while ChartEditor consistently outperforms models with similar-scale and larger-scale on chart editing tasks.

cs.MM↗
arXiv2025

DrivAerStar: An Industrial-Grade CFD Dataset for Vehicle Aerodynamic Optimization

Vehicle aerodynamics optimization has become critical for automotive electrification, where drag reduction directly determines electric vehicle range and energy efficiency. Traditional approaches face an intractable trade-off: computationally expensive Computational Fluid Dynamics (CFD) simulations requiring weeks per design iteration, or simplified models that sacrifice production-grade accuracy. While machine learning offers transformative potential, existing datasets exhibit fundamental limitations -- inadequate mesh resolution, missing vehicle components, and validation errors exceeding 5% -- preventing deployment in industrial workflows. We present DrivAerStar, comprising 12,000 industrial-grade automotive CFD simulations generated using STAR-CCM+${}^\unicode{xAE}$ software. The dataset systematically explores three vehicle configurations through 20 Computer Aided Design (CAD) parameters via Free Form Deformation (FFD) algorithms, including complete engine compartments and cooling systems with realistic internal airflow. DrivAerStar achieves wind tunnel validation accuracy below 1.04% -- a five-fold improvement over existing datasets -- through refined mesh strategies with strict wall $y^+$ control. Benchmarks demonstrate that models trained on this data achieve production-ready accuracy while reducing computational costs from weeks to minutes. This represents the first dataset bridging academic machine learning research and industrial CFD practice, establishing a new standard for data-driven aerodynamic optimization in automotive development. Beyond automotive applications, DrivAerStar demonstrates a paradigm for integrating high-fidelity physics simulations with Artificial Intelligence (AI) across engineering disciplines where computational constraints currently limit innovation.

cs.LG↗
arXiv2025

A Technical Exploration of Causal Inference with Hybrid LLM Synthetic Data

Large Language Models (LLMs) offer a flexible means to generate synthetic tabular data, yet existing approaches often fail to preserve key causal parameters such as the average treatment effect (ATE). In this technical exploration, we first demonstrate that state-of-the-art synthetic data generators, both GAN- and LLM-based, can achieve high predictive fidelity while substantially misestimating causal effects. To address this gap, we propose a hybrid generation framework that combines model-based covariate synthesis (monitored via distance-to-closest-record filtering) with separately learned propensity and outcome models, thereby ensuring that (W, A, Y) triplets retain their underlying causal structure. We further introduce a synthetic pairing strategy to mitigate positivity violations and a realistic evaluation protocol that leverages unlimited synthetic samples to benchmark traditional estimators (IPTW, AIPW, substitution) under complex covariate distributions. This work lays the groundwork for LLM-powered data pipelines that support robust causal analysis. Our code is available at https://github.com/Xyc-arch/llm-synthetic-for-causal-inference.git.

cs.LG↗
arXiv2025

Generative Modeling of Shape-Dependent Self-Contact Human Poses

One can hardly model self-contact of human poses without considering underlying body shapes. For example, the pose of rubbing a belly for a person with a low BMI leads to penetration of the hand into the belly for a person with a high BMI. Despite its relevance, existing self-contact datasets lack the variety of self-contact poses and precise body shapes, limiting conclusive analysis between self-contact poses and shapes. To address this, we begin by introducing the first extensive self-contact dataset with precise body shape registration, Goliath-SC, consisting of 383K self-contact poses across 130 subjects. Using this dataset, we propose generative modeling of self-contact prior conditioned by body shape parameters, based on a body-part-wise latent diffusion with self-attention. We further incorporate this prior into single-view human pose estimation while refining estimated poses to be in contact. Our experiments suggest that shape conditioning is vital to the successful modeling of self-contact pose distribution, hence improving single-view pose estimation in self-contact.

cs.CV↗
arXiv2025

What's in the Box: Ergonomic and Expressive Capture Tracking over Generic Data Structures (Extended Version)

Capturing types in Scala unify static effect and resource tracking with object capabilities, enabling lightweight effect polymorphism with minimal notational overhead. However, their expressiveness has been insufficient for tracking capabilities embedded in generic data structures, preventing them from scaling to the standard collections library -- an essential prerequisite for broader adoption. This limitation stems from the inability to name capabilities within the system's notion of box types. This paper develops System Capless, a new foundation for capturing types that provides the theoretical basis for reach capabilities (rcaps), a novel mechanism for naming "what's in the box." The calculus refines the universal capability notion into a new scheme with existential and universal capture set quantification. Intuitively, rcaps witness existentially quantified capture sets inside the boxes of generic types in a way that does not require exposing existential capture types in the surface language. We have fully mechanized the formal metatheory of System Capless in Lean, including proofs of type soundness and scope safety. System Capless supports the same lightweight notation of capturing types plus rcaps, as certified by a type-preserving translation, and also enables fully optional explicit capture-set quantification to increase expressiveness. Finally, we present a full reimplementation of capture checking in Scala 3 based on System Capless and migrate the entire Scala collections library and an asynchronous programming library to evaluate its practicality and ergonomics. Our results demonstrate that reach capabilities enable the adoption of capture checking in production code with minimal changes and minimal-to-zero notational overhead in a vast majority of cases.

cs.PL↗
arXiv2025

ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

Parametric body models offer expressive 3D representation of humans across a wide range of poses, shapes, and facial expressions, typically derived by learning a basis over registered 3D meshes. However, existing human mesh modeling approaches struggle to capture detailed variations across diverse body poses and shapes, largely due to limited training data diversity and restrictive modeling assumptions. Moreover, the common paradigm first optimizes the external body surface using a linear basis, then regresses internal skeletal joints from surface vertices. This approach introduces problematic dependencies between internal skeleton and outer soft tissue, limiting direct control over body height and bone lengths. To address these issues, we present ATLAS, a high-fidelity body model learned from 600k high-resolution scans captured using 240 synchronized cameras. Unlike previous methods, we explicitly decouple the shape and skeleton bases by grounding our mesh representation in the human skeleton. This decoupling enables enhanced shape expressivity, fine-grained customization of body attributes, and keypoint fitting independent of external soft-tissue characteristics. ATLAS outperforms existing methods by fitting unseen subjects in diverse poses more accurately, and quantitative evaluations show that our non-linear pose correctives more effectively capture complex poses compared to linear models.

cs.CV↗
arXiv2025

Learning measurement-induced phase transitions using attention

Measurement-induced phase transitions (MIPTs) epitomize new intellectual pursuits inspired by the advent of quantum hardware and the emergence of discrete and programmable circuit dynamics. Nevertheless, experimentally observing this transition is challenging, often requiring non-scalable protocols, such as post-selecting measurement trajectories or relying on classical simulations. We introduce a scalable data-centric approach using Quantum Attention Networks (QuAN) to detect MIPTs without requiring post-selection or classical simulation. Applying QuAN to dynamics generated by Haar random unitaries and weak measurements, we first demonstrate that it can pinpoint MIPTs using their interpretation as "learnability" transitions, where it becomes possible to distinguish two different initial states from the measurement record, locating a phase boundary consistent with exact results. Motivated by sample efficiency, we consider an alternative "phase recognition" task-classifying weak- and strong-monitoring data generated from a single initial state. We find QuAN can provide an efficient and noise-tolerant upper bound on the MIPT based on measurement data alone by coupling Born-distribution-level (inter-trajectory) and dynamical (temporal) attention. In particular, our inspection of the inter-trajectory scores of the model trained with minimal sample size processing test data confirmed that QuAN paid special attention to the tail of the distribution of the Born probabilities at early times. This reassuring interpretation of QuAN's learning implies the phase-recognition approach can meaningfully signal MIPT in an experimentally accessible manner. Our results lay the groundwork for observing MIPT on near-term quantum hardware and highlight attention-based architectures as powerful tools for learning complex quantum dynamics.

quant-ph↗
arXiv2025

ChartM$^3$: Benchmarking Chart Editing with Multimodal Instructions

Charts are a fundamental visualization format widely used in data analysis across research and industry. While enabling users to edit charts based on high-level intentions is of great practical value, existing methods primarily rely on natural language instructions, which are often too ambiguous to support fine-grained editing. In this work, we introduce a novel paradigm for multimodal chart editing, where user intent is expressed through a combination of natural language and visual indicators that explicitly highlight the elements to be modified. To support this paradigm, we present Chart$\text{M}^3$, a new benchmark for Multimodal chart editing with Multi-level complexity and Multi-perspective evaluation. Chart$\text{M}^3$ contains 1,000 samples spanning four levels of editing difficulty. Each sample includes triplets in the form of (chart, code, multimodal instructions). To comprehensively evaluate chart editing models, Chart$\text{M}^3$ provides metrics that assess both visual appearance and code correctness. Our benchmark reveals significant limitations in current multimodal large language models (MLLMs), including GPT-4o, particularly in their ability to interpret and act on visual indicators. To address this, we construct Chart$\text{M}^3$-Train, a large-scale training set with 24,000 multimodal chart editing samples. Fine-tuning MLLMs on this dataset leads to substantial improvements, demonstrating the importance of multimodal supervision in building practical chart editing systems. Our datasets, codes, and evaluation tools are available at https://github.com/MLrollIT/ChartM3. %https://github.com/MLrollIT/ChartM3Our datasets, codes, and evaluation tools are available at https://github.com/yaolinli/VCE.

cs.CV↗
arXiv2025

Learning to decode logical circuits

With the development of quantum hardware bringing the error-corrected quantum circuits to the near future, the lack of an efficient polynomial-time decoding algorithms for logical circuits presents a critical bottleneck. While quantum memory decoding has been well-studied, inevitable correlated errors introduced by entangling logical gates prevent the straightforward generalization of quantum memory decoders. We introduce a data-centric modular decoder framework, Multi-Core Circuit Decoder (MCCD), consisting of decoder modules corresponding to each logical operation supported by the quantum hardware. The MCCD handles both single-qubit and entangling gates within a unified framework. We train MCCD using mirror-symmetric random Clifford circuits, demonstrating its ability to effectively learn correlated decoding patterns. Through extensive testing on circuits significantly deeper than those used in training, we show that MCCD maintains high logical accuracy while exhibiting competitive polynomial decoding time across increasing circuit depths and code distances. When compared with conventional decoders like Minimum Weight Perfect Matching (MWPM), Most Likely Error (MLE), and Belief Propagation with Ordered Statistics Post-processing (BP-OSD), MCCD achieves competitive accuracy with substantially better time efficiency, particularly for circuits with entangling gates. Our approach represents a noise-model agnostic solution to the decoding challenge for deep logical quantum circuits.

quant-ph↗
arXiv2025

Average-exact mixed anomalies and compatible phases

The quantum anomaly of a global symmetry is known to strongly constrain the allowed low-energy physics in a clean and isolated quantum system. However, the effect of quantum anomalies in disordered systems is much less understood, especially when the global symmetry is only preserved on average by the disorder. In this work, we focus on disordered systems with both average and exact symmetries $A\times K$, where the exact symmetry $K$ is respected in every disorder configuration, and the average $A$ is only preserved on average by the disorder ensemble. When there is a mixed quantum anomaly between the average and exact symmetries, we argue that the mixed state representing the ensemble of disordered ground states cannot be featureless. While disordered mixed states smoothly connected to the anomaly-compatible phases in clean limit are certainly allowed, we also found disordered phases that have no clean-limit counterparts, including the glassy states with strong-to-weak symmetry breaking, and average topological orders for certain anomalies. We construct solvable lattice models to demonstrate each of these possibilities. We also provide a field-theoretic argument to provide a criterion for whether a given average-exact mixed anomaly admits a compatible average topological order.

cond-mat.str-el↗
arXiv2024

Goal State Generation for Robotic Manipulation Based on Linguistically Guided Hybrid Gaussian Diffusion

In robotic manipulation tasks, achieving a designated target state for the manipulated object is often essential to facilitate motion planning for robotic arms. Specifically, in tasks such as hanging a mug, the mug must be positioned within a feasible region around the hook. Previous approaches have enabled the generation of multiple feasible target states for mugs; however, these target states are typically generated randomly, lacking control over the specific generation locations. This limitation makes such methods less effective in scenarios where constraints exist, such as hooks already occupied by other mugs or when specific operational objectives must be met. Moreover, due to the frequent physical interactions between the mug and the rack in real-world hanging scenarios, imprecisely generated target states from end-to-end models often result in overlapping point clouds. This overlap adversely impacts subsequent motion planning for the robotic arm. To address these challenges, we propose a Linguistically Guided Hybrid Gaussian Diffusion (LHGD) network for generating manipulation target states, combined with a gravity coverage coefficient-based method for target state refinement. To evaluate our approach under a language-specified distribution setting, we collected multiple feasible target states for 10 types of mugs across 5 different racks with 10 distinct hooks. Additionally, we prepared five unseen mug designs for validation purposes. Experimental results demonstrate that our method achieves the highest success rates across single-mode, multi-mode, and language-specified distribution manipulation tasks. Furthermore, it significantly reduces point cloud overlap, directly producing collision-free target states and eliminating the need for additional obstacle avoidance operations by the robotic arm.

cs.RO↗