Related papers: VulnLLM-R: Specialized Reasoning LLM with Agent Sc…

Equipping large language models (LLMs) with complex, interleaved reasoning and tool-use capabilities has become a key focus in agentic AI research, especially with recent advances in reasoning-oriented (``thinking'') models. Such…

Large language models (LLMs) can detect software vulnerabilities, but how do they actually identify vulnerable code? We address this question using mechanistic interpretability; analyzing the internal computations of a neural network to…

Software is prone to security vulnerabilities. Program analysis tools to detect them have limited effectiveness in practice due to their reliance on human labeled specifications. Large language models (or LLMs) have shown impressive code…

Recent advancements in LLMs indicate potential for novel applications, as evidenced by the reasoning capabilities in the latest OpenAI and DeepSeek models. To apply these models to domain-specific applications beyond text generation,…

Vision-Language-Action (VLA) models aim to unify perception, language understanding, and action generation, offering strong cross-task and cross-scene generalization with broad impact on embodied AI. However, current VLA models often lack…

This work revisits the dominant supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm for training Large Vision-Language Models (LVLMs), and reveals a key finding: SFT can significantly undermine subsequent RL by inducing…

Security vulnerabilities are increasingly prevalent in modern software and they are widely consequential to our society. Various approaches to defending against these vulnerabilities have been proposed, among which those leveraging deep…

Large Language Models (LLMs) are emerging as transformative tools for software vulnerability detection, addressing critical challenges in the security domain. Traditional methods, such as static and dynamic analysis, often falter due to…

Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length of Chain-of-Thought. These longer intermediate reasoning…

Context: Traditional software security analysis methods struggle to keep pace with the scale and complexity of modern codebases, requiring intelligent automation to detect, assess, and remediate vulnerabilities more efficiently and…

The reasoning capabilities of LLM (Large Language Model) are widely acknowledged in recent research, inspiring studies on tool learning and autonomous agents. LLM serves as the "brain" of the agent, orchestrating multiple tools for…

In this paper, we present the first comprehensive empirical study of specialized LLM-based detectors and compare them with traditional static analyzers at the project scale. Specifically, our study evaluates five latest and representative…

Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLVR) fails when correct solutions are rarely sampled even…

Multimodal Large Language Models (MLLMs) are widely used in various fields due to their powerful cross-modal comprehension and generation capabilities. However, more modalities bring more vulnerabilities to being utilized for jailbreak…

Reasoning Vision-Language Models (VLMs) have shown promising performance on complex multimodal tasks. However, they still face significant challenges: they are highly sensitive to reasoning errors, require large volumes of annotated data or…

Software vulnerability detection is critical in software security because it identifies potential bugs in software systems, enabling immediate remediation and mitigation measures to be implemented before they may be exploited. Automatic…

Large Language Models (LLMs) have become integral to automated code analysis, enabling tasks such as vulnerability detection and code comprehension. However, their integration introduces novel attack surfaces. In this paper, we identify and…

Personalization in social robotics is critical for fostering effective human-robot interactions, yet systems often face the cold start problem, where initial user preferences or characteristics are unavailable. This paper proposes a novel…

The rapidly evolving Node$.$js ecosystem currently includes millions of packages and is a critical part of modern software supply chains, making vulnerability detection of Node$.$js packages increasingly important. However, traditional…

The demand for efficient large language model (LLM) inference has propelled the development of dedicated accelerators. As accelerators are vulnerable to hardware faults due to aging, variation, etc, existing accelerator designs often…