Wei Liu

Rel-Zero proposes a novel zero-watermarking technique that embeds invisible watermarks by exploiting the invariance of relational distances between image patches during AI editing, achieving superior robustness.

The paper introduces SEED, a large-scale benchmark dataset for tracing sequential deepfake facial edits, and proposes FAITH, a frequency-aware Transformer model that effectively detects and orders these cumulative editing events.

LocalAlign proposes a generalizable prompt injection defense by generating near-target adversarial examples, which enforces a tighter robustness boundary around the correct model response.

The paper introduces RAGCharacter, a forensic framework that enables black-box, character-level traceback to pinpoint the exact poisoned span in retrieved evidence responsible for a misgeneration event in Retrieval-Augmented Generation (RAG).

KVerus is a retrieval-augmented system that significantly improves the scalability and resilience of formal verification for Rust code by managing complex cross-module dependencies and adapting to code evolution.

The paper introduces FraudBench, a multimodal benchmark designed to detect AI-generated fraudulent refund evidence, finding that current AI models struggle significantly with claim-conditioned fake-damage detection.

The paper introduces a novel third-order, rotation-invariant spherical bispectrum for watermarking panoramic images, enabling reliable watermark embedding and extraction under arbitrary 3D rotations.

The paper introduces SEC-bench Pro, a rigorous benchmark for evaluating LLM-based bug hunting on complex software, finding that even advanced agents struggle with long-horizon security tasks.

The paper introduces OmniVerifier-M1, a multimodal meta-verifier that uses symbolic outputs and decoupled reinforcement learning to provide robust, fine-grained verification and error localization for large multimodal models.

UniAudio-Token is a framework that enhances existing semantic speech tokenizers with general audio perception, allowing them to handle diverse audio types while maintaining high-fidelity speech capabilities.

The paper introduces DiscourseFlip, a novel graph-guided attack that demonstrates how coordinated poisoning across a multi-topic query space can manipulate the overall opinion generated by black-box Retrieval-Augmented Generation (RAG) systems.

The paper introduces DiscourseFlip, a novel black-box, graph-guided attack that manipulates opinions across an entire multi-topic query network, demonstrating a significant leap in scope and effectiveness over existing RAG attack methods.

The paper introduces U4D, an uncertainty-aware framework that synthesizes 4D LiDAR scenes by prioritizing the reconstruction of geometrically difficult and uncertain regions first, leading to state-of-the-art fidelity and temporal consistency.

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.

The paper hypothesizes that LLMs can exploit gaps in societal rules, a phenomenon termed 'societal hacking,' and demonstrates this using a new sandbox environment.

SharedRequest introduces a model-agnostic framework that enhances LLM privacy and efficiency by batching and mixing prompts with noisy variants, achieving high utility and significant cost reduction.

This paper presents a comprehensive survey on reconfigurable antennas for next-generation mobile networks, focusing on their potential and applications.