arXiv subjects

Yutong Huang

Publications and source records attributed to Yutong Huang.

11 recordsLinked to original sources

arXiv2026

DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models

The emergence of groundbreaking large language models capable of performing complex reasoning tasks holds significant promise for addressing various scientific challenges, including those arising in complex clinical scenarios. To enable their safe and effective deployment in real-world healthcare settings, it is urgently necessary to benchmark the diagnostic capabilities of current models systematically. Given the limitations of existing medical benchmarks in evaluating advanced diagnostic reasoning, we present DiagnosisArena, a comprehensive and challenging benchmark designed to rigorously assess professional-level diagnostic competence. DiagnosisArena consists of 1,113 pairs of segmented patient cases and corresponding diagnoses, spanning 28 medical specialties, deriving from clinical case reports published in 10 top-tier medical journals. The benchmark is developed through a meticulous construction pipeline, involving multiple rounds of screening and review by both AI systems and human experts, with thorough checks conducted to prevent data leakage. Our study reveals that even the most advanced reasoning models, o3, o1, and DeepSeek-R1, achieve only 51.12%, 31.09%, and 17.79% accuracy, respectively. This finding highlights a significant generalization bottleneck in current large language models when faced with clinical diagnostic reasoning challenges. Through DiagnosisArena, we aim to drive further advancements in AI's diagnostic reasoning capabilities, enabling more effective solutions for real-world clinical diagnostic challenges. We provide the benchmark and evaluation tools for further research and development https://github.com/SPIRAL-MED/DiagnosisArena.

cs.CL↗

arXiv2026

MedMCP-Calc: Benchmarking LLMs for Realistic Medical Calculator Scenarios via MCP Integration

Medical calculators are fundamental to quantitative, evidence-based clinical practice. However, their real-world use is an adaptive, multi-stage process, requiring proactive EHR data acquisition, scenario-dependent calculator selection, and multi-step computation, whereas current benchmarks focus only on static single-step calculations with explicit instructions. To address these limitations, we introduce MedMCP-Calc, the first benchmark for evaluating LLMs in realistic medical calculator scenarios through Model Context Protocol (MCP) integration. MedMCP-Calc comprises 118 scenario tasks across 4 clinical domains, featuring fuzzy task descriptions mimicking natural queries, structured EHR database interaction, external reference retrieval, and process-level evaluation. Our evaluation of 23 leading models reveals critical limitations: even top performers like Claude Opus 4.5 exhibit substantial gaps, including difficulty selecting appropriate calculators for end-to-end workflows given fuzzy queries, poor performance in iterative SQL-based database interactions, and marked reluctance to leverage external tools for numerical computation. Performance also varies considerably across clinical domains. Building on these findings, we develop CalcMate, a fine-tuned model incorporating scenario planning and tool augmentation, achieving state-of-the-art performance among open-source models. Benchmark and Codes are available in https://github.com/SPIRAL-MED/MedMCP-Calc.

cs.AI↗

arXiv2026

TokenMem: Faithful Knowledge Injection for Frozen LLMs

Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge, but suffers from knowledge conflicts: when retrieved information contradicts parametric memory, the shared self-attention pathway produces unpredictable outputs. We present TokenMem, a lightweight memory system that injects knowledge into frozen LLMs through a dedicated cross-attention channel, bypassing competition with parametric memory in the residual stream. TokenMem trains only a thin gating adapter ($\sim$3-7M parameters) via a two-phase curriculum: first learning general knowledge utilization, then strengthening faithful compliance under counterfactual knowledge. In controlled experiments on five models spanning three families (Qwen3-4B/8B/14B, LLaMA-3.1-8B, OLMo-3-7B), TokenMem achieves 69-70% Knowledge Compliance (KC) on counterfactual benchmarks, compared to 20-52% for vanilla RAG, a gap of up to 49 percentage points. Ablation studies show that the two-phase curriculum is critical: removing Phase 2 collapses KC to near-zero. Mechanistic analysis reveals that the gate adapter learns a conflict-aware, layer-specific injection strategy without explicit supervision.

cs.AI↗

arXiv2026

TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents

Computer-use agents increasingly operate inside live personal workspaces, where their actions can modify files, applications, GUI state, credentials, and authenticated sessions. This creates a tension between safety and quality: agents need isolation and rollback to avoid damaging user state, but also need fast branching to support speculative execution and parallel search. Existing VMs, containers, and checkpoint/restore systems can isolate or recover workloads, but they do not provide low-latency versioning of a full interactive workspace. We present TClone, a forkable personal workspace system for computer-use agents. TClone enables a live GUI workspace to be snapshotted, forked into isolated branches, rolled back, and selectively committed or merged. Its design separates fast branch creation from durable checkpointing, using sibling containers, copy-on-write memory sharing, filesystem versioning, GUI-local execution, and asynchronous checkpointing. In our end-to-end agent-loop measurement, TClone reduces total task latency by 1.9x and 1.5x over KVM and CRIU. By making workspace versioning a first-class systems primitive, TClone supports safer and higher-quality agent execution over real personal computing environments.

cs.OS↗

arXiv2026

PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow

Graphic design is a creative and innovative process that plays a crucial role in applications such as e-commerce and advertising. However, developing an automated design system that can faithfully translate user intentions into editable design files remains an open challenge. Although recent studies have leveraged powerful text-to-image models and MLLMs to assist graphic design, they typically simplify professional workflows, resulting in limited flexibility and intuitiveness. To address these limitations, we propose PSDesigner, an automated graphic design system that emulates the creative workflow of human designers. Building upon multiple specialized components, PSDesigner collects theme-related assets based on user instructions, and autonomously infers and executes tool calls to manipulate design files, such as integrating new assets or refining inferior elements. To endow the system with strong tool-use capabilities, we construct a design dataset, CreativePSD, which contains a large amount of high-quality PSD design files annotated with operation traces across a wide range of design scenarios and artistic styles, enabling models to learn expert design procedures. Extensive experiments demonstrate that PSDesigner outperforms existing methods across diverse graphic design tasks, empowering non-specialists to conveniently create production-quality designs.

cs.CV↗

arXiv2025

Learning Semantics, Not Addresses: Runtime Neural Prefetching for Far Memory

Memory prefetching has long boosted CPU caches and is increasingly vital for far-memory systems, where large portions of memory are offloaded to cheaper, remote tiers. While effective prefetching requires accurate prediction of future accesses, prior ML approaches have been limited to simulation or small-scale hardware. We introduce FarSight, the first Linux-based far-memory system to leverage deep learning by decoupling application semantics from runtime memory layout. This separation enables offline-trained models to predict access patterns over a compact ordinal vocabulary, which are resolved at runtime through lightweight mappings. Across four data-intensive workloads, FarSight delivers up to 3.6x higher performance than the state-of-the-art.

cs.LG↗

arXiv2025

An Early Exploration of Deep-Learning-Driven Prefetching for Far Memory

Far-memory systems, where applications store less-active data in more energy-efficient memory media, are increasingly adopted by data centers. However, applications are bottlenecked by on-demand data fetching from far- to local-memory. We present Memix, a far-memory system that embodies a deep-learning-system co-design for efficient and accurate prefetching, minimizing on-demand far-memory accesses. One key observation is that memory accesses are shaped by both application semantics and runtime context, providing an opportunity to optimize each independently. Preliminary evaluation of Memix on data-intensive workloads shows that it outperforms the state-of-the-art far-memory system by up to 42%.

cs.OS↗

arXiv2024

Nl2Hltl2Plan: Scaling Up Natural Language Understanding for Multi-Robots Through Hierarchical Temporal Logic Task Representation

To enable non-experts to specify long-horizon, multi-robot collaborative tasks, language models are increasingly used to translate natural language commands into formal specifications. However, because translation can occur in multiple ways, such translations may lack accuracy or lead to inefficient multi-robot planning. Our key insight is that concise hierarchical specifications can simplify planning while remaining straightforward to derive from human instructions. We propose Nl2Hltl2Plan, a framework that translates natural language commands into hierarchical Linear Temporal Logic (LTL) and solves the corresponding planning problem. The translation involves two steps leveraging Large Language Models (LLMs). First, an LLM transforms instructions into a Hierarchical Task Tree, capturing logical and temporal relations. Next, a fine-tuned LLM converts sub-tasks into flat LTL formulas, which are aggregated into hierarchical specifications, with the lowest level corresponding to ordered robot actions. These specifications are then used with off-the-shelf planners. Our Nl2Hltl2Plan demonstrates the potential of LLMs in hierarchical reasoning for multi-robot task planning. Evaluations in simulation and real-world experiments with human participants show that Nl2Hltl2Plan outperforms existing methods, handling more complex instructions while achieving higher success rates and lower costs in task allocation and planning. Additional details are available at https://nl2hltl2plan.github.io .

cs.RO↗

arXiv2023

Optimization of probabilistic quantum search algorithm with a priori information

A quantum computer encodes information in quantum states and runs quantum algorithms to surpass the classical counterparts by exploiting quantum superposition and quantum correlation. Grover's quantum search algorithm is a typical quantum algorithm that proves the superiority of quantum computing over classical computing. It has a quadratic reduction in the query complexity of database search, and is known to be optimal when no a priori information about the elements of the database is provided. In this work, we consider a probabilistic Grover search algorithm allowing nonzero probability of failure for a database with a general a priori probability distribution of the elements, and minimize the number of oracle calls by optimizing the initial state of the quantum system and the reflection axis of the diffusion operator. The initial state and the reflection axis are allowed to not coincide, and thus the quantum search algorithm rotates the quantum system in a three-dimensional subspace spanned by the initial state, the reflection axis and the search target state in general. The number of oracle calls is minimized by a variational method, and formal results are obtained with the assumption of low failure probability. The results show that for a nonuniform a priori distribution of the database elements, the number of oracle calls can be significantly reduced given a small decrease in the success probability of the quantum search algorithm, leading to a lower average query complexity to find the solution of the search problem. The results are applied to a simple but nontrivial database model with two-value a priori probabilities to show the power of the optimized quantum search algorithm. The paper concludes with a discussion about the generalization to higher-order results that allows for a larger failure probability for the quantum search algorithm.

quant-ph↗

arXiv2022

Clio: A Hardware-Software Co-Designed Disaggregated Memory System

Memory disaggregation has attracted great attention recently because of its benefits in efficient memory utilization and ease of management. So far, memory disaggregation research has all taken one of two approaches: building/emulating memory nodes using regular servers or building them using raw memory devices with no processing power. The former incurs higher monetary cost and faces tail latency and scalability limitations, while the latter introduces performance, security, and management problems. Server-based memory nodes and memory nodes with no processing power are two extreme approaches. We seek a sweet spot in the middle by proposing a hardware-based memory disaggregation solution that has the right amount of processing power at memory nodes. Furthermore, we take a clean-slate approach by starting from the requirements of memory disaggregation and designing a memory-disaggregation-native system. We built Clio, a disaggregated memory system that virtualizes, protects, and manages disaggregated memory at hardware-based memory nodes. The Clio hardware includes a new virtual memory system, a customized network system, and a framework for computation offloading. In building Clio, we not only co-design OS functionalities, hardware architecture, and the network system, but also co-design compute nodes and memory nodes. Our FPGA prototype of Clio demonstrates that each memory node can achieve 100 Gbps throughput and an end-to-end latency of 2.5 us at median and 3.2us at the 99th percentile. Clio also scales much better and has orders of magnitude lower tail latency than RDMA. It has 1.1x to 3.4x energy saving compared to CPU-based and SmartNIC-based disaggregated memory systems and is 2.7x faster than software-based SmartNIC solutions.

cs.DC↗

arXiv2019

See the World through Network Cameras

Millions of network cameras have been deployed worldwide. Real-time data from many network cameras can offer instant views of multiple locations with applications in public safety, transportation management, urban planning, agriculture, forestry, social sciences, atmospheric information, and more. This paper describes the real-time data available from worldwide network cameras and potential applications. Second, this paper outlines the CAM2 System available to users at https://www.cam2project.net/. This information includes strategies to discover network cameras and create the camera database, user interface, and computing platforms. Third, this paper describes many opportunities provided by data from network cameras and challenges to be addressed.

cs.CV↗