arXiv subjects

Yang Lin

Publications and source records attributed to Yang Lin.

At least 19 recordsLinked to original sources

arXiv2026

HyperRepair: Recovering Forgotten General Capabilities of Fine-Tuned Language Models

Fine-tuning improves a language model's performance in a target domain but can weaken its general capabilities. Existing methods often face a trade-off between general capabilities and domain specialization, making it difficult to preserve both. We introduce HyperRepair, a framework for recovering general capabilities while retaining domain specialization at only inference cost. To make recovery generalizable across models sharing a pretrained backbone, HyperRepair learns a hypernetwork from repairs trained on source models. The hypernetwork uses activation fingerprints that summarize changes from the pretrained backbone to generate a tailored Repairing Side Net (RSN), whose prompt-conditioned gate applies corrections selectively. This enables recovery on models from unseen adaptation domains without target-domain examples or additional optimization. We evaluate HyperRpair across two model families, 12 LoRA adaptation datasets, and 15 general benchmarks. On the default split, HyperRepair achieves 93.4% of the base models' average general score while retaining 99.5% of the fine-tuned models' average domain score.

cs.CL↗

arXiv2026

Agent as Policy for Robotic Manipulation

We demonstrate that a general-purpose agent can directly drive a physical robot throughout task execution without any task-specific or environment-specific training. We introduce Agent as Policy (AGP), which places task planning and execution under the agent's control. Given a task and a robot interface, the agent interprets visual evidence, writes executable programs, issues motion commands, and revises its actions in response to physical outcomes. This brings the agent's reasoning and programming capabilities into continuous interaction with the physical world. We study AGP across multiple real-world manipulation tasks spanning precision manipulation, dynamic motions, and deformable objects. These include assembly from human videos, block construction from goal images, dice flipping, targeted throwing, and bimanual towel folding. AGP achieves success rates of at least 80% in seven of eight task configurations and significantly outperforms previous agentic robot systems. We further study efficiency through task experience accumulation and find that reusing saved procedures and programs shortens execution time across repeated trials. These findings support a path for general-purpose agents to act as robot policies, extending their autonomy to physical manipulation through runtime reasoning, programming, and interaction.

cs.CL↗

arXiv2026

A closed-form solution for streaming and Lagrangian transport in a deforming circular cavity

Streaming from a deforming cavity wall serves micromixing, pumping and particle handling. We solve it in closed form in a two-dimensional circular cavity, for any azimuthal wall mode $m$, as $\mathrm{Wo}^2 \to 0$. A biharmonic inversion against the Reynolds stress, corrected by the second-order slip a moving wall imposes, gives the Lagrangian mean a tracer follows for a deforming no-slip wall, $ψ_L = -[m(5m+4)a_m^2/(128(m+2)(2m+1))]\,r^{2m}(r^2-1)^2\sin 2mθ$, with a companion form for a shear-free interface. For a single mode the factor $(5m+4)/(m+2)$ relating it to the auxiliary solution $ψ_2$ is the same for every member of the co-phased prescribed-velocity family; at $m=2$ the physical Eulerian mean peaks an order of magnitude above $ψ_2$, with opposite sign. The no-slip cell centers lie at $r^2 = m/(m+2)$, and at large $m$ the peak streamfunction falls as $m^{-2}$, the peak speed as $m^{-1}$. At fixed radial wall-velocity amplitude the ranking over $m$ follows the wall kinematics: an externally driven wall peaks at $m=1$, a wall with zero first-order surface strain at $m=3$. Mode superpositions invert without degenerating, each harmonic carrying its own correction. At finite $\mathrm{Wo}$ the first-order field stays closed form in Bessel functions and the mean flow reduces to quadrature; the construction approaches the $m=2$ Rayleigh limit on a separate tangentially driven boundary problem. An independent finite-element solver, with the closed form withheld, reproduces $ψ_2$ with quadratic mesh convergence.

physics.flu-dyn↗

arXiv2026

Robotic Valve Turning: Axial Misalignment Correction Using Reaction Torque Feedback

In this work, we propose a haptic update control law that uses reaction torques to correct axial misalignment during robotic valve manipulation. Unlike vision-based estimates, which can be affected by calibration errors, occlusion, and uncertainty in the contact geometry, reaction torques arise directly from the physical interaction between the gripper and valve. A geometric relationship exists between the error (misalignment) vector and these torques. The primary aim of this work is to propose a stable controller exploiting this geometric property. Our control law is proven to be uniformly asymptotically stable. Simulations are performed for verification. Furthermore, we experimentally test the robustness of our method using a Kinova Gen3 robotic arm for initial misalignments ranging from $-15^\circ$ to $15^\circ$ at 3 different valve positions and report the resulting data distribution. The absolute value of the median misalignment across all 18 test cases is found to be within $2.46^\circ$ and that of reaction torques within $0.23\mathrm{Nm}$.

cs.RO↗

arXiv2026

Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning

Process Reinforcement Learning~(PRL) has demonstrated considerable potential in enhancing the reasoning capabilities of Large Language Models~(LLMs). However, introducing additional process reward models incurs substantial computational overhead, and there is no unified theoretical framework for process-level advantage estimation. To bridge this gap, we propose \textbf{S}elf-Guided \textbf{P}rocess \textbf{R}eward \textbf{O}ptimization~(\textbf{SPRO}), a novel framework that enables process-aware RL through two key innovations: (1) we show that process rewards can be derived intrinsically from the policy model itself, and (2) we redefine step-wise advantage by introducing well-defined Cumulative Process Rewards~(\textbf{CPR}) and \textbf{M}asked \textbf{S}tep \textbf{A}dvantage~(\textbf{MSA}), which facilitates rigorous step-wise action advantage estimation within shared-prompt sampling groups. Our experimental results show that SPRO outperforms vanilla GRPO with 3.4x higher training efficiency and a 12.9\% test accuracy improvement. Furthermore, SPRO maintains a stable and elevated policy entropy throughout training while achieving a considerable reduction in response length, evidencing sufficient exploration and prevention of reward hacking. Notably, SPRO incurs no additional computational overhead compared to outcome-supervised RL methods such as GRPO, which benefit industrial implementation.

cs.LG↗

arXiv2026

LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models

Natural Language to SQL (NL2SQL) aims to translate natural language queries into executable SQL statements, offering non-expert users intuitive access to databases. While recent approaches leveraging large-scale private LLMs such as GPT-4 have achieved state-of-the-art results, they face two critical challenges: the lack of openness and reproducibility, and the prohibitive computational cost of test-time scaling. To address these issues, we explore improving the model-level performance of small-scale public LLMs in NL2SQL under resource-constrained settings. Our exploratory experiments reveal the potential of task decomposition for enhancing NL2SQL performance, but also highlight the difficulty of enabling LLMs to decompose queries effectively. Motivated by these findings, we propose LearNAT, a novel framework designed to enhance decomposition capabilities of LLM. LearNAT introduces (1) a Decomposition Synthesis Procedure, which leverages AST-guided search with pruning strategies to generate verifiable and efficient decompositions, and (2) Margin-Aware Reinforcement Learning, which provides fine-grained preference optimization for multi-step reasoning beyond standard DPO. Extensive experiments on benchmark datasets demonstrate that LearNAT significantly improves the performance of small-scale LLMs, achieving results comparable to GPT-4 with only a 7B parameter model. These results validate the effectiveness of verifiable decomposition and fine-grained preference learning in advancing NL2SQL towards openness, transparency, and efficiency. Our code is publicly available at https://github.com/MrBlankness/LearNAT.

cs.CL↗

arXiv2026

Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories

Current approaches to enhance Large Language Model (LLM) reasoning, such as Chain-of-Thought and "Wait" prompts, primarily encourage models to think more, yet often fail to guide them toward Truth. While Representation Editing (RepE) offers a intrinsic control, its application to dynamic reasoning trajectories remains underexplored. In this work, we bridge this gap by investigating the geometry of truth within unfolding reasoning chains. We uncover three critical insights: (1) Truth is encoded at the sentence level and is entangled with latent reasoning patterns; (2) Effective intervention follows an Uncertainty Principle and a Decay Effect, requiring localization to early, high-entropy forks; (3) Naive steering vectors suffer from noise, risking collateral damage to correct trajectories. Based on these findings, we propose DynaSteer, a dynamic RepE framework. DynaSteer employs pattern clustering to disentangle reasoning manifolds and utilizes Fisher-LDA to project purified truth. By dynamically monitoring lookahead entropy, it selectively steers and rolls back trajectories only when necessary. Comprehensive experimental results on several MATH benchmark verify the effectiveness of DynaSteer, and experiments on out-of-domain coding tasks further confirm its generalization ability. Our code is publicly available at https://github.com/tianlwang/DynaSteer.

cs.AI↗

arXiv2026

Enhancing LLM Medical Coding with Structured External Knowledge

Accurate medical coding requires consulting authoritative resources such as the ICD tabular list and coding guidelines. Existing LLM-based automated methods largely rely on LLMs' internal knowledge, which is prone to hallucination and cannot keep pace with guideline updates. We introduce RAG-Coding, an agentic, training-free method that augments LLMs with structured external knowledge: the tabular list is encoded as a knowledge graph capturing hierarchical and instructional code relationships, and the guidelines are distilled into concise, code-specific summaries rather than retrieved as raw text. To enable our study, we also introduce MDACE-2025, expert re-annotations of the MDACE dataset under the 2025 ICD-10-CM/PCS guidelines, adding code sequencing and justification comments. On MDACE, RAG-Coding outperforms the best LLM-based baseline by 3--13\% in micro-F1 across five LLM backbones, and achieves comparable micro- and macro-F1 to the supervised state-of-the-art, with higher recall ($+$11\%) at the cost of precision ($-$6\%). On MDACE-2025, RAG-Coding outperforms all baselines, demonstrating effective generalisation to updated guidelines. Ablations confirm stepwise gains, highlighting the importance of integrating structured external knowledge for LLM-based medical coding.

cs.CL↗

arXiv2026

BoomHQ: Learning to Boost Multiple Hybrid Queries on Vector DBMSs

Hybrid queries, which combine vector nearest neighbor searches with scalar predicates, represent a fundamental challenge in managing vector databases. Existing methods often restrict the number of vector columns involved or the complexity of scalar predicates, thereby limiting their flexibility in handling diverse query patterns. Moreover, these approaches typically do not fully leverage the correlations between scalar and vector attributes, or the distributional patterns observed from query vector neighborhoods. To address these limitations, we introduce BoomHQ, a learning-based framework to boost multiple hybrid queries on vector DBMSs. First, BoomHQ models the correlation between vector and scalar attributes using an autoencoder-based architecture, which is also friendly to data updates. Second, BoomHQ captures prevailing query patterns, particularly using estimated selectivity of scalar predicates within the neighborhood of a query vector. Guided by these two key features, BoomHQ predicts the execution hints and rewrites the original query into an optimized version. Furthermore, we extend well-known benchmarks by introducing vector and scalar data with inherent correlations to better evaluate query execution. Experimental results demonstrate that for multiple hybrid queries at specified recall thresholds, our method achieves a 2x average and over 25x peak speedup compared to the state-of-the-art. Additionally, BoomHQ shows strong robustness against data updates and consistent optimization effectiveness across three representative vector database systems.

cs.DB↗

arXiv2026

SBF: An Effective Representation to Augment Skeleton for Video-based Human Action Recognition

Many modern video-based human action recognition (HAR) approaches use 2D skeleton as the intermediate representation in their prediction pipelines. Despite overall encouraging results, these approaches still struggle in many common scenes, mainly because the skeleton does not capture critical action-related information pertaining to the depth of the joints, contour of the human body, and interaction between the human and objects. To address this, we propose an effective approach to augment skeleton with a representation capturing action-related information in the pipeline of HAR. The representation, termed Scale-Body-Flow (SBF), consists of three distinct components, namely a scale map volume given by the scale (and hence depth information) of each joint, a body map outlining the human subject, and a flow map indicating human-object interaction given by pixel-wise optical flow values. To predict SBF, we further present SFSNet, a novel segmentation network supervised by the skeleton and optical flow without extra annotation overhead beyond the existing skeleton extraction. Extensive experiments across different datasets demonstrate that our pipeline based on SBF and SFSNet achieves significantly higher HAR accuracy with similar compactness and efficiency as compared with the state-of-the-art skeleton-only approaches.

cs.CV↗

arXiv2026

Speaker Anonymisation for Speech-based Suicide Risk Detection

Adolescent suicide is a critical global health issue, and speech provides a cost-effective modality for automatic suicide risk detection. Given the vulnerable population, protecting speaker identity is particularly important, as speech itself can reveal personally identifiable information if the data is leaked or maliciously exploited. This work presents the first systematic study of speaker anonymisation for speech-based suicide risk detection. A broad range of anonymisation methods are investigated, including techniques based on traditional signal processing, neural voice conversion, and speech synthesis. A comprehensive evaluation framework is built to assess the trade-off between protecting speaker identity and preserving information essential for suicide risk detection. Results show that combining anonymisation methods that retain complementary information yields detection performance comparable to that of original speech, while achieving protection of speaker identity for vulnerable populations.

eess.AS↗

arXiv2025

Systematic validation of time-resolved diffuse optical simulators via non-contact SPAD-based measurements

Objective: Time-domain diffuse optical imaging (DOI) requires accurate forward models for photon propagation in scattering media. However, existing simulators lack comprehensive experimental validation, especially for non-contact configurations with oblique illumination. This study rigorously evaluates three widely used open-source simulators, including MMC, NIRFASTer, and Toast++, using time-resolved experimental data. Approach: All simulations employed a unified mesh and point-source illumination. Virtual source correction was applied to FEM solvers for oblique incidence. A time-resolved DOI system with a 32 $\times$ 32 single-photon avalanche diode (SPAD) array acquired transmission-mode data from 16 standardized phantoms with varying absorption coefficient $μ_a$ and reduced scattering coefficient $μ_s'$. The simulation results were quantified across five metrics: spatial-domain (SD) precision, time-domain (TD) precision, oblique beam accuracy, computational speed, and mesh-density independence. Results: Among three simulators, MMC achieves superior accuracy in SD and TD metrics, and shows robustness across all optical properties. NIRFASTer and Toast++ demonstrate comparable overall performance. In general, MMC is optimal for accuracy-critical TD-DOI applications, while NIRFASTer and Toast++ suit scenarios prioritizing speed with sufficiently large $μ_s'$. Besides, virtual source correction is essential for non-contact FEM modeling, which reduced average errors by > 34% in large-angle scenarios. Significance: This work provides benchmarked guidelines for simulator selection during the development phase of next-generation TD-DOI systems. Our work represents the first study to systematically validate TD simulators against SPAD array-based data under clinically relevant non-contact conditions, bridging a critical gap in biomedical optical simulation standards.

physics.optics↗

arXiv2025

MedDCR: Learning to Design Agentic Workflows for Medical Coding

Medical coding converts free-text clinical notes into standardized diagnostic and procedural codes, which are essential for billing, hospital operations, and medical research. Unlike ordinary text classification, it requires multi-step reasoning: extracting diagnostic concepts, applying guideline constraints, mapping to hierarchical codebooks, and ensuring cross-document consistency. Recent advances leverage agentic LLMs, but most rely on rigid, manually crafted workflows that fail to capture the nuance and variability of real-world documentation, leaving open the question of how to systematically learn effective workflows. We present MedDCR, a closed-loop framework that treats workflow design as a learning problem. A Designer proposes workflows, a Coder executes them, and a Reflector evaluates predictions and provides constructive feedback, while a memory archive preserves prior designs for reuse and iterative refinement. On benchmark datasets, MedDCR outperforms state-of-the-art baselines and produces interpretable, adaptable workflows that better reflect real coding practice, improving both the reliability and trustworthiness of automated systems.

cs.AI↗

arXiv2025

Transporter: A 128$\times$4 SPAD Imager with On-chip Encoder for Spiking Neural Network-based Processing

Single-photon avalanche diodes (SPADs) are widely used today in time-resolved imaging applications. However, traditional architectures rely on time-to-digital converters (TDCs) and histogram-based processing, leading to significant data transfer and processing challenges. Previous work based on recurrent neural networks has realized histogram-free processing. To further address these limitations, we propose a novel paradigm that eliminates TDCs by integrating in-sensor spike encoders. This approach enables preprocessing of photon arrival events in the sensor while significantly compressing data, reducing complexity, and maintaining real-time edge processing capabilities. A dedicated spike encoder folds multiple laser repetition periods, transforming phase-based spike trains into density-based spike trains optimized for spiking neural network processing and training via backpropagation through time. As a proof of concept, we introduce Transporter, a 128$\times$4 SPAD sensor with a per-pixel D flip-flop ring-based spike encoder, designed for intelligent active time-resolved imaging. This work demonstrates a path toward more efficient, neuromorphic SPAD imaging systems with reduced data overhead and enhanced real-time processing.

eess.IV↗

arXiv2025

Taming the Real-world Complexities in CPT E/M Coding with Large Language Models

Evaluation and Management (E/M) coding, under the Current Procedural Terminology (CPT) taxonomy, documents medical services provided to patients by physicians. Used primarily for billing purposes, it is in physicians' best interest to provide accurate CPT E/M codes. %While important, it is an auxiliary task that adds to physicians' documentation burden. Automating this coding task will help alleviate physicians' documentation burden, improve billing efficiency, and ultimately enable better patient care. However, a number of real-world complexities have made E/M encoding automation a challenging task. In this paper, we elaborate some of the key complexities and present ProFees, our LLM-based framework that tackles them, followed by a systematic evaluation. On an expert-curated real-world dataset, ProFees achieves an increase in coding accuracy of more than 36\% over a commercial CPT E/M coding system and almost 5\% over our strongest single-prompt baseline, demonstrating its effectiveness in addressing the real-world complexities.

cs.AI↗

arXiv2025

LLM4Hint: Leveraging Large Language Models for Hint Recommendation in Offline Query Optimization

Query optimization is essential for efficient SQL query execution in DBMS, and remains attractive over time due to the growth of data volumes and advances in hardware. Existing traditional optimizers struggle with the cumbersome hand-tuning required for complex workloads, and the learning-based methods face limitations in ensuring generalization. With the great success of Large Language Model (LLM) across diverse downstream tasks, this paper explores how LLMs can be incorporated to enhance the generalization of learned optimizers. Though promising, such an incorporation still presents challenges, mainly including high model inference latency, and the substantial fine-tuning cost and suboptimal performance due to inherent discrepancy between the token sequences in LLM and structured SQL execution plans with rich numerical features. In this paper, we focus on recurring queries in offline optimization to alleviate the issue of high inference latency, and propose \textbf{LLM4Hint} that leverages moderate-sized backbone LLMs to recommend query optimization hints. LLM4Hint achieves the goals through: (i) integrating a lightweight model to produce a soft prompt, which captures the data distribution in DBMS and the SQL predicates to provide sufficient optimization features while simultaneously reducing the context length fed to the LLM, (ii) devising a query rewriting strategy using a larger commercial LLM, so as to simplify SQL semantics for the backbone LLM and reduce fine-tuning costs, and (iii) introducing an explicit matching prompt to facilitate alignment between the LLM and the lightweight model, which can accelerate convergence of the combined model. Experiments show that LLM4Hint, by leveraging the LLM's stronger capability to understand the query statement, can outperform the state-of-the-art learned optimizers in terms of both effectiveness and generalization.

cs.DB↗

arXiv2025

Multi-Scale Transformer Architecture for Accurate Medical Image Classification

This study introduces an AI-driven skin lesion classification algorithm built on an enhanced Transformer architecture, addressing the challenges of accuracy and robustness in medical image analysis. By integrating a multi-scale feature fusion mechanism and refining the self-attention process, the model effectively extracts both global and local features, enhancing its ability to detect lesions with ambiguous boundaries and intricate structures. Performance evaluation on the ISIC 2017 dataset demonstrates that the improved Transformer surpasses established AI models, including ResNet50, VGG19, ResNext, and Vision Transformer, across key metrics such as accuracy, AUC, F1-Score, and Precision. Grad-CAM visualizations further highlight the interpretability of the model, showcasing strong alignment between the algorithm's focus areas and actual lesion sites. This research underscores the transformative potential of advanced AI models in medical imaging, paving the way for more accurate and reliable diagnostic tools. Future work will explore the scalability of this approach to broader medical imaging tasks and investigate the integration of multimodal data to enhance AI-driven diagnostic frameworks for intelligent healthcare.

cs.CV↗

arXiv2025

Quantifying Correlations of Machine Learning Models

Machine Learning models are being extensively used in safety critical applications where errors from these models could cause harm to the user. Such risks are amplified when multiple machine learning models, which are deployed concurrently, interact and make errors simultaneously. This paper explores three scenarios where error correlations between multiple models arise, resulting in such aggregated risks. Using real-world data, we simulate these scenarios and quantify the correlations in errors of different models. Our findings indicate that aggregated risks are substantial, particularly when models share similar algorithms, training datasets, or foundational models. Overall, we observe that correlations across models are pervasive and likely to intensify with increased reliance on foundational models and widely used public datasets, highlighting the need for effective mitigation strategies to address these challenges.

cs.LG↗