相关论文: Learning to Identify Conflicts in RPKI

Safety alignment in Large Language Models (LLMs) often involves mediating internal representations to refuse harmful requests. Recent research has demonstrated that these safety mechanisms can be bypassed by ablating or removing specific…

Unmanned Aerial Vehicles (UAVs) are suited as cost-effective and adaptable platforms for carrying Wi-Fi Access Points (APs) and cellular Base Stations (BSs). Implementing aerial networks in disaster management scenarios and crowded areas…

A core problem in the development and maintenance of crowd-sourced filter lists is that their maintainers cannot confidently predict whether (and where) a new filter list rule will break websites. This is a result of enormity of the Web,…

Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. Within these frameworks, the policy update relies on…

A major drawback of reasoning models is their excessive token usage, inflating computational cost, resource demand, and latency. We show this verbosity stems not from deeper reasoning but from reinforcement learning loss minimization when…

Modern distributed systems are supported by fault-tolerant algorithms, like Reliable Broadcast and Consensus, that assure the correct operation of the system even when some of the nodes of the system fail. However, the development of…

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced LLM reasoning, but remains constrained by inefficient exploration under limited rollout budgets, leading to low sampling success and unstable training in complex tasks. We…

Large language models (LLMs) often struggle with knowledge-intensive tasks due to a lack of background knowledge and a tendency to hallucinate. To address these limitations, integrating knowledge graphs (KGs) with LLMs has been intensively…

Safety-critical robot systems need thorough testing to expose design flaws and software bugs which could endanger humans. Testing in simulation is becoming increasingly popular, as it can be applied early in the development process and does…

Safety guarantees are a prerequisite to the deployment of reinforcement learning (RL) agents in safety-critical tasks. Often, deployment environments exhibit non-stationary dynamics or are subject to changing performance goals, requiring…

The democratization of open-source Large Language Models (LLMs) allows users to fine-tune and deploy models on local infrastructure but exposes them to a First Mile deployment landscape. Unlike black-box API consumption, the reliability of…

Reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) are important techniques to align large language models (LLM) with human preference. However, the quality of RLHF and DPO training is seriously…

Vision-and-Language Navigation (VLN) aims to navigate to the target location by following a given instruction. Unlike existing methods focused on predicting a more accurate action at each step in navigation, in this paper, we make the first…

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularly in the domain of complex reasoning tasks. However,…

Darknet technology such as Tor has been used by various threat actors for organising illegal activities and data exfiltration. As such, there is a case for organisations to block such traffic, or to try and identify when it is used and for…

Open-source licenses establish the legal foundation for software reuse, yet license variants, including both modified standard licenses and custom-created alternatives, introduce significant compliance complexities. Despite their prevalence…

Training against white-box deception detectors has been proposed as a way to make AI systems honest. However, such training risks models learning to obfuscate their deception to evade the detector. Prior work has studied obfuscation only in…

Malware spread among websites and between websites and clients is an increasing problem. Search engines play an important role in directing users to websites and are a natural control point for intervening, using mechanisms such as…

The successful deployment of safe and trustworthy Connected and Autonomous Vehicles (CAVs) will highly depend on the ability to devise robust and effective security solutions to resist sophisticated cyber attacks and patch up critical…

Reinforcement Learning from Human Feedback (RLHF) has advanced alignment capabilities significantly but remains hindered by two core challenges: \textbf{reward hacking} and \textbf{stable optimization}. Current solutions independently…