arXiv subjects

Yimin Liu

Publications and source records attributed to Yimin Liu.

At least 19 recordsLinked to original sources

arXiv2026

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conventions, and specialized correctness criteria make this knowledge difficult to convert into reliable learning experience-a challenge we call the scientific experience bottleneck. We introduce ScienceIDE, infrastructure for turning the world's scientific code into programmable environments for scientific agents. Guided by expert-defined scientific cases and acceptance criteria, agents transform repositories into executable environments that support task generation, execution, and scientific verification. These environments provide a shared foundation for supervised fine-tuning, reinforcement learning, and evaluation. Using verified interaction trajectories, we train PhAI-IDE-72B, PhAI-IDE-9B, and PhAI-IDE-4B. The model family shows gains in held-out scientific-code repair and across selected general-purpose benchmarks in code, reasoning, and knowledge, providing evidence of positive transfer from scientific experience to broader capabilities. ScienceIDE lays the foundation for an integrated workspace for agent learning and scientific practice, making humanity's scientific software a shared substrate for developing scientific intelligence. Code: https://github.com/aitofound/ScienceIDE

cs.CL↗

arXiv2026

Extended Proofs for Encrypted Sensing in Bistatic Radar: Unified Analysis and Randomly Activated Arrays

This supplementary material provides the complete mathematical development for the signal-to-noise ratio loss (SNRL) analysis of pulse-wise spatially randomized encrypted sensing. We first derive a reduced model in which the transmit-side randomization is represented by an independent and identically distributed complex spatial coefficient. Based on this model, we establish the almost-sure and mean asymptotic SNRL, derive the leading bias and variance for a finite coherent processing interval (CPI), and obtain closed-form coefficient moments and asymptotic SNRL for independent Bernoulli element activation. These results complement the concise statements and proof sketches in the associated paper.

eess.SP↗

arXiv2026

BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure

LM-agent benchmarks increasingly function as interactive evaluation infrastructure. Agents observe state, call tools, modify workspaces, submit artifacts, and receive rewards from outcome procedures. This interactivity makes evaluations vulnerable to reward hacking: an agent improves its measured score by exploiting the reward-relevant trajectory instead of solving the intended task. Existing defenses rely largely on task-specific patches, prompt instructions, or post-hoc detectors. They do not provide reusable evidence that a concrete run remained within its intended evaluation boundary. This paper presents BenchShield, a model-backed instrumentation layer for reward integrity in LLM-agent evaluation. BenchShield grounds detection in a finite lifecycle model of an evaluation's reward-relevant events. Within the benchmark infrastructure, two complementary analyses operate over this model. A static, phase-aware taint analysis exposes reward-hacking paths before a run. Its runtime counterpart uses infrastructure-side evidence to attribute concrete agent use and emit evidence-backed claims. We construct BenchShield Trajectories, a human-labeled corpus of 456 adjudicated trajectories from more than 31,000 public agent runs across three benchmarks. Compared with an agentic hackability scanner baseline on the same tasks and model, BenchShield improves full-chain recall from 23-94% to 77-100%, same-vector coverage from 16-56% to 43-78%, and reduces per-task cost by up to 65%. Its runtime analysis achieves 96% accuracy in detecting reward hacking from infrastructure-side evidence.

cs.CR↗

arXiv2026

What Keeps Agent Skills from Being Reusable? Evidence from 138K SKILL.md Files

Under the current standard, Agent Skills are SKILL.md files that combine instructions with supporting resources, enabling Large Language Model (LLM) agents to reuse procedures beyond a single conversation. Yet many public skills appear to originate from a single task, repository, or conversation, even when they are shared as reusable components. We analyze this gap across 138,133 public SKILL.md files from 20,556 repositories using a two-tier defect taxonomy grounded in the official specification and best-practice guidance. We find that 91.8% of skills contain at least one detected defect, with stable estimates across lenient and strict thresholds (88.8-94.6%). The dominant failures are ordinary packaging problems rather than exotic attacks: weak routing metadata, bloated or non-actionable bodies, and poor resource organization. A deterministic routing stress test over 20,000 skills shows the functional impact: skills with valid routing metadata are retrieved more reliably from startup descriptions than skills with routing defects. Defect rates vary by platform and provenance: specification-aware skills contain fewer defects, while AI-marked skills show more safety and portability problems. Lightweight enforcement and repair experiments support a quality-assured generation workflow combining spec-aware prompting, lightweight linting, automated repair, and safety gating.

cs.AI↗

arXiv2026

SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills

Agent Skills---structured packages of instructions and scripts that augment LLM-based agents---are rapidly proliferating, yet their security properties remain under-explored. We present \textsc{SkillsMetric}, a five-stage static analysis framework that scores skill packages along pattern density, statistical anomaly, dataflow taint, import anomaly, and capability mismatch dimensions. We construct an adversarial evaluation dataset of 2{,}266 skills spanning 16~attack types across code-level, system-level, and semantic-level threats, and evaluate on the full SkillMD-138K corpus. Our framework achieves an AUC of 0.93 and 5-fold cross-validated F1 of 73.4\%$\pm$0.5\%, with strong detection of data exfiltration (93\%) and steganographic payloads (93\%). Crucially, we identify fundamental blind spots: \emph{host destruction} attacks using common shell commands evade all five stages (0\% detection), and \emph{prompt injection} via natural-language manipulation achieves only 42\% detection. These findings establish that static analysis alone is insufficient for skill security, motivating defense-in-depth architectures that combine fast static pre-screening with semantic review.

cs.CR↗

arXiv2026

Corner Reflector Array Jamming Discrimination Using Multi-Dimensional Micro-Motion Features with Frequency Agile Radar

This paper introduces a robust discrimination method for distinguishing real ship targets from corner-reflector-array jamming with frequency-agile radar. The key idea is to exploit the multidimensional micro-motion signatures that separate rigid ships from non-rigid decoys. From Range-Velocity maps we derive two new hand-crafted descriptors-mean weighted residual (MWR) and complementary contrast factor (CCF) and fuse them with deep features learned by a lightweight CNN. An XGBoost classifier then gives the final decision. Extensive simulations show that the hybrid feature set consistently outperforms state-of-the-art alternatives, confirming the superiority of the proposed approach.

cs.LG↗

arXiv2026

Xray-Visual Models: Scaling Vision models on Industry Scale Data

We present Xray-Visual, a unified vision model architecture for large-scale image and video understanding trained on industry-scale social media data. Our model leverages over 15 billion curated image-text pairs and 10 billion video-hashtag pairs from Facebook and Instagram, employing robust data curation pipelines that incorporate balancing and noise suppression strategies to maximize semantic diversity while minimizing label noise. We introduce a three-stage training pipeline that combines self-supervised MAE, semi-supervised hashtag classification, and CLIP-style contrastive learning to jointly optimize image and video modalities. Our architecture builds on a Vision Transformer backbone enhanced with efficient token reorganization (EViT) for improved computational efficiency. Extensive experiments demonstrate that Xray-Visual achieves state-of-the-art performance across diverse benchmarks, including ImageNet for image classification, Kinetics and HMDB51 for video understanding, and MSCOCO for cross-modal retrieval. The model exhibits strong robustness to domain shift and adversarial perturbations. We further demonstrate that integrating large language models as text encoders (LLM2CLIP) significantly enhances retrieval performance and generalization capabilities, particularly in real-world environments. Xray-Visual establishes new benchmarks for scalable, multimodal vision models, while maintaining superior accuracy and computational efficiency.

cs.CV↗

arXiv2026

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focused Skills with at most three modules outperform larger or exhaustive bundles, and smaller models with Skills can match larger models without them. SkillsBench establishes paired evaluation as the foundation for rigorous measurement of Skill efficacy on agentic, expertise-heavy work.

cs.AI↗

arXiv2026

ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces

Large language model (LLM) agents are increasingly deployed to automate productivity tasks (e.g., email, scheduling, document management), but evaluating them on live services is risky due to potentially irreversible changes. Existing benchmarks rely on simplified environments and fail to capture realistic, stateful, multi-service workflows. We introduce ClawsBench, a benchmark for evaluating and improving LLM agents in realistic productivity settings. It includes five high-fidelity mock services (Gmail, Slack, Google Calendar, Google Docs, Google Drive) with full state management and deterministic snapshot/restore, along with 44 structured tasks covering single-service, cross-service, and safety-critical scenarios. We decompose agent scaffolding into two independent levers (domain skills that inject API knowledge via progressive disclosure, and a meta prompt that coordinates behavior across services) and vary both to measure their separate and combined effects. Experiments across 6 models, 4 agent harnesses, and 33 conditions show that with full scaffolding, agents achieve task success rates of 39-64% but exhibit unsafe action rates of 7-33%. On OpenClaw, the top five models fall within a 10 percentage-point band on task success (53-63%), with unsafe action rates from 7% to 23% and no consistent ordering between the two metrics. We identify eight recurring patterns of unsafe behavior, including multi-step sandbox escalation and silent contract modification. We release the trajectories and future dataset at https://clawsbench.com.

cs.AI↗

arXiv2025

Robust HRRP Recognition under Interrupted Sampling Repeater Jamming using a Prior Jamming Information-Guided Network

Radar automatic target recognition (RATR) based on high-resolution range profile (HRRP) has attracted increasing attention due to its ability to capture fine-grained structural features. However, recognizing targets under electronic countermeasures (ECM), especially the mainstream interrupted-sampling repeater jamming (ISRJ), remains a significant challenge, as HRRPs often suffer from serious feature distortion. To address this, we propose a robust HRRP recognition method guided by prior jamming information. Specifically, we introduce a point spread function (PSF) as prior information to model the HRRP distortion induced by ISRJ. Based on this, we design a recognition network that leverages this prior through a prior-guided feature interaction module and a hybrid loss function to enhance the model's discriminative capability. With the aid of prior information, the model can learn invariant features within distorted HRRP under different jamming parameters. Both the simulated and measured-data experiments demonstrate that our method consistently outperforms state-of-the-art approaches and exhibits stronger generalization capabilities when facing unseen jamming parameters.

eess.SP↗

arXiv2025

A set of nearly good real numbers to specify the ground states associated with a Hamiltonian containing non-commutable terms and the effect of the odd-channel of a pair of different bosons emerging in multi-species systems

A distinguishing feature of multi-species boson systems is the appearance of the odd channel, in which the spins of two different bosons are coupled to an odd integer. Through exact numerical solutions of the Schrodinger equation for a medium-body cold system containing two kinds of spin-1 atoms, the effect of the odd channel on the ground state (GS) has been studied. It was found that the odd-channel causes two types of fluctuation (a mixing of various components). (i) coherent mixing, where all the components have the same sign. In this way, the probability of an odd-pair emerging in the spin-state would be smaller; thus, this way would be adopted by the GS when the odd channel is repulsive. (ii) cyclic mixing, where half selected components have the + sign while the other half have the - sign. In this way, the probability of an odd-pair is larger; thus, this way would be adopted by the GS when the odd channel is attractive. It was further found that the terms in the Hamiltonian are no longer all commutable. Accordingly, the spin of a single species S_X (X=A, B) is no longer conserved. However, its average \overline{S_X} is well defined. It turns out that S_X and \overline{S_X} vary with the strengths in a similar way. The former jumps step-by-step from a good quantum number (an even integer) to the next good quantum number, the latter jumps also in a step-by-step way, but from a "real number" to another well-separated "real number". Exactly speaking, each of these real numbers is not exactly a number but an interval with a very narrow width at the real axis. Thus, the GS can be specified by these real numbers. It was found that, when the strengths of the two intraspecies interactions are not remarkably different, and/or the particle numbers are larger, the widths of the intervals are narrower, the above picture holds more nicely, and the GS can be well-specified by these real numbers.

cond-mat.other↗

arXiv2025

Robust Radar HRRP Recognition under Non-uniform Jamming Based on Complex-valued Frequency Attention Network

Complex electromagnetic environments, often containing multiple jammers with different jamming patterns, produce non-uniform jamming power across the frequency spectrum. This spectral non-uniformity directly induces severe distortion in the target's HRRP, consequently compromising the performance and reliability of conventional HRRP-based target recognition methods. This paper proposes a novel, end-to-end trained network for robust radar target recognition. The core of our model is a CFA module that operates directly on the complex spectrum of the received echo. The CFA module learns to generate an adaptive frequency-domain filter, assigning lower weights to bands corrupted by strong jamming while preserving critical target information in cleaner bands. The filtered spectrum is then fed into a classifier backbone for recognition. Experimental results on simulated HRRP data with various jamming combinations demonstrate our method's superiority. Notably, under severe jamming conditions, our model achieves a recognition accuracy nearly 9% higher than traditional model-based approaches, all while introducing negligible computational overhead. This highlights its exceptional performance and robustness in challenging jamming environments.

eess.SP↗

arXiv2025

DeepDR: an integrated deep-learning model web server for drug repositioning

Background: Identifying new indications for approved drugs is a complex and time-consuming process that requires extensive knowledge of pharmacology, clinical data, and advanced computational methods. Recently, deep learning (DL) methods have shown their capability for the accurate prediction of drug repositioning. However, implementing DL-based modeling requires in-depth domain knowledge and proficient programming skills. Results: In this application, we introduce DeepDR, the first integrated platform that combines a variety of established DL-based models for disease- and target-specific drug repositioning tasks. DeepDR leverages invaluable experience to recommend candidate drugs, which covers more than 15 networks and a comprehensive knowledge graph that includes 5.9 million edges across 107 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from six existing databases and a large scientific corpus of 24 million PubMed publications. Additionally, the recommended results include detailed descriptions of the recommended drugs and visualize key patterns with interpretability through a knowledge graph. Conclusion: DeepDR is free and open to all users without the requirement of registration. We believe it can provide an easy-to-use, systematic, highly accurate, and computationally automated platform for both experimental and computational scientists.

cs.LG↗

arXiv2025

Advancing Image Super-resolution Techniques in Remote Sensing: A Comprehensive Survey

Remote sensing image super-resolution (RSISR) is a crucial task in remote sensing image processing, aiming to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts. Despite the growing number of RSISR methods proposed in recent years, a systematic and comprehensive review of these methods is still lacking. This paper presents a thorough review of RSISR algorithms, covering methodologies, datasets, and evaluation metrics. We provide an in-depth analysis of RSISR methods, categorizing them into supervised, unsupervised, and quality evaluation approaches, to help researchers understand current trends and challenges. Our review also discusses the strengths, limitations, and inherent challenges of these techniques. Notably, our analysis reveals significant limitations in existing methods, particularly in preserving fine-grained textures and geometric structures under large-scale degradation. Based on these findings, we outline future research directions, highlighting the need for domain-specific architectures and robust evaluation protocols to bridge the gap between synthetic and real-world RSISR scenarios.

eess.IV↗

arXiv2025

Recovering Partially Corrupted Objects via Sketch-Guided Bidirectional Feature Interaction

Text-guided diffusion models have achieved remarkable success in object inpainting by providing high-level semantic guidance through text prompts. However, they often lack precise pixel-level spatial control, especially in scenarios involving partially corrupted objects where critical uncorrupted cues remain. To overcome this limitation, sketch-guided methods have been introduced, using either indirect gradient modulation or direct sketch injection to improve structural control. Yet, existing approaches typically establish a one-way mapping from the sketch to the masked regions only, neglecting the contextual information from unmasked object areas. This leads to a disconnection between the sketch and the uncorrupted content, thereby causing sketch-guided inconsistency and structural mismatch. To tackle this challenge, we propose a sketch-guided bidirectional feature interaction framework built upon a pretrained Stable Diffusion model. Our bidirectional interaction features two complementary directions, context-to-sketch and sketch-to-inpainting, that enable fine-grained spatial control for partially corrupted object inpainting. In the context-to-sketch direction, multi-scale latents from uncorrupted object regions are propagated to the sketch branch to generate a visual mask that adapts the sketch features to the visible context and denoising progress. In the sketch-to-inpainting direction, a sketch-conditional affine transformation modulates the influence of sketch guidance based on the learned visual mask, ensuring consistency with uncorrupted object content. This interaction is applied at multiple scales within the encoder of the diffusion U-Net, enabling the model to restore object structures with enhanced spatial fidelity. Extensive experiments on two newly constructed benchmark datasets demonstrate that our approach outperforms state-of-the-art methods.

cs.CV↗

arXiv2025

Stochastic Optimization of Inventory at Large-scale Supply Chains

Today's global supply chains face growing challenges due to rapidly changing market conditions, increased network complexity and inter-dependency, and dynamic uncertainties in supply, demand, and other factors. To combat these challenges, organizations employ Material Requirements Planning (MRP) software solutions to set inventory stock buffers - for raw materials, work-in-process goods, and finished products - to help them meet customer service levels. However, holding excess inventory further complicates operations and can lock up millions of dollars of capital that could be otherwise deployed. Furthermore, most commercially available MRP solutions fall short in considering uncertainties and do not result in optimal solutions for modern enterprises. At C3 AI, we fundamentally reformulate the inventory management problem as a constrained stochastic optimization. We then propose a simulation-optimization framework that minimizes inventory and related costs while maintaining desired service levels. The framework's goal is to find the optimal reorder parameters that minimize costs subject to a pre-defined service-level constraint and all other real-world operational constraints. These optimal reorder parameters can be fed back into an MRP system to drive optimal order placement, or used to place optimal orders directly. This approach has proven successful in reducing inventory levels by 10-35 percent, resulting in hundreds of millions of dollars of economic benefit for major enterprises at a global scale.

math.OC↗

arXiv2025

Rotational Flow Dominates Abrupt Seasonal Change in Zonally Asymmetric Tropical Meridional Circulation

The seasonality of the tropical meridional circulation evolves differently across different regions, governs the onset and retreat of monsoons and migration of tropical precipitation, thereby influencing agricultural productivity and disaster preparedness in the tropics and subtropics. By defining a pseudo meridional overturning streamfunction (Ψpseudo) and defining a new vector-type, dual-component index (ASCI), we diagnose zonally asymmetric abrupt seasonal change (ASC) of tropical meridional circulation. Ψpseudo converges to traditional, meridional overturning streamfunction (Ψm) after being averaged over a zonal circle around any latitude. By applying the Helmholtz decomposition to horizontal velocity fields so as to decompose Ψpseudo into rotational and divergent components, we quantitatively compare the contributions of horizontally rotational and divergent flows to the abrupt seasonal change. We find that the zonal sectors associated with strong deep convection exhibit the most pronounced ASC of tropical meridional circulation, and all of subregions exhibiting ASC contain landmass with low heat inertia. Particularly, in contrast to the case of zonally symmetric Hadley cell, rotational flow, rather than the thermal-direct divergent flow, dominates the zonally asymmetric ASC in the tropics, although the divergent flow also contributes to the ASC over the zonal sectors associated with deep convection. We suggest that the interplay between tropical Rossby-type eddies with extratropical eddies and tropical circulation is essential to the zonally asymmetric ASC of tropical Hadley circulation.

physics.ao-ph↗

arXiv2024

A MARL Based Multi-Target Tracking Algorithm Under Jamming Against Radar

Unmanned aerial vehicles (UAVs) have played an increasingly important role in military operations and social life. Among all application scenarios, multi-target tracking tasks accomplished by UAV swarms have received extensive attention. However, when UAVs use radar to track targets, the tracking performance can be severely compromised by jammers. To track targets in the presence of jammers, UAVs can use passive radar to position the jammer. This paper proposes a system where a UAV swarm selects the radar's active or passive work mode to track multiple differently located and potentially jammer-carrying targets. After presenting the optimization problem and proving its solving difficulty, we use a multi-agent reinforcement learning algorithm to solve this control problem. We also propose a mechanism based on simulated annealing algorithm to avoid cases where UAV actions violate constraints. Simulation experiments demonstrate the effectiveness of the proposed algorithm.

eess.SY↗