arXiv subjects

Ziqing Wang

Publications and source records attributed to Ziqing Wang.

At least 19 recordsLinked to original sources

arXiv2026

RTP-LLM: Building an Evolvable and Reliable LLM Inference Engine at Alibaba Scale

Large language models and inference techniques evolve rapidly, making model enablement a recurring production task rather than a one-time integration effort. At Alibaba, a shared inference infrastructure must keep pace with new models and serving capabilities while remaining reliable across heterogeneous production environments. To reconcile rapid evolution with production reliability, we present RTP-LLM, an open-source production inference engine developed and deployed at Alibaba. Its architecture separates model-specific execution from shared request processing, state management, and resource coordination. Explicit interfaces localize compatible model changes while allowing models and deployment configurations to reuse common serving mechanisms. RTP-LLM has evolved from an exploratory system into a shared production engine that supports $\sim$100 models and processes hundreds of trillions of tokens per day. We describe how its architecture and production practices accommodate model evolution and contain the impact of failures, and share lessons for building evolvable and reliable inference engines at enterprise scale.

cs.OS↗

arXiv2026

Quantum Advantage in Beam-Displacement Estimation for Inter-Satellite Quantum-Secure Time Transfer

In this work, we investigate the practical feasibility of achieving a quantum advantage, in the context of inter-satellite quantum communication, of satellite position estimation. The investigation focuses on a quantum-enhanced scheme in which squeezing is added to the derivative mode of a Gaussian probe beam as a means of estimating photon-beam displacement. The performance of the scheme is compared against the standard quantum limit achieved by an optimal classical beam-displacement estimation scheme under a fair same-total-energy constraint. We find that although the benefit provided by squeezing rapidly diminishes as the inter-satellite distance increases due to diffraction-induced beam spreading and subsequent truncation by the finite receiver aperture, a quantum advantage can still be expected over inter-satellite distances up to approximately 100 km under practical satellite configurations. This distance scale between satellites is anticipated for Starlink-type satellite constellations.

quant-ph↗

arXiv2026

DiMOS: Doob-Guided Inference-Time Multi-Objective Search for Scientific Design

Scientific design often requires jointly satisfying multiple objectives and constraints. Pretrained masked diffusion models provide a generative foundation for this task, but fine-tuning them to meet these objectives and constraints incurs additional training costs, motivating inference-time guidance with frozen models. However, such guidance faces two challenges: pass-or-fail constraints and black-box reward models may provide no useful gradients, while jointly satisfying multiple requirements can leave a small feasible region, making feasible designs difficult to find within a limited inference budget. To address these challenges, we introduce DiMOS, a training-free framework for multi-objective scientific design. Using joint rewards from candidate completions, DiMOS performs approximate Doob-guided local resampling without requiring reward gradients. To allocate computation efficiently, it uses budget-efficient trajectory search to focus computation on promising continuations. Across six DNA, protein, and RNA tasks, DiMOS attains the highest joint success rate at comparable generation times, up to $1.98\times$ the strongest baseline on DNA and protein, while maintaining high sequence uniqueness and naturalness.

cs.AI↗

arXiv2026

MedicalHarness: A Controlled Evaluation of LLMs and Agent Harnesses on Medical Tasks

LLM agents are increasingly built for medical work and scored on clinical benchmarks. Each such score, however, comes from a model running inside an agent harness, the system that controls the loop between the model and its environment. An agent's score is therefore a property of a model--harness pair. For medical agents, how much outcomes change with the harness has rarely been measured. Measuring this change, and explaining it, raises two challenges. First, a harness comparison must change nothing but the harness and be repeated across models and kinds of task. Second, comparing whole harnesses leaves their mechanisms bundled together, so it cannot show when an individual mechanism helps. To address these challenges, we present MedicalHarness, a controlled study of models and agent harnesses on medical tasks. We first build MedicalHarnessBench to evaluate agents on $107$ tasks across four domains that each test a different harness capability. Using this benchmark, we run five open-weight models under five agent harnesses, changing only the harness within a comparison, and analyze both outcomes and execution traces. To study individual mechanisms, we build MH-Lab, a controlled harness that switches off context management, planning or tool exposure one at a time within a shared execution loop. We find that the harness and its interaction with the model account for about a quarter of the outcome variance, and that no single harness is best across models and tasks. Code and data are available at https://github.com/REAL-Lab-NU/MedicalHarness.

cs.CL↗

arXiv2026

RAPTOR: Ridge-Adaptive Logistic Probes

Probing studies what information is encoded in a frozen LLM's layer representations by training a lightweight predictor on top of them. Beyond analysis, probes are often used operationally in probe-then-steer pipelines: a learned concept vector is extracted from a probe and injected via additive activation steering by adding it to a layer representation during the forward pass. The effectiveness of this pipeline hinges on estimating concept vectors that are accurate, directionally stable under ablation, and inexpensive to obtain. Motivated by these desiderata, we propose RAPTOR (Ridge-Adaptive Logistic Probe), a simple L2-regularized logistic probe whose validation-tuned ridge strength yields concept vectors from normalized weights. Across extensive experiments on instruction-tuned LLMs and human-written concept datasets, RAPTOR matches or exceeds strong baselines in accuracy while achieving competitive directional stability and substantially lower training cost; these quantitative results are supported by qualitative downstream steering demonstrations. Finally, using the Convex Gaussian Min-max Theorem (CGMT), we provide a mechanistic characterization of ridge logistic regression in an idealized Gaussian teacher-student model in the high-dimensional few-shot regime, explaining how penalty strength mediates probe accuracy and concept-vector stability and yielding structural predictions that qualitatively align with trends observed on real LLM embeddings.

cs.LG↗

arXiv2026

LatentDx: Latent Multi-Agent Communication for Cross-Hospital Rare-Disease Diagnosis

Rare diseases affect over $300$ million patients across more than $7{,}000$ conditions, yet no single hospital encounters enough cases of any one condition for reliable diagnosis. Cross-hospital collaboration could help by allowing a diagnosing institution to use distributed, case-specific diagnostic evidence, but privacy regulations restrict the transmission of identifiable clinical text across institutional boundaries. This setting raises two challenges: existing medical agent systems often rely on textual evidence exchange, while raw latent states such as hidden states and KV caches may still reveal prompt-derived clinical content. We introduce LatentDx, a latent multi-agent communication framework in which hospital agents keep private clinical records and retrieved cases local, and send compact latent KV blocks to a host agent for rare-disease diagnosis. LatentDx supports two deployment settings: same-backbone hospital agents use latent KV distillation, while hospitals with different LLM backbones use cross-family latent alignment. On CrossRare-Bench, a self-built large-scale rare-disease benchmark with hospital-level partitions, LatentDx improves cross-hospital diagnostic performance while reducing reconstructable clinical content relative to raw-latent communication baselines.

cs.CL↗

arXiv2026

Adaptive Context Parallelism for Production LLM Serving

As LLM context windows expand and input sequences grow longer, serving systems face increasing computational and memory demands. Context parallelism (CP), which partitions the input sequence across multiple ranks to parallelize the computation, has therefore become increasingly important for efficient LLM serving. However, existing CP-enabled systems either rely on static CP configurations or adjust the CP degree only for active requests or batches. In this paper, we present Vertumnus, an adaptive CP serving system designed for heterogeneous and evolving workloads. At the request level, Vertumnus routes requests among workers with different CP degrees using a placement cost that combines predicted queuing delay, cache-aware prefill time, and GPU-time cost. At the cluster level, Vertumnus adapts the worker composition through seconds-scale split and merge operations as workload demand changes. Vertumnus further introduces a global prefix-cache management policy that coordinates cache placement and replication among workers with the same or different CP degrees, preserving cache locality as request assignments and worker composition change. Experiments on a 64-GPU cluster with public and production workloads show that, under the highest evaluated loads, Vertumnus reduces mean TTFT by up to 28.1% and improves token-weighted SLO attainment by up to 13.3 percentage points over the strongest baseline.

cs.OS↗

arXiv2026

Predicting Immune Biomarkers with MultiModal Mixture-of-Expert Pathology Foundation Models Empowers Precision Oncology

Predicting immune biomarkers associated with the tumor immune microenvironment (TIME) is critical for advancing precision oncology, yet existing approaches are largely limited to single image modalities and suffer from insufficient resolution and incomplete utilization of complementary clinical and biological information. Here we introduce MixTIME, a multimodal foundation model that leverages a mixture-of-experts (MoE) architecture to integrate pathology foundation models trained across distinct modalities: image only (UNIv2), image text (CONCHv1.5), and image transcriptomic (STPath) representations for pixel-level and slide-level prediction of multiplex immunofluorescence (mIF) protein expression from hematoxylin and eosin (HE) whole-slide images. MixTIME employs a learnable router to dynamically weight expert contributions and is trained with a distribution- and tendency-aware loss function. Benchmarked on two datasets of different scales, MixTIME achieves state-of-the-art performance across 17 protein markers as measured by correlation metrics. The predicted mIF profiles substantially enhance downstream tasks, including spatial domain identification, survival prediction, and AI-assisted pathology report generation validated by expert pathologists from multiple institutes across the world. Furthermore, MixTIME enables longitudinal tracking of protein expression dynamics across clinical time points and reveals protein gene interaction patterns linked to drug resistance and immune suppression in tumor microenvironments. Collectively, MixTIME provides a scalable framework for multimodal biomarker discovery and clinical translation in computational pathology.

cs.CV↗

arXiv2026

Can Post-Training Turn LLMs into Good Medical Coders? An Empirical Study of Generative ICD Coding

Automated International Classification of Diseases (ICD) coding is a core medical-coding task for billing, epidemiology, and clinical decision support. Generative large language models (LLMs) are often reported as weak medical coders, but this finding mainly comes from inference-time settings such as prompting, retrieval, reranking, or tool use, leaving the role of task-specific post-training underexplored. We present a controlled empirical study of post-training for generative ICD coding, comparing discriminative baselines with LLM coders across prompting, supervised fine-tuning, and reinforcement learning under a common protocol and metric set. To our knowledge, this is the first study to evaluate RL-based post-training for generative LLM coders in ICD coding. We further introduce PHI, a diagnostic curriculum that extends GRPO to refine missed-code cases. Our results show that prompting-only evaluation substantially underestimates the potential of LLMs for ICD coding. SFT provides the main capability jump, GRPO further improves code-set prediction beyond SFT, and PHI provides targeted gains on macro-level performance. These findings suggest that the main bottleneck is not the generative formulation alone, but how the model is adapted and optimized for full-taxonomy recall. We release our code, data splits, and checkpoints at https://github.com/AlexandreWANG915/LLM4ICD.

cs.CL↗

arXiv2026

Benchmarking AI Agents for Addressing Scientific Challenges Across Scales

AI agents are increasingly being developed to accelerate scientific discovery, yet their practical capabilities in real research settings remain poorly understood. Existing benchmarks for AI agents rarely capture the complexity, heterogeneity, and extended reasoning required by scientific work, whereas benchmarks for scientific tasks often reduce research to static, direct problems and provide limited support for interactive evaluation. Here, we introduce SciAgentArena, a systematic benchmark for evaluating AI agents in real-world scientific research scenarios drawn from emerging needs across multiple domains. SciAgentArena comprises approximately 200 tasks with stepwise verification and an interactive, agent-agnostic environment for assessing diverse AI agents. Using this benchmark, we find that current agents can contribute effectively to well-specified data-analysis workflows, particularly when the task structure and evaluation criteria are clear. However, their performance remains uneven across scientific contexts: agents struggle to generate genuinely novel insights, sustain self-directed exploration, and formulate robust solutions for open-ended research questions. We further characterize common failure modes across agents and identify opportunities for improving their reliability, autonomy, and scientific reasoning. Together, SciAgentArena provides a practical framework for measuring progress in AI agents for science and for guiding the design of future agents capable of addressing complex scientific challenges. Full codes, tasks, and datasets can be accessed via this link: https://sciagentarena.github.io/.

cs.AI↗

arXiv2026

MedLoCoMo: A Long-Context Multi-Session Medical Dialogue Benchmark for Large Language Models

MedLoCoMo is a Medical Long-Context Memory benchmark for patient-specific clinical reasoning over multi-admission medical dialogue. Existing medical QA benchmarks largely test short context knowledge or single document grounding, leaving open whether LLMs can use, connect, and abstain over longitudinal patient histories. We build MedLoCoMo from deidentified MIMIC-IV and MIMIC-IV-Note records by constructing admission-level clinical packets, synthesizing grounded doctor-patient conversations, and generating evidence linked QA items over single-admission, cross-admission, and adversarial unanswerable settings. The benchmark contains 100 patient timelines averaging 1,669.8 turns, 29.7 sessions, and 74,512.2 tokens per conversation. Across the evaluated baselines, cross-admission reasoning is consistently harder than localized evidence use, even when models have long context windows or use external memory or retrieval methods. The code and MedLoCoMo benchmark release is available at https://github.com/leozzy13/MedLoCoMo for use and reproducibility.

cs.AI↗

arXiv2026

eLLM: Elastic Memory Management Framework for Efficient LLM Serving

Large Language Models are increasingly being deployed in datacenters. Serving these models requires careful memory management, as their memory usage includes static weights, dynamic activations, and key-value caches. While static weights are constant and predictable, dynamic components such as activations and KV caches change frequently during runtime, presenting significant challenges for efficient memory management. Modern LLM serving systems typically handle runtime memory and KV caches at distinct abstraction levels: runtime memory management relies on static tensor abstractions, whereas KV caches utilize a page table-based virtualization layer built on top of the tensor abstraction. This virtualization dynamically manages KV caches to mitigate memory fragmentation. However, this dual-level approach fundamentally isolates runtime memory and KV cache management, resulting in suboptimal memory utilization under dynamic workloads, which can lead to a nearly 20% drop in throughput. To address these limitations, we propose eLLM, an elastic memory management framework inspired by the classical memory ballooning mechanism in operating systems. The core components of eLLM include: (1) Virtual Tensor Abstraction, which decouples the virtual address space of tensors from the physical GPU memory, creating a unified and flexible memory pool; (2) an Elastic Memory Mechanism that dynamically adjusts memory allocation through runtime memory inflation and deflation, leveraging CPU memory as an extensible buffer; and (3) a Lightweight Scheduling Strategy employing SLO-aware policies to optimize memory utilization and effectively balance performance trade-offs under stringent SLO constraints. Comprehensive evaluations demonstrate that eLLM significantly outperforms state-of-the-art systems, 2.32x higher decoding throughput, and supporting 3x larger batch sizes for 128K-token inputs.

cs.DC↗

arXiv2026

HopRank: Self-Supervised LLM Preference-Tuning on Graphs for Few-Shot Node Classification

Node classification on text-attributed graphs (TAGs) is a fundamental task with broad applications in citation analysis, social networks, and recommendation systems. Current GNN-based approaches suffer from shallow text encoding and heavy dependence on labeled data, limiting their effectiveness in label-scarce settings. While large language models (LLMs) naturally address the text understanding gap with deep semantic reasoning, existing LLM-for-graph methods either still require abundant labels during training or fail to exploit the rich structural signals freely available in graph topology. Our key observation is that, in many real-world TAGs, edges predominantly connect similar nodes under the homophily principle, meaning graph topology inherently encodes class structure without any labels. Building on this insight, we reformulate node classification as a link prediction task and present HopRank, a fully self-supervised LLM-tuning framework for TAGs. HopRank constructs preference data via hierarchical hop-based sampling and employs adaptive preference learning to prioritize informative training signals without any class labels. At inference, nodes are classified by predicting their connection preferences to labeled anchors, with an adaptive early-exit voting scheme to improve efficiency. Experiments on three TAG benchmarks show that HopRank matches fully-supervised GNNs and substantially outperforms prior graph-LLM methods, despite using zero labeled training data.

cs.CL↗

arXiv2026

Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models

Achieving seamless, human-like interaction remains a key challenge for full-duplex spoken dialogue models (SDMs). Reinforcement learning (RL) has substantially enhanced text- and vision-language models, while well-designed reward signals are crucial for the performance of RL. We consider RL a promising strategy to address the key challenge for SDMs. However, a fundamental barrier persists: prevailing automated metrics for assessing interaction quality rely on superficial proxies, such as behavioral statistics or timing-prediction accuracy, failing to provide reliable reward signals for RL. On the other hand, human evaluations, despite their richness, remain costly, inconsistent, and difficult to scale. We tackle this critical barrier by proposing a Dual-Axis Generative Reward Model, which is trained to understand complex interaction dynamics using a detailed taxonomy and an annotated dataset, produces a single score and, crucially, provides separate evaluations for semantic quality and interaction timing. Such dual outputs furnish precise diagnostic feedback for SDMs and deliver a dependable, instructive reward signal suitable for online reinforcement learning. Our model achieves state-of-the-art performance on interaction-quality assessment across a wide spectrum of datasets, spanning synthetic dialogues and complex real-world interactions.

cs.AI↗

arXiv2026

WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training

End-to-end spoken dialogue models have garnered significant attention because they offer a higher potential ceiling in expressiveness and perceptual ability than cascaded systems. However, the intelligence and expressiveness of current open-source spoken dialogue models often remain below expectations. Motivated by the success of online reinforcement learning(RL) in other domains, one might attempt to directly apply preference optimization to spoken dialogue models, yet this transfer is non-trivial. We analyze these obstacles from the perspectives of reward modeling and rollout sampling, focusing on how sparse preference supervision interacts with dense speech generation under shared-parameter updates. Based on the analysis, we propose a modality-aware adaptive post-training recipe that makes RL practical for spoken dialogue: it constrains preference updates to the semantic channel and improves acoustic behavior via explicit anchoring, while dynamically regulating their mixture from rollout statistics to avoid unreliable preference gradients. We evaluate the method across multiple spoken dialogue benchmarks and representative architectures, and observe consistent improvements in semantic quality and speech expressiveness.

cs.AI↗

arXiv2026

MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization

In drug discovery, molecular optimization aims to iteratively refine a lead compound to improve molecular properties while preserving structural similarity to the original molecule. However, each oracle evaluation is expensive, making sample efficiency a key challenge for existing methods under a limited oracle budget. Trial-and-error approaches require many oracle calls, while methods that leverage external knowledge tend to reuse familiar templates and struggle on challenging objectives. A key missing piece is long-term memory that can ground decisions and provide reusable insights for future optimizations. To address this, we present MolMem (\textbf{Mol}ecular optimization with \textbf{Mem}ory), a multi-turn agentic reinforcement learning (RL) framework with a dual-memory system. Specifically, MolMem uses Static Exemplar Memory to retrieve relevant exemplars for cold-start grounding, and Evolving Skill Memory to distill successful trajectories into reusable strategies. Built on this memory-augmented formulation, we train the policy with dense step-wise rewards, turning costly rollouts into long-term knowledge that improves future optimization. Extensive experiments show that MolMem achieves 90\% success on single-property tasks (1.5$\times$ over the best baseline) and 52\% on multi-property tasks using only 500 oracle calls. Our code is available at https://github.com/REAL-Lab-NU/MolMem.

cs.LG↗

arXiv2026

Relative Wavefront Error Correction Over a 2.4 km Free-Space Optical Link via Machine Learning

In coherent optical communication across turbulent atmospheric channels, reference beacons can be multiplexed with information-encoded signals during transmission. In this case, it is commonly assumed that the wavefront distortion of the two is equivalent. In contrast to this assumption, we present experimental evidence of relative wavefront errors (WFEs) between polarization-multiplexed reference beacons and signals, after passing through a 2.4 km atmospheric link. We develop machine learning-based wavefront correction algorithms to compensate for observed WFEs, via phase retrieval, resulting in up to a 2/3 reduction in the relative phase error variance. Further, we analyze the excess noise contributions from relative WFEs in the context of continuous-variable quantum key distribution (CV-QKD), where our findings suggest that if future CV-QKD implementations employ wavefront correction algorithms similar to those reported here, an order of magnitude increase in secure key rates may be forthcoming.

physics.optics↗

arXiv2026

GlassMol: Interpretable Molecular Property Prediction with Concept Bottleneck Models

Machine learning accelerates molecular property prediction, yet state-of-the-art Large Language Models and Graph Neural Networks operate as black boxes. In drug discovery, where safety is critical, this opacity risks masking false correlations and excluding human expertise. Existing interpretability methods suffer from the effectiveness-trustworthiness trade-off: explanations may fail to reflect a model's true reasoning, degrade performance, or lack domain grounding. Concept Bottleneck Models (CBMs) offer a solution by projecting inputs to human-interpretable concepts before readout, ensuring that explanations are inherently faithful to the decision process. However, adapting CBMs to chemistry faces three challenges: the Relevance Gap (selecting task-relevant concepts from a large descriptor space), the Annotation Gap (obtaining concept supervision for molecular data), and the Capacity Gap (degrading performance due to bottleneck constraints). We introduce GlassMol, a model-agnostic CBM that addresses these gaps through automated concept curation and LLM-guided concept selection. Experiments across thirteen benchmarks demonstrate that \method generally matches or exceeds black-box baselines, suggesting that interpretability does not sacrifice performance and challenging the commonly assumed trade-off. Code is available at https://github.com/walleio/GlassMol.

cs.LG↗