Related papers: From Theory to Protocol: Executable Frameworks for…
With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable…
We formulate a model for intermittent communication that can capture bursty transmissions or a sporadically available channel, where in either case the receiver does not know a priori when the transmissions will occur. Focusing on the…
Recently, the cross-modal pre-training task has been a hotspot because of its wide application in various down-streaming researches including retrieval, captioning, question answering and so on. However, exiting methods adopt a one-stream…
Generative AI is rapidly moving from research to deployment, elevating the need for responsible development, evaluation, and governance. We conduct a PRISMA guided review of 232 studies (November 2022 - December 2025), spanning large…
Learning is a complex dynamical process shaped by a range of interconnected decisions. Careful design of hyperparameter schedules for artificial neural networks or efficient allocation of cognitive resources by biological learners can…
Generating intermediate steps, or Chain of Thought (CoT), is an effective way to significantly improve language models' (LM) multi-step reasoning capability. However, the CoT lengths can grow rapidly with the problem complexity, easily…
Ultra-reliable and low-latency communications (URLLC) are considered as one of three new application scenarios in the fifth generation cellular networks. In this work, we aim to reduce the user experienced delay through prediction and…
AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for…
We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs. While less capable than humans in many real-world scenarios, GPT-4 exhibits human-level performance on…
Provably correct distributed protocols, which are a critical component of modern distributed systems, are highly challenging to design and have often required decades of human effort. These protocols allow multiple agents to coordinate to…
Self-stabilization is a general paradigm to provide forward recovery capabilities to distributed systems and networks. Intuitively, a protocol is self-stabilizing if it is able to recover without external intervention from any catastrophic…
Emergent communication has made strides towards learning communication from scratch, but has focused primarily on protocols that resemble human language. In nature, multi-agent cooperation gives rise to a wide range of communication that…
As the complexity and destructiveness of Advanced Persistent Threat (APT) increase, there is a growing tendency to identify a series of actions undertaken to achieve the attacker's target, called attack investigation. Currently, analysts…
The remarkable capabilities of modern large reasoning models are largely unlocked through post-training techniques such as supervised fine-tuning (SFT) and reinforcement learning (RL). However, the architectural mechanisms behind such…
Reinforcement learning has shown promising results in learning neural network policies for complicated control tasks. However, the lack of formal guarantees about the behavior of such policies remains an impediment to their deployment. We…
Latent Chain-of-Thought (Latent CoT) models promise efficient reasoning via continuous representations, yet exhibit puzzling performance inconsistencies: excelling at exploration (ProsQA: 97.0%) but failing at computation (GSM8K: 34.1%). We…
In the last years, Deep Learning technology has been proposed in different fields, bringing many advances in each of them, but identifying new threats in these solutions regarding cybersecurity. Those implemented models have brought several…
Chain-of-Thought (CoT) prompting has been used to enhance the reasoning capability of LLMs. However, its reliability in security-sensitive analytical tasks remains insufficiently examined, particularly under structured human evaluation.…
Collaborative perception significantly enhances autonomous driving safety by extending each vehicle's perception range through message sharing among connected and autonomous vehicles. Unfortunately, it is also vulnerable to adversarial…
Decoding strategies play a central role in shaping the reasoning ability of large language models (LLMs). Traditional methods such as greedy decoding and beam search often suffer from error propagation, while sampling-based approaches…