Searcharxiv⌕ Search

arXiv subjects

Yilin Wen

Publications and source records attributed to Yilin Wen.

At least 19 recordsLinked to original sources
arXiv2026

The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy

The growing ability of large language models and vision-language models to jointly interpret and reason over images and text is reshaping medical imaging AI, moving it from task-specific predictors toward autonomous agents that perceive, reason, plan, remember, and act in clinical environments. This survey departs from the capability-first perspective of existing literature and instead begins from clinical deployment, asking what tasks, contamination-resistant benchmarks, and interactive training environments are required before medical agents can be trusted in practice. Medical agents are formalized as sequential decision-making systems under partial observability, together with a three-level autonomy taxonomy spanning assisted, cooperative, and fully autonomous operation. The field is organized along a unified scaling spine consisting of framework scaling, capability scaling, and environment scaling. Within this framework, clinical environment scaling, the integration of tools, data, and clinical gyms, is identified as the most actionable yet underexplored direction for agents operating in PACS, EHR, and FHIR ecosystems. Clinical self-evolution, where agents improve through interaction with their environments rather than parameter scaling alone, is further positioned as a key research frontier, drawing insights from self-improving agents, agent gyms, and test-time compute scaling. Applications across radiology, pathology, ophthalmology, and hospital workflows are examined together with deployment challenges including hallucination, cascading failures, and fairness. By consolidating more than 300 references, with particular emphasis on advances from 2025 to 2026, this survey provides a roadmap toward trustworthy, self-improving medical imaging systems for real clinical practice.

cs.AI↗
arXiv2026

CoRe: A Continuously Reward-Finetuned LLM Query Rewriter for Multi-Stage Context-Aware Relevance in Web-Scale Video Search

LLM-based query rewriters in production face a tension: the training reward must reflect how the rewrite is consumed by the production ranker, yet the training procedure must be cheap enough to support continuous redeployment as data drifts. We present CoRe (Context Relevance), such a system, redeployed weekly for over five months in a major short-video search engine. Our reward uses the deployed multimodal relevance model as its source and a multiplicative ratio form mirroring the production fusion algebra, closing the simulation-production gap that offline reward proxies leave open. A semi-online Mixed Preference Optimization loop makes this reward affordable at multi-million-instance weekly scale: a DPO-style pairwise objective restricts the gradient pass to a small top-k/bottom-k subset of sampled trajectories, and a phase structure reduces trainer/inference-server parameter syncs from per-step to per-phase. An automated promotion gate over reward-like and stability metrics detected and recovered from a real reward-hacking incident in production. Rewriter output is consumed as parallel relevance signals at recall, rawrank, and finerank without displacing the original signals, bounding rewriter-failure blast radius. Online A/B from two sequential production launches, first deploying the rewriter at finerank, then extending consumption to recall and rawrank, delivers statistically significant reductions in change-query rate on rewrite-impacted queries, with all headline relevance and engagement metrics moving in the expected direction.

cs.IR↗
arXiv2026

Data-driven Head Motion Generation through Natural Gaze-Head Coordination

We present the first data-driven approach to model temporal gaze-head coordination from large-scale in-the-wild facial videos. To obtain training data for generalizable learning, we propose an automatic pipeline that extracts natural yet diverse gaze and head motions with off-the-shelf appearance-based gaze estimators. To capture the probabilistic correlation and temporal dynamics of gaze-head coordination, we build our model on a generative conditional Variational Autoencoder for plausible yet diverse gaze-conditioned head motion generations. We further apply our framework to gaze-controlled facial video generation, where we enable video generation with natural and realistic head motion correlated to the input gaze - an aspect that has not been emphasized before. Human evaluation and quantitative comparisons demonstrate our method's effectiveness and validate our design choices, with evaluators showing statistically significant preference for our approach over baseline methods.

cs.CV↗
arXiv2026

Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Sequence-Level Likelihood

Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs), particularly in their mathemat ical reasoning performance. However, GRPO and related entropy regularization methods still struggle with token-level sparse-rewards, which is an inherent chal lenge in chain-of-thought (CoT) reasoning. These approaches often rely on undifferen tiated token-level entropy regularization, which easily leads to entropy collapse or model degradation under sparse token rewards. In this work, we propose TEPO, a novel token-level framework that (1) leverages sequence-level likelihood to link group-level rewards with individual tokens via token-level aggregation, and (2) introduces a token-level KL-Divergence mask constraint that targets tokens with positive advantages and decreasing entropy to mitigate abrupt policy updates. Experiments demonstrate that TEPO not only achieves state-of-the-art performance on mathematical reasoning benchmarks but also markedly enhances training stability, reducing convergence time by 50% compared with GRPO/DAPO.

cs.CL↗
arXiv2026

PolyFormer: learning efficient reformulations for scalable optimization under complex physical constraints

Real-world optimization problems are often constrained by complex physical laws that limit computational scalability. These constraints are inherently tied to complex regions, and thus learning models that incorporate physical and geometric knowledge, i.e., physics-informed machine learning (PIML), offer a promising pathway for efficient solution. Here, we introduce PolyFormer, which opens a new direction for PIML in prescriptive optimization tasks, where physical and geometric knowledge is not merely used to regularize learning models, but to simplify the problems themselves. PolyFormer captures geometric structures behind constraints and transforms them into efficient polytopic reformulations, thereby decoupling problem complexity from solution difficulty and enabling off-the-shelf optimization solvers to efficiently produce feasible solutions with acceptable optimality loss. Through evaluations across three important problems (large-scale resource aggregation, network-constrained optimization, and optimization under uncertainty), PolyFormer achieves computational speedups up to 6,400-fold and memory reductions up to 99.87%, while maintaining solution quality competitive with or superior to state-of-the-art methods. These results demonstrate that PolyFormer provides an efficient and reliable solution for scalable constrained optimization, expanding the scope of PIML to prescriptive tasks in scientific discovery and engineering applications.

cs.LG↗
arXiv2026

Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcement

Retrieval-augmented generation (RAG) improves performance on knowledge-intensive tasks but can be derailed by wrong, irrelevant, or conflicting retrieved text, causing models to rely on inaccurate evidence and cascade errors. We propose Knowledgeable-R1, a reinforcement-learning framework that explicitly trains large language models to use parametric knowledge (PK) to resist contextual interference while still exploiting external context when it is reliably helpful. Knowledgeable-R1 introduces a joint sampling scheme that generates paired responses with and without retrieval, and learns both local advantages (within each decoding regime) and global advantages under the same input to quantify when to ignore misleading context versus adopt it. We employ an asymmetric advantage transformation that amplifies exploratory behaviors toward parametric knowledge. Experiments show that Knowledgeable-R1 significantly improves robustness and reasoning accuracy in knowledge conflict scenarios and general RAG scenarios, outperforming SOTA baselines by +22.89% in counterfactual scenarios, and without degradation when the retrieved context is fully accurate.Our code are available at https://github.com/lcy80366872/knowledgeable-R1.

cs.CL↗
arXiv2026

Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis

Safety alignment in Large Language Models (LLMs) inherently presents a multi-objective optimization conflict, often accompanied by an unintended degradation of general capabilities. Existing mitigation strategies typically rely on global gradient geometry to resolve these conflicts, yet they overlook Modular Heterogeneity within Transformers, specifically that the functional sensitivity and degree of conflict vary substantially across different attention heads. Such global approaches impose uniform update rules across all parameters, often resulting in suboptimal trade-offs by indiscriminately updating utility sensitive heads that exhibit intense gradient conflicts. To address this limitation, we propose Conflict-Aware Sparse Tuning (CAST), a framework that integrates head-level diagnosis with sparse fine-tuning. CAST first constructs a pre-alignment conflict map by synthesizing Optimization Conflict and Functional Sensitivity, which then guides the selective update of parameters. Experiments reveal that alignment conflicts in LLMs are not uniformly distributed. We find that the drop in general capabilities mainly comes from updating a small group of ``high-conflict'' heads. By simply skipping these heads during training, we significantly reduce this loss without compromising safety, offering an interpretable and parameter-efficient approach to improving the safety-utility trade-off.

cs.LG↗
arXiv2025

Robust Long-term Test-Time Adaptation for 3D Human Pose Estimation through Motion Discretization

Online test-time adaptation addresses the train-test domain gap by adapting the model on unlabeled streaming test inputs before making the final prediction. However, online adaptation for 3D human pose estimation suffers from error accumulation when relying on self-supervision with imperfect predictions, leading to degraded performance over time. To mitigate this fundamental challenge, we propose a novel solution that highlights the use of motion discretization. Specifically, we employ unsupervised clustering in the latent motion representation space to derive a set of anchor motions, whose regularity aids in supervising the human pose estimator and enables efficient self-replay. Additionally, we introduce an effective and efficient soft-reset mechanism by reverting the pose estimator to its exponential moving average during continuous adaptation. We examine long-term online adaptation by continuously adapting to out-of-domain streaming test videos of the same individual, which allows for the capture of consistent personal shape and motion traits throughout the streaming observation. By mitigating error accumulation, our solution enables robust exploitation of these personal traits for enhanced accuracy. Experiments demonstrate that our solution outperforms previous online test-time adaptation methods and validate our design choices.

cs.CV↗
arXiv2025

Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood

Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs), particularly by boosting their mathematical performance. However, GRPO and related entropy-regularization methods still face challenges rooted in the sparse token rewards inherent to chain-of-thought (CoT). Current approaches often rely on undifferentiated token-level entropy adjustments, which frequently lead to entropy collapse or model collapse. In this work, we propose TEPO, a novel token-level framework that incorporates Markov Likelihood (sequence likelihood) links group-level rewards with tokens via token-level aggregation. Experiments show that TEPO consistently outperforms existing baselines across key metrics (including @k and accuracy). It not only sets a new state of the art on mathematical reasoning tasks but also significantly enhances training stability.

cs.CL↗
arXiv2024

Generative Hierarchical Temporal Transformer for Hand Pose and Action Modeling

We present a novel unified framework that concurrently tackles recognition and future prediction for human hand pose and action modeling. Previous works generally provide isolated solutions for either recognition or prediction, which not only increases the complexity of integration in practical applications, but more importantly, cannot exploit the synergy of both sides and suffer suboptimal performances in their respective domains. To address this problem, we propose a generative Transformer VAE architecture to model hand pose and action, where the encoder and decoder capture recognition and prediction respectively, and their connection through the VAE bottleneck mandates the learning of consistent hand motion from the past to the future and vice versa. Furthermore, to faithfully model the semantic dependency and different temporal granularity of hand pose and action, we decompose the framework into two cascaded VAE blocks: the first and latter blocks respectively model the short-span poses and long-span action, and are connected by a mid-level feature representing a sub-second series of hand poses. This decomposition into block cascades facilitates capturing both short-term and long-term temporal regularity in pose and action modeling, and enables training two blocks separately to fully utilize datasets with annotations of different temporal granularities. We train and evaluate our framework across multiple datasets; results show that our joint modeling of recognition and prediction improves over isolated solutions, and that our semantic and temporal hierarchy facilitates long-term pose and action modeling.

cs.CV↗
arXiv2024

Quantifying and Optimizing the Time-Coupled Flexibilities at the Distribution-Level for TSO-DSO Coordination

The flexibilities provided by the distributed energy resources (DERs) in distribution systems enable the coordination of transmission system operator (TSO) and distribution system operators (DSOs). At the distribution level, the flexibilities should be optimized for participation in the transmission system operation. This paper first proposes a flexibility quantification method that quantifies the costs of providing flexibilities and their values to the DSO in the TSO-DSO coordination. Compared with traditional power-range-based quantification approaches that are mainly suitable for generators, the proposed method can directly capture the time-coupling characteristics of DERs' individual and aggregated flexibility regions. Based on the quantification method, we further propose a DSO optimization model to activate the flexibilities from DER aggregators in the distribution system for energy arbitrage and ancillary services provision in the transmission system, along with a revenue allocation strategy that ensures a non-profit DSO. Numerical tests on the IEEE test system verify the proposed methods.

eess.SY↗
arXiv2024

Multiple Joint Chance Constraints Approximation for Uncertainty Modeling in Dispatch Problems

Uncertainty modeling has become increasingly important in power system decision-making. The widely-used tractable uncertainty modeling method-chance constraints with Conditional Value at Risk (CVaR) approximation, can be overconservative and even turn an originally feasible problem into an infeasible one. This paper proposes a new approximation method for multiple joint chance constraints (JCCs) to model the uncertainty in dispatch problems, which solves the conservativeness and potential infeasibility concerns of CVaR. The proposed method is also convenient for controlling the risk levels of different JCCs, which is necessary for power system applications since different resources may be affected by varying degrees of uncertainty or have different importance to the system. We then formulate a data-driven distributionally robust chance-constrained programming model for the power system multiperiod dispatch problem and leverage the proposed approximation method to solve it. In the numerical simulations, two small general examples clearly demonstrate the superiority of the proposed method, and the results of the multiperiod dispatch problem on IEEE test cases verify its practicality.

math.OC↗
arXiv2024

MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models

Large language models (LLMs) have achieved remarkable performance in natural language understanding and generation tasks. However, they often suffer from limitations such as difficulty in incorporating new knowledge, generating hallucinations, and explaining their reasoning process. To address these challenges, we propose a novel prompting pipeline, named \method, that leverages knowledge graphs (KGs) to enhance LLMs' inference and transparency. Our method enables LLMs to comprehend KG inputs and infer with a combination of implicit and external knowledge. Moreover, our method elicits the mind map of LLMs, which reveals their reasoning pathways based on the ontology of knowledge. We evaluate our method on diverse question \& answering tasks, especially in medical domains, and show significant improvements over baselines. We also introduce a new hallucination evaluation benchmark and analyze the effects of different components of our method. Our results demonstrate the effectiveness and robustness of our method in merging knowledge from LLMs and KGs for combined inference. To reproduce our results and extend the framework further, we make our codebase available at https://github.com/wyl-willing/MindMap.

cs.AI↗
arXiv2023

Improved Inner Approximation for Aggregating Power Flexibility in Active Distribution Networks and its Applications

Concise and reliable modeling for aggregating power flexibility of distributed energy resources in active distribution networks (ADNs) is a crucial technique for coordinating transmission and distribution networks. Our recent research has successfully derived an explicit expression for the exact aggregation model (EAM) of power flexibility at the substation level under linearized distribution network constraints. The EAM, however, is impractical for decision-making purposes due to its exponential complexity. In this paper, we propose an inner approximation method for aggregating flexibility in ADNs that utilizes the properties of the EAM to improve performance. Specifically, the geometric prototype of the inner approximation model is defined according to a subset of the coefficient vector set of the EAM, which enhances the accuracy. On the other hand, the computation efficiency of the inner approximation is also significantly improved by exploiting the regularity of coefficient vectors in the EAM in the parameter calculation process. The inner approximated flexibility model of ADNs is further incorporated into the security-constrained unit commitment problem as an application. Numerical simulations verify the effectiveness of the proposed method.

eess.SY↗
arXiv2023

Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos

Understanding dynamic hand motions and actions from egocentric RGB videos is a fundamental yet challenging task due to self-occlusion and ambiguity. To address occlusion and ambiguity, we develop a transformer-based framework to exploit temporal information for robust estimation. Noticing the different temporal granularity of and the semantic correlation between hand pose estimation and action recognition, we build a network hierarchy with two cascaded transformer encoders, where the first one exploits the short-term temporal cue for hand pose estimation, and the latter aggregates per-frame pose and object information over a longer time span to recognize the action. Our approach achieves competitive results on two first-person hand action benchmarks, namely FPHA and H2O. Extensive ablation studies verify our design choices.

cs.CV↗
arXiv2023

Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images

In this paper, we present a generalizable model-free 6-DoF object pose estimator called Gen6D. Existing generalizable pose estimators either need high-quality object models or require additional depth maps or object masks in test time, which significantly limits their application scope. In contrast, our pose estimator only requires some posed images of the unseen object and is able to accurately predict the poses of the object in arbitrary environments. Gen6D consists of an object detector, a viewpoint selector and a pose refiner, all of which do not require the 3D object model and can generalize to unseen objects. Experiments show that Gen6D achieves state-of-the-art results on two model-free datasets: the MOPED dataset and a new GenMOP dataset collected by us. In addition, on the LINEMOD dataset, Gen6D achieves competitive results compared with instance-specific pose estimators. Project page: https://liuyuan-pal.github.io/Gen6D/.

cs.CV↗
arXiv2023

IMKGA-SM: Interpretable Multimodal Knowledge Graph Answer Prediction via Sequence Modeling

Multimodal knowledge graph link prediction aims to improve the accuracy and efficiency of link prediction tasks for multimodal data. However, for complex multimodal information and sparse training data, it is usually difficult to achieve interpretability and high accuracy simultaneously for most methods. To address this difficulty, a new model is developed in this paper, namely Interpretable Multimodal Knowledge Graph Answer Prediction via Sequence Modeling (IMKGA-SM). First, a multi-modal fine-grained fusion method is proposed, and Vgg16 and Optical Character Recognition (OCR) techniques are adopted to effectively extract text information from images and images. Then, the knowledge graph link prediction task is modelled as an offline reinforcement learning Markov decision model, which is then abstracted into a unified sequence framework. An interactive perception-based reward expectation mechanism and a special causal masking mechanism are designed, which "converts" the query into an inference path. Then, an autoregressive dynamic gradient adjustment mechanism is proposed to alleviate the insufficient problem of multimodal optimization. Finally, two datasets are adopted for experiments, and the popular SOTA baselines are used for comparison. The results show that the developed IMKGA-SM achieves much better performance than SOTA baselines on multimodal link prediction datasets of different sizes.

cs.AI↗
arXiv2022

DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation

Scalable 6D pose estimation for rigid objects from RGB images aims at handling multiple objects and generalizing to novel objects. Building on a well-known auto-encoding framework to cope with object symmetry and the lack of labeled training data, we achieve scalability by disentangling the latent representation of auto-encoder into shape and pose sub-spaces. The latent shape space models the similarity of different objects through contrastive metric learning, and the latent pose code is compared with canonical rotations for rotation retrieval. Because different object symmetries induce inconsistent latent pose spaces, we re-entangle the shape representation with canonical rotations to generate shape-dependent pose codebooks for rotation retrieval. We show state-of-the-art performance on two benchmarks containing textureless CAD objects without category and daily objects with categories respectively, and further demonstrate improved scalability by extending to a more challenging setting of daily objects across categories.

cs.CV↗