Large Language Models (LLMs) demonstrate strong reasoning and task planning capabilities but remain fundamentally limited in physical interaction modeling. Existing approaches integrate perception via Vision-Language Models (VLMs) or adaptive decision-making through Reinforcement Learning (RL), but they fail to capture dynamic object interactions or require task-specific training, limiting their real-world applicability. We introduce APEX (Anticipatory Physics-Enhanced Execution), a framework that equips LLMs with physics-driven foresight for real-time task planning. APEX constructs structured graphs to identify and model the most relevant dynamic interactions in the environment, providing LLMs with explicit physical state updates. Simultaneously, APEX provides low-latency forward simulations of physically feasible actions, allowing LLMs to select optimal strategies based on predictive outcomes rather than static observations. We evaluate APEX on three benchmarks designed to assess perception, prediction, and decision-making: (1) Physics Reasoning Benchmark, testing causal inference and object motion prediction; (2) Tetris, evaluating whether physics-informed prediction enhances decision-making performance in long-horizon planning tasks; (3) Dynamic Obstacle Avoidance, assessing the immediate integration of perception and action feasibility analysis. APEX significantly outperforms standard LLMs and VLM-based models, demonstrating the necessity of explicit physics reasoning for bridging the gap between language-based intelligence and real-world task execution. The source code and experiment setup are publicly available at https://github.com/hwj20/APEX_EXP .

Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech. The richer speech signal introduces new security risks compared to text-based models, as adversaries can better bypass safety mechanisms by injecting imperceptible noise to speech. We analyze adversarial attacks and find that SLMs are substantially more vulnerable to jailbreak attacks, which can achieve a perfect 100% attack success rate in some instances. To improve security, we propose post-hoc patching defenses used to intervene during inference by modifying the SLM's activations that improve robustness up to 99% with (i) negligible impact on utility and (ii) without any re-training. We conduct ablation studies to maximize the efficacy of our defenses and improve the utility/security trade-off, validated with large-scale benchmarks unique to SLMs.

As the adoption of Generative AI in real-world services grow explosively, energy has emerged as a critical bottleneck resource. However, energy remains a metric that is often overlooked, under-explored, or poorly understood in the context of building ML systems. We present the ML$.$ENERGY Benchmark, a benchmark suite and tool for measuring inference energy consumption under realistic service environments, and the corresponding ML$.$ENERGY Leaderboard, which have served as a valuable resource for those hoping to understand and optimize the energy consumption of their generative AI services. In this paper, we explain four key design principles for benchmarking ML energy we have acquired over time, and then describe how they are implemented in the ML$.$ENERGY Benchmark. We then highlight results from the early 2025 iteration of the benchmark, including energy measurements of 40 widely used model architectures across 6 different tasks, case studies of how ML design choices impact energy consumption, and how automated optimization recommendations can lead to significant (sometimes more than 40%) energy savings without changing what is being computed by the model. The ML$.$ENERGY Benchmark is open-source and can be easily extended to various customized models and application scenarios.

Abstract--Artificial Intelligence (AI) is expected to be an integral part of next-generation AI-native 6G networks. With the prevalence of AI, researchers have identified numerous use cases of AI in network security. However, there are very few studies that analyze the suitability of Large Language Models (LLMs) in network security. T o fill this gap, we examine the suitability of LLMs in network security, particularly with the case study of STRIDE threat modeling. We utilize four prompting techniques with five LLMs to perform STRIDE classification of 5G threats. From our evaluation results, we point out key findings and detailed insights along with the explanation of the possible underlying factors influencing the behavior of LLMs in the modeling of certain threats. The numerical results and the insights support the necessity for adjusting and fine-tuning LLMs for network security use cases. Future networks, such as Sixth Generation (6G) networks, are envisioned to integrate Artificial Intelligence (AI) into their networks to be AI-Native networks [1] to improve performance, efficiency, and scalability [2].

Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rewards. Recent RLVR works that operate under the zero setting avoid supervision in labeling the reasoning process, but still depend on manually curated collections of questions and answers for training. The scarcity of high-quality, human-produced examples raises concerns about the long-term scalability of relying on human supervision, a challenge already evident in the domain of language model pretraining. Furthermore, in a hypothetical future where AI surpasses human intelligence, tasks provided by humans may offer limited learning potential for a superintelligent system. To address these concerns, we propose a new RLVR paradigm called Absolute Zero, in which a single model learns to propose tasks that maximize its own learning progress and improves reasoning by solving them, without relying on any external data. Under this paradigm, we introduce the Absolute Zero Reasoner (AZR), a system that self-evolves its training curriculum and reasoning ability by using a code executor to both validate proposed code reasoning tasks and verify answers, serving as an unified source of verifiable reward to guide open-ended yet grounded learning. Despite being trained entirely without external data, AZR achieves overall SOTA performance on coding and mathematical reasoning tasks, outperforming existing zero-setting models that rely on tens of thousands of in-domain human-curated examples. Furthermore, we demonstrate that AZR can be effectively applied across different model scales and is compatible with various model classes.

This study investigates whether individuals can learn to accurately discriminate between human-written and AI-produced texts when provided with immediate feedback, and if they can use this feedback to recalibrate their self-perceived competence. We also explore the specific criteria individuals rely upon when making these decisions, focusing on textual style and perceived readability. We used GPT-4o to generate several hundred texts across various genres and text types comparable to Koditex, a multi-register corpus of human-written texts. We then presented randomized text pairs to 254 Czech native speakers who identified which text was human-written and which was AI-generated. Participants were randomly assigned to two conditions: one receiving immediate feedback after each trial, the other receiving no feedback until experiment completion. We recorded accuracy in identification, confidence levels, response times, and judgments about text readability along with demographic data and participants' engagement with AI technologies prior to the experiment. Participants receiving immediate feedback showed significant improvement in accuracy and confidence calibration. Participants initially held incorrect assumptions about AI-generated text features, including expectations about stylistic rigidity and readability. Notably, without feedback, participants made the most errors precisely when feeling most confident -- an issue largely resolved among the feedback group. The ability to differentiate between human and AI-generated texts can be effectively learned through targeted training with explicit feedback, which helps correct misconceptions about AI stylistic features and readability, as well as potential other variables that were not explored, while facilitating more accurate self-assessment. This finding might be particularly important in educational contexts.

Lay summaries for scientific documents typically include explanations to help readers grasp sophisticated concepts or arguments. However, current automatic summarization methods do not explicitly model explanations, which makes it difficult to align the proportion of explanatory content with human-written summaries. In this paper, we present a plan-based approach that leverages discourse frameworks to organize summary generation and guide explanatory sentences by prompting responses to the plan. Specifically, we propose two discourse-driven planning strategies, where the plan is conditioned as part of the input or part of the output prefix, respectively. Empirical experiments on three lay summarization datasets show that our approach outperforms existing state-of-the-art methods in terms of summary quality, and it enhances model robustness, controllability, and mitigates hallucination.

Artificial Intelligence (AI) holds great promise for transforming healthcare, particularly in disease diagnosis, prognosis, and patient care. The increasing availability of digital medical data, such as images, omics, biosignals, and electronic health records, combined with advances in computing, has enabled AI models to approach expert-level performance. However, widespread clinical adoption remains limited, primarily due to challenges beyond technical performance, including ethical concerns, regulatory barriers, and lack of trust. To address these issues, AI systems must align with the principles of Trustworthy AI (TAI), which emphasize human agency and oversight, algorithmic robustness, privacy and data governance, transparency, bias and discrimination avoidance, and accountability. Yet, the complexity of healthcare processes (e.g., screening, diagnosis, prognosis, and treatment) and the diversity of stakeholders (clinicians, patients, providers, regulators) complicate the integration of TAI principles. To bridge the gap between TAI theory and practical implementation, this paper proposes a design framework to support developers in embedding TAI principles into medical AI systems. Thus, for each stakeholder identified across various healthcare processes, we propose a disease-agnostic collection of requirements that medical AI systems should incorporate to adhere to the principles of TAI. Additionally, we examine the challenges and tradeoffs that may arise when applying these principles in practice. To ground the discussion, we focus on cardiovascular diseases, a field marked by both high prevalence and active AI innovation, and demonstrate how TAI principles have been applied and where key obstacles persist.

While metrics available during pre-training, such as perplexity, correlate well with model performance at scaling-laws studies, their predictive capacities at a fixed model size remain unclear, hindering effective model selection and development. To address this gap, we formulate the task of selecting pre-training checkpoints to maximize downstream fine-tuning performance as a pairwise classification problem: predicting which of two LLMs, differing in their pre-training, will perform better after supervised fine-tuning (SFT). We construct a dataset using 50 1B parameter LLM variants with systematically varied pre-training configurations, e.g., objectives or data, and evaluate them on diverse downstream tasks after SFT. We first conduct a study and demonstrate that the conventional perplexity is a misleading indicator. As such, we introduce novel unsupervised and supervised proxy metrics derived from pre-training that successfully reduce the relative performance prediction error rate by over 50%. Despite the inherent complexity of this task, we demonstrate the practical utility of our proposed proxies in specific scenarios, paving the way for more efficient design of pre-training schemes optimized for various downstream tasks.

The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in training data, linguistic imbalances, or adversarial manipulation. Despite mitigation efforts, recent studies show that LLMs remain vulnerable to adversarial attacks that elicit biased outputs. This work proposes a scalable benchmarking framework to assess LLM robustness to adversarial bias elicitation. Our methodology involves: (i) systematically probing models across multiple tasks targeting diverse sociocultural biases, (ii) quantifying robustness through safety scores using an LLM-as-a-Judge approach, and (iii) employing jailbreak techniques to reveal safety vulnerabilities. To facilitate systematic benchmarking, we release a curated dataset of bias-related prompts, named CLEAR-Bias. Our analysis, identifying DeepSeek V3 as the most reliable judge LLM, reveals that bias resilience is uneven, with age, disability, and intersectional biases among the most prominent. Some small models outperform larger ones in safety, suggesting that training and architecture may matter more than scale. However, no model is fully robust to adversarial elicitation, with jailbreak attacks using low-resource languages or refusal suppression proving effective across model families. We also find that successive LLM generations exhibit slight safety gains, while models fine-tuned for the medical domain tend to be less safe than their general-purpose counterparts.