相关论文: Exposing Hidden Interfaces: LLM-Guided Type Infere…

The transition from neural machine translation to agentic workflows has revolutionized Automated Program Repair (APR). However, existing agents, despite their advanced reasoning capabilities, frequently suffer from the ``Intent Gap'' -- the…

While vision-language-action (VLA) models have advanced generalist robotic learning, cross-embodiment transfer remains challenging due to kinematic heterogeneity and the high cost of collecting sufficient real-world demonstrations to…

As the complexity of System-on-Chip (SoC) designs grows, the shift-left paradigm necessitates the rapid development of high-fidelity reference models (typically written in SystemC) for early architecture exploration and verification. While…

The notable success of large language models (LLMs) has sparked an upsurge in building language agents to complete various complex tasks. We present AMOR, an agent framework based on open-source LLMs, which reasons with external knowledge…

Intent detection, a core component of natural language understanding, has considerably evolved as a crucial mechanism in safeguarding large language models (LLMs). While prior work has applied intent detection to enhance LLMs' moderation…

Recent advancements in large language models, such as GPT-4, have demonstrated remarkable capabilities in processing standard queries. Despite these advancements, their performance substantially declines in \textbf{advanced mathematical…

Agentic security systems increasingly audit live targets with tool-using LLMs, but prior systems fix a single coordination topology, leaving unclear when additional agents help and when they only add cost. We treat topology choice as an…

The emergence of multimodal large language models has redefined the agent paradigm by integrating language and vision modalities with external data sources, enabling agents to better interpret human instructions and execute increasingly…

Retrieval Augmented Generation (RAG) has emerged as an effective solution for mitigating hallucinations in Large Language Models (LLMs). The retrieval stage in RAG typically involves a pre-trained embedding model, which converts queries and…

Traditional, centralized security tools often miss adaptive, multi-vector attacks. We present the Multi-Agent LLM Cyber Defense Framework (MALCDF), a practical setup where four large language model (LLM) agents-Detection, Intelligence,…

Even when prompts and parameters are secured, transformer language models remain vulnerable because their key-value (KV) cache during inference constitutes an overlooked attack surface. This paper introduces Malicious Token Injection (MTI),…

State-of-the-art large language models (LLMs) are typically deployed as online services, requiring users to transmit detailed prompts to cloud servers. This raises significant privacy concerns. In response, we introduce ConfusionPrompt, a…

Large language models (LLMs) remain acutely vulnerable to prompt injection and related jailbreak attacks; heuristic guardrails (rules, filters, LLM judges) are routinely bypassed. We present Contextual Integrity Verification (CIV), an…

Personalized recommendation requires capturing the complex latent intents underlying user-item interactions. Existing structural models, however, often fail to preserve perspective-dependent interaction semantics and provide only indirect…

Machine learning (ML) underpins foundation models in finance, healthcare, and critical infrastructure, making them targets for data poisoning, model extraction, prompt injection, automated jailbreaking, and preference-guided black-box…

As multimodal systems increasingly process sensitive personal data, the ability to selectively revoke specific data modalities has become a critical requirement for privacy compliance and user autonomy. We present Missing-by-Design (MBD), a…

For many compiled languages, source-level types are erased very early in the compilation process. As a result, further compiler passes may convert type-safe source into type-unsafe machine code. Type-unsafe idioms in the original source and…

Recent advancements in the reasoning capabilities of large language models (LLMs) show that employing group relative policy optimization (GRPO) algorithm for reinforcement learning (RL) training allows the models to use more…

In recent years, vision-language research has shifted to study tasks which require more complex reasoning, such as interactive question answering, visual common sense reasoning, and question-answer plausibility prediction. However, the…

Constraint inference is widely considered essential to align reinforcement learning agents with safety boundaries and operational guidelines by observing expert demonstrations. However, existing approaches typically assume homogeneous…