Large Language Model (LLM) agents use memory to learn from past interactions, enabling autonomous planning and decision-making in complex environments. However, this reliance on memory introduces a critical security risk: an adversary can inject seemingly harmless records into an agent's memory to manipulate its future behavior. This vulnerability is characterized by two core aspects: First, the malicious effect of injected records is only activated within a specific context, making them hard to detect when individual memory entries are audited in isolation. Second, once triggered, the manipulation can initiate a self-reinforcing error cycle: the corrupted outcome is stored as precedent, which not only amplifies the initial error but also progressively lowers the threshold for similar attacks in the future. To address these challenges, we introduce A-MemGuard (Agent-Memory Guard), the first proactive defense framework for LLM agent memory. The core idea of our work is the insight that memory itself must become both self-checking and self-correcting. Without modifying the agent's core architecture, A-MemGuard combines two mechanisms: (1) consensus-based validation, which detects anomalies by comparing reasoning paths derived from multiple related memories and (2) a dual-memory structure, where detected failures are distilled into ``lessons'' stored separately and consulted before future actions, breaking error cycles and enabling adaptation. Comprehensive evaluations on multiple benchmarks show that A-MemGuard effectively cuts attack success rates by over 95% while incurring a minimal utility cost. This work shifts LLM memory security from static filtering to a proactive, experience-driven model where defenses strengthen over time. Our code is available in https://github.com/TangciuYueng/AMemGuard

In this case study, we select a set of controversial Romanian historical questions and ask multiple Large Language Models to answer them across languages and contexts, in order to assess their biases. Besides being a study mainly performed for educational purposes, the motivation also lies in the recognition that history is often presented through altered perspectives, primarily influenced by the culture and ideals of a state, even through large language models. Since they are often trained on certain data sets that may present certain ambiguities, the lack of neutrality is subsequently instilled in users. The research process was carried out in three stages, to confirm the idea that the type of response expected can influence, to a certain extent, the response itself; after providing an affirmative answer to some given question, an LLM could shift its way of thinking after being asked the same question again, but being told to respond with a numerical value of a scale. Results show that binary response stability is relatively high but far from perfect and varies by language. Models often flip stance across languages or between formats; numeric ratings frequently diverge from the initial binary choice, and the most consistent models are not always those judged most accurate or neutral. Our research brings to light the predisposition of models to such inconsistencies, within a specific contextualization of the language for the question asked.

Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to the self-attention's quadratic complexity with input tokens. Recently, researchers have proposed a series of methods based on block selection and compression to alleviate this problem, but they either have issues with semantic incompleteness or poor training-inference efficiency. To comprehensively address these challenges, we propose ChunkLLM, a lightweight and pluggable training framework. Specifically, we introduce two components: QK Adapter (Q-Adapter and K-Adapter) and Chunk Adapter. The former is attached to each Transformer layer, serving dual purposes of feature compression and chunk attention acquisition. The latter operates at the bottommost layer of the model, functioning to detect chunk boundaries by leveraging contextual semantic information. During the training phase, the parameters of the backbone remain frozen, with only the QK Adapter and Chunk Adapter undergoing training. Notably, we design an attention distillation method for training the QK Adapter, which enhances the recall rate of key chunks. During the inference phase, chunk selection is triggered exclusively when the current token is detected as a chunk boundary, thereby accelerating model inference. Experimental evaluations are conducted on a diverse set of long-text and short-text benchmark datasets spanning multiple tasks. ChunkLLM not only attains comparable performance on short-text benchmarks but also maintains 98.64% of the performance on long-context benchmarks while preserving a 48.58% key-value cache retention rate. Particularly, ChunkLLM attains a maximum speedup of 4.48x in comparison to the vanilla Transformer in the processing of 120K long texts.

Artificial Intelligence (AI) systems introduce unprecedented privacy challenges as they process increasingly sensitive data. Traditional privacy frameworks prove inadequate for AI technologies due to unique characteristics such as autonomous learning and black-box decision-making. This paper presents a taxonomy classifying AI privacy risks, synthesised from 45 studies identified through systematic review. We identify 19 key risks grouped under four categories: Dataset-Level, Model-Level, Infrastructure-Level, and Insider Threat Risks. Findings reveal a balanced distribution across these dimensions, with human error (9.45%) emerging as the most significant factor. This taxonomy challenges conventional security approaches that typically prioritise technical controls over human factors, highlighting gaps in holistic understanding. By bridging technical and behavioural dimensions of AI privacy, this paper contributes to advancing trustworthy AI development and provides a foundation for future research.

Abstract-- We develop an end-to-end deep learning framework for downlink beamforming in large-scale sparse multiple-input multiple-output (MIMO) channels. The core is a deep encoder-decoder network (EDN) architecture with three modules: (i) an encoder neural network (NN), deployed at each user end, that compresses estimated downlink channels into low-dimensional latent vectors. The latent vector from each user is compressed and then fed back to the BS. The training of EDN leverages two key strategies: (a) semi-amortized learning, where the beamformer decoder NN contains an analytical gradient ascent during both training and inference stages, and (b) knowledge distillation, where the loss function consists of a supervised term and an unsupervised term, and starting from supervised training with MMSE beamformers, over the epochs, the model training gradually shifts toward unsupervised using the sum-rate objective. The proposed EDN beamforming framework is extended to both far-field and near-field hybrid beamforming scenarios.

The human language system represents both linguistic forms and meanings, but the abstractness of the meaning representations remains debated. Here, we searched for abstract representations of meaning in the language cortex by modeling neural responses to sentences using representations from vision and language models. When we generate images corresponding to sentences and extract vision model embeddings, we find that aggregating across multiple generated images yields increasingly accurate predictions of language cortex responses--sometimes rivaling large language models. Similarly, averaging embeddings across multiple paraphrases of a sentence improves prediction accuracy compared to any single paraphrase. Enriching paraphrases with contextual details that may be implicit (e.g., augmenting "I had a pancake" to include details like "maple syrup") further increases prediction accuracy, even surpassing predictions based on the embedding of the original sentence, suggesting that the language system maintains richer and broader semantic representations than language models. Together, these results demonstrate the existence of highly abstract, form-independent meaning representations within the language cortex.

Abstract--This study examines the application of artificial intelligence (AI) and large language models (LLM) to improve access to legal texts in Senegal's judicial system. The emphasis is on the difficulties of extracting and organizing legal documents, highlighting the need for better access to judicial information. The research successfully extracted 7,967 articles from various legal documents, particularly focusing on the Land and Public Domain Code. A detailed graph database was developed, which contains 2,872 nodes and 10,774 relationships, aiding in the visualization of interconnections within legal texts. In addition, advanced triple extraction techniques were utilized for knowledge, demonstrating the effectiveness of models such as GPT - 4o, GPT -4, and Mistral-Large in identifying relationships and relevant metadata. Through these technologies, the aim is to create a solid framework that allows Senegalese citizens and legal professionals to more effectively understand their rights and responsibilities. Artificial intelligence (AI) is a transformative technology that raises significant ethical considerations regarding its use. Initiatives like Microsoft's "AI for Humanitarian Action" and Google's "AI for Social Good" focus on enhancing jurisprudence and human rights [1]. Moreover, the Center for Social Good Data Science at the University of Chicago applies AI to improve criminal justice systems.

While biases in large language models (LLMs), such as stereotypes and cultural tendencies in outputs, have been examined and identified, their presence and characteristics in spoken dialogue models (SDMs) with audio input and output remain largely unexplored. Paralinguistic features, such as age, gender, and accent, can affect model outputs; when compounded by multi-turn conversations, these effects may exacerbate biases, with potential implications for fairness in decision-making and recommendation tasks. In this paper, we systematically evaluate biases in speech LLMs and study the impact of multi-turn dialogues with repeated negative feedback. Bias is measured using Group Unfairness Score (GUS) for decisions and similarity-based normalized statistics rate (SNSR) for recommendations, across both open-source models like Qwen2.5-Omni and GLM-4-Voice, as well as closed-source APIs such as GPT-4o Audio and Gemini-2.5-Flash. Our analysis reveals that closed-source models generally exhibit lower bias, while open-source models are more sensitive to age and gender, and recommendation tasks tend to amplify cross-group disparities. We found that biased decisions may persist in multi-turn conversations. This work provides the first systematic study of biases in end-to-end spoken dialogue models, offering insights towards fair and reliable audio-based interactive systems. To facilitate further research, we release the FairDialogue dataset and evaluation code.

Abstract--We explore how large language models (LLMs) assess offensiveness in political discourse when prompted to adopt specific political and cultural perspectives. Using a multilingual subset of the MD-Agreement dataset centered on tweets from the 2020 US elections, we evaluate several recent LLMs - including DeepSeek-R1, o4-mini, GPT -4.1-mini, Qwen3, Gemma, and Mistral - tasked with judging tweets as offensive or non-offensive from the viewpoints of varied political personas (far-right, conservative, centrist, progressive) across English, Polish, and Russian contexts. Our results show that larger models with explicit reasoning abilities (e.g., DeepSeek-R1, o4-mini) are more consistent and sensitive to ideological and cultural variation, while smaller models often fail to capture subtle distinctions. We find that reasoning capabilities significantly improve both the personalization and interpretability of offensiveness judgments, suggesting that such mechanisms are key to adapting LLMs for nuanced sociopolitical text classification across languages and ideologies. Detecting offensive language is vital for fostering respectful discourse, particularly on social media. Y et, offensiveness is inherently subjective - shaped by individual ideologies, cultural backgrounds, and values [1], [2]. Supervised models rely on ground-truth labels that reflect annotators' biases, complicating efforts to build fair and robust systems [3]. Political discourse, marked by polarization, offers a compelling lens: individuals often tolerate combative language from their own side while labeling opposing views as offensive [4]. Recent advances in large language models (LLMs) - from GPT -based to instruction-tuned variants - have improved context-sensitive understanding [5]-[8].

Network intrusion detection, a well-explored cybersecurity field, has predominantly relied on supervised learning algorithms in the past two decades. However, their limitations in detecting only known anomalies prompt the exploration of alternative approaches. Motivated by the success of self-supervised learning in computer vision, there is a rising interest in adapting this paradigm for network intrusion detection. While prior research mainly delved into contrastive self-supervised methods, the efficacy of non-contrastive methods, in conjunction with encoder architectures serving as the representation learning backbone and augmentation strategies that determine what is learned, remains unclear for effective attack detection. This paper compares the performance of five non-contrastive self-supervised learning methods using three encoder architectures and six augmentation strategies. Ninety experiments are systematically conducted on two network intrusion detection datasets, UNSW-NB15 and 5G-NIDD. For each self-supervised model, the combination of encoder architecture and augmentation method yielding the highest average precision, recall, F1-score, and AUCROC is reported.