Jie Li

The paper demonstrates that current transfer-based AML systems fail in complex DeFi environments because economic value migration can be structurally decoupled from explicit token transfers.

The paper independently stress-tests Claude Code's auto mode permission system using a deliberately ambiguous benchmark, finding that its true false negative rate is significantly higher than reported, particularly due to unmonitored file edits.

The paper proposes GeoMark, a geometry-aware localized watermarking framework that robustly protects Embedding-as-a-Service (EaaS) against model stealing and copyright infringement while preserving utility.

The paper introduces GateScope, a black-box framework that audits commercial LLM API gateways, revealing frequent discrepancies in model behavior, billing, and performance across real-world services.

The paper introduces XekRung, a frontier large language model for cybersecurity, which achieves state-of-the-art performance on domain-specific benchmarks through a comprehensive training and evaluation pipeline.

Misrouter introduces an input-only adversarial framework to exploit the routing mechanisms of Mixture-of-Experts (MoE) LLMs, enabling unsafe behavior induction against remotely hosted, black-box services.

The paper analyzes Codes of Conduct (CoCs) for online video games using a novel pipeline, finding that most multiplayer games lack CoCs despite safety needs, and that CoCs often lack specificity regarding interpersonal and underage safety harms.

The paper introduces Obsessive Experience Poisoning (OEP), a low-privilege black-box attack that poisons self-evolving LLM agents by generating locally correct but harmful experiences, causing dangerous over-generalization during reflection.

OpenURMA provides the first open, clean-room implementation of Huawei's Unified Bus (UB) protocol, demonstrating a significant reduction in latency and increase in throughput for remote memory access compared to existing RDMA standards like RoCEv2.

ADWIN introduces an adaptive window framework for on-policy distillation (OPD) that efficiently manages the supervision horizon by training on short, teacher-anchored prefixes while using delayed full-rollout probes to maintain alignment, significantly reducing training cost while preserving accuracy.

The paper addresses the challenge of multi-turn view planning for VLMs by proposing an iterative framework that uses self-exploration and view graph distillation, significantly improving planning performance over state-of-the-art models.

GaMi is a multimodal material identification system that uses mmWave and acoustic sensing with a cross-modal subtractive disentanglement framework to achieve high accuracy (95.2%) for material identification regardless of geometric variations.

WaveFilter is a novel, training-free framework that uses wavelet transforms to efficiently filter critical tokens in the KV cache, significantly improving the long-context performance of Diffusion LLMs.

The paper introduces RefMem-Bench, a new benchmark for measuring reflective memory in long-horizon dialogue, and proposes REMIND, a framework that significantly improves models' ability to synthesize fragmented cues into high-level interpretations.

LongAttnComp introduces a novel, two-stage fine-tuning framework for context compression that significantly improves long-context reasoning performance, matching or exceeding full-context accuracy on demanding tasks like code debugging.

COMAP introduces a novel co-evolutionary framework that simultaneously updates textual world models and agent policies through closed-loop interaction, significantly improving long-horizon decision-making for LLM agents.

SentGuard introduces a novel sentence-level streaming guardrail that operates in parallel with LLM generation, achieving high detection rates of unsafe content early in the response while maintaining low false-positive rates.

This study successfully demonstrates that federated learning can achieve prediction accuracy comparable to centralized modeling for multi-center sepsis prediction while fundamentally preserving patient data privacy.

The paper proposes OneReason, a framework that enhances the reasoning capability of generative recommendation models by focusing on improving item perception and structuring user behavior into coherent latent interests.

RiskFlow is a novel framework that generates realistic and safety-critical multi-agent traffic scenarios by reformulating trajectory generation as a single-pass transport problem in the action space.