Peking University

Lookahead-Then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars

Diffusion Large Language Models (dLLMs) have demonstrated promising capabilities and are increasingly used to produce formal languages defined by context-free grammars, such as source code and chemical expressions. However, as probabilistic models, they still struggle to generate...

SymWeb: Feedback-Driven Context Exploration and Context-Aware Symbolic Execution for Browser-Embedded WebAssembly Vulnerability Detection

Browser-deployed WebAssembly (Wasm) modules often inherit memory-safety bugs from C and C++-style code, yet exploiting, and even reaching, these bugs in the Web threat model is fundamentally context-dependent. JavaScript (JS) controls the exported-call schedule and constructs the...

AttnCompress: Dynamic Attention-Guided Trajectory Compression for Software Engineering Agents

The transition from human-centric assistance to Autonomous Software Engineering (ASE) agents has enabled the resolution of complex real-world SE tasks. However, the trial-and-error nature of these agents generates lengthy interaction trajectories, creating severe bottlenecks in t...

CLIR: Liveness-Driven and Structure-Aware Fuzzing for the Cranelift Compiler

Modern compilers are complex software systems that must correctly translate high-level programming languages into machine code across multiple architectures. Cranelift, a fast and modern compiler backend originally developed for WebAssembly and recently adopted as an experimental...

CausalRepair: Bridging the Causality Gap in Large Language Model-Based Automated Program Repair via Dual-Slicing

Automated Program Repair (APR) aims to automatically fix buggy programs. In recent years, with the rapid advancement of Large Language Models (LLMs), LLM-based APR techniques have achieved significant progress. Despite their potential, the effectiveness of LLMs relies heavily on...

Characteristics of p53 and Smad4 immunohistochemistry in pancreatic ductal adenocarcinoma and validation by next-generation sequencing.

BACKGROUND: has been extensively adopted in routine pathology practice. However, standardized IHC pattern classification schemes and rigorous validation of their predictive accuracy for underlying genomic alterations remain lacking in PDAC. METHODS: mutations was rigorously evalu...

EventSpec: Defining and Detecting Event-Semantic Issues in Blockchain Ecosystems

In recent years, smart contracts have become the backbone of decentralized applications (DApps), and off-chain systems such as bridges, wallets, and indexers rely heavily on event logs to track contract execution and state changes. However, the Ethereum Virtual Machine (EVM) does...

Efficient Grammar-Constrained Decoding via Parser Stack Classification

LLMs are widely used to generate structured output like source code or JSON. Grammar-constrained decoding (GCD) can guarantee the syntactic validity of the generated output, by masking out tokens that violate rules specified by a context-free grammar. However, the online computat...

Defusing Logic Bombs in Symbolic Execution with LLM-Generated Ghost Code

Symbolic execution is a powerful program analysis technique, but its effectiveness is fundamentally limited by solver-hostile program fragments, complex numerical reasoning, and unbounded heap structures. Recent work proposed replacing constraint solvers with large language model...

Reducing Hallucinations in LLM-Generated Code via Semantic Triangulation

Large language models (LLMs) can generate executable code from natural language descriptions, but the resulting programs frequently contain bugs due to hallucinations. In the absence of formal specifications, existing approaches attempt to assess correctness using LLM-generated p...

Contamination Means Overestimation? A Fine-Grained Empirical Study in Code Intelligence

In recent years, code intelligence has gained increasing importance in the field of automated software engineering. Meanwhile, the widespread adoption of Pretrained Language Models (PLMs) and Large Language Models (LLMs) has raised concerns regarding data contamination and its po...

Directed Evolution of a Protein Catenane Reveals How Noncanonical Topology Modulates Sequence–Property Relationships

Abstract Single-domain protein catenanes, in which two mechanically interlocked polypeptide rings fold into a compact structure, provide a tractable system for probing how chemical topology reshapes protein fitness. Using single-domain catenated dihydrofolate reductase (cat-DHFR)...

Environmental Injection Attacks against GUI Agents in Realistic Dynamic Environments

Graphical User Interface (GUI) agents are increasingly deployed to interact with online web services, yet their exposure to open-world content renders them vulnerable to Environmental Injection Attacks (EIAs). In these attacks, an attacker can inject crafted triggers into a websi...

Risk Prediction Models and Predictors of Low Anterior Resection Syndrome in Patients with Rectal Cancer: A Systematic Review and Meta-Analysis

Objectives Identifying patients at high risk of low anterior resection syndrome (LARS) after rectal cancer surgery may facilitate early management and improve postoperative quality of life. Several LARS prediction models have been developed, but their predictive performance and m...

AccLock: Unlocking Identity with Heartbeat Using In-Ear Accelerometers

The widespread use of earphones has enabled various sensing applications, including activity recognition, health monitoring, and context-aware computing. Among these, earphone-based user authentication has become a key technique by leveraging unique biometric features. However, e...

GUIA uditor : Enabling Post-hoc Child Safety Forensics via Action-Guided GUI Provenance on Mobile Devices

The proliferation of smart devices exposes children to online risks like grooming and financial scams that are deeply embedded within legitimate applications. Current approaches rely on automated prevention and detection, a paradigm that is fundamentally limited by its inherent f...

PnPSelect: Plug-and-Play IoT Device Selection Using Ultra-Wideband Signals

In recent years, the number of Internet of Things (IoT) devices in smart homes has rapidly increased. A key challenge affecting user experience is how to enable users to efficiently and intuitively select the devices they wish to control. This paper proposes PnPSelect, a plug-and...

Numerical spectrums control cohomological spectrums

Let X be a smooth irreducible projective variety over a field k with dimX=d. Let τ:Ql→C be any field embedding. Let f:X→X be a surjective endomorphism. We show that for every i=0,…,2d, the spectral radius of f∗ on the numerical group Ni(X)⊗R and on the l-adic cohomology group H2i...

Integrated metabolomic and targeted lipidomic profiling reveals systemic metabolic dysregulation in the follicular microenvironment of polycystic ovary syndrome

Polycystic ovary syndrome (PCOS) is a prevalent endocrine and metabolic disorder that significantly impacts female fertility. The follicular microenvironment, particularly follicular fluid (FF), plays a critical role in oocyte development, yet the systemic metabolic dysregulation...

Molecular Machine‐Driven Fluorogenic Probes for Motion–Signal Conversion and Hydrophilicity Retention in Live‐Cell Nanoscopy

ABSTRACT Traditional fluorogenic and cell‐permeable molecular probes for live‐cell nanoscopy mainly rely on structural or hydrophilicity changes to generate intracellular fluorescence signals. Here, we introduce molecular machines into fluorogenic probe design. As a proof of conc...