Large Language Models (LLMs) are increasingly embedded in autonomous systems and public-facing environments, yet they remain susceptible to jailbreak vulnerabilities that may undermine their security and trustworthiness. Adversarial suffixes are considered to be the current state-of-the-art jailbreak, consistently outperforming simpler methods and frequently succeeding even in black-box settings. Existing defenses rely on access to the internal architecture of models limiting diverse deployment, increase memory and computation footprints dramatically, or can be bypassed with simple prompt engineering methods. We introduce $\textbf{Adversarial Suffix Filtering}$ (ASF), a lightweight novel model-agnostic defensive pipeline designed to protect LLMs against adversarial suffix attacks. ASF functions as an input preprocessor and sanitizer that detects and filters adversarially crafted suffixes in prompts, effectively neutralizing malicious injections. We demonstrate that ASF provides comprehensive defense capabilities across both black-box and white-box attack settings, reducing the attack efficacy of state-of-the-art adversarial suffix generation methods to below 4%, while only minimally affecting the target model's capabilities in non-adversarial scenarios.

Scaling robot learning requires vast and diverse datasets. Yet the prevailing data collection paradigm-human teleoperation-remains costly and constrained by manual effort and physical robot access. We introduce Real2Render2Real (R2R2R), a novel approach for generating robot training data without relying on object dynamics simulation or teleoperation of robot hardware. The input is a smartphone-captured scan of one or more objects and a single video of a human demonstration. R2R2R renders thousands of high visual fidelity robot-agnostic demonstrations by reconstructing detailed 3D object geometry and appearance, and tracking 6-DoF object motion. R2R2R uses 3D Gaussian Splatting (3DGS) to enable flexible asset generation and trajectory synthesis for both rigid and articulated objects, converting these representations to meshes to maintain compatibility with scalable rendering engines like IsaacLab but with collision modeling off. Robot demonstration data generated by R2R2R integrates directly with models that operate on robot proprioceptive states and image observations, such as vision-language-action models (VLA) and imitation learning policies. Physical experiments suggest that models trained on R2R2R data from a single human demonstration can match the performance of models trained on 150 human teleoperation demonstrations. Project page: https://real2render2real.com

Large Language Models (LLMs) are predominantly trained and aligned in ways that reinforce Western-centric epistemologies and socio-cultural norms, leading to cultural homogenization and limiting their ability to reflect global civilizational plurality . Existing benchmarking frameworks fail to adequately capture this bias, as they rely on rigid, closed-form assessments that overlook the complexity of cultural inclusivity. To address this, we introduce WorldView-Bench, a benchmark designed to evaluate Global Cultural Inclusiv-ity (GCI) in LLMs by analyzing their ability to accommodate diverse worldviews. Our approach is grounded in the Multiplex Worldview proposed by Senturk et al., which distinguishes between Uniplex models, reinforcing cultural homogenization, and Multiplex models, which integrate diverse perspectives. WorldView-Bench measures Cultural Polarization, the exclusion of alternative perspectives, through free-form generative evaluation rather than conventional categorical benchmarks. We implement applied multiplex-ity through two intervention strategies: (1) Contextually-Implemented Multiplex LLMs, where system prompts embed multiplexity principles, and (2) Multi-Agent System (MAS)- Implemented Multiplex LLMs, where multiple LLM agents representing distinct cultural perspectives collaboratively generate responses. Our results demonstrate a significant increase in Perspectives Distribution Score (PDS) entropy from 13% at baseline to 94% with MAS-Implemented Multiplex LLMs, alongside a shift toward positive sentiment (67.7%) and enhanced cultural balance. These findings highlight the potential of multiplex-aware AI evaluation in mitigating cultural bias in LLMs, paving the way for more inclusive and ethically aligned AI systems.

While vision-language models have advanced significantly, their application in language-conditioned robotic manipulation is still underexplored, especially for contact-rich tasks that extend beyond visually dominant pick-and-place scenarios. To bridge this gap, we introduce Vision-Tactile-Language-Action model, a novel framework that enables robust policy generation in contact-intensive scenarios by effectively integrating visual and tactile inputs through cross-modal language grounding. A low-cost, multi-modal dataset has been constructed in a simulation environment, containing vision-tactile-action-instruction pairs specifically designed for the fingertip insertion task. Furthermore, we introduce Direct Preference Optimization (DPO) to offer regression-like supervision for the VTLA model, effectively bridging the gap between classification-based next token prediction loss and continuous robotic tasks. Experimental results show that the VTLA model outperforms traditional imitation learning methods (e.g., diffusion policies) and existing multi-modal baselines (TLA/VLA), achieving over 90% success rates on unseen peg shapes. Finally, we conduct real-world peg-in-hole experiments to demonstrate the exceptional Sim2Real performance of the proposed VTLA model. For supplementary videos and results, please visit our project website: https://sites.google.com/view/vtla

Since 2022, versions of generative AI chatbots such as ChatGPT and Claude have been trained using a specialized technique called Reinforcement Learning from Human Feedback (RLHF) to fine-tune language model output using feedback from human annotators. As a result, the integration of RLHF has greatly enhanced the outputs of these large language models (LLMs) and made the interactions and responses appear more "human-like" than those of previous versions using only supervised learning. The increasing convergence of human and machine-written text has potentially severe ethical, sociotechnical, and pedagogical implications relating to transparency, trust, bias, and interpersonal relations. To highlight these implications, this paper presents a rhetorical analysis of some of the central procedures and processes currently being reshaped by RLHF-enhanced generative AI chatbots: upholding language conventions, information seeking practices, and expectations for social relationships. Rhetorical investigations of generative AI and LLMs have, to this point, focused largely on the persuasiveness of the content generated. Using Ian Bogost's concept of procedural rhetoric, this paper shifts the site of rhetorical investigation from content analysis to the underlying mechanisms of persuasion built into RLHF-enhanced LLMs. In doing so, this theoretical investigation opens a new direction for further inquiry in AI ethics that considers how procedures rerouted through AI-driven technologies might reinforce hegemonic language use, perpetuate biases, decontextualize learning, and encroach upon human relationships. It will therefore be of interest to educators, researchers, scholars, and the growing number of users of generative AI chatbots.

Parameter-efficient fine-tuning (PEFT) methods have shown promise in adapting large language models, yet existing approaches exhibit counter-intuitive phenomena: integrating router into prompt tuning (PT) increases training efficiency yet does not improve performance universally; parameter reduction through matrix decomposition can improve performance in specific domains. Motivated by these observations and the modular nature of PT, we propose PT-MoE, a novel framework that integrates matrix decomposition with mixture-of-experts (MoE) routing for efficient PT. Results across 17 datasets demonstrate that PT-MoE achieves state-of-the-art performance in both question answering (QA) and mathematical problem solving tasks, improving F1 score by 1.49 points over PT and 2.13 points over LoRA in QA tasks, while enhancing mathematical accuracy by 10.75 points over PT and 0.44 points over LoRA, all while using 25% fewer parameters than LoRA. Our analysis reveals that while PT methods generally excel in QA tasks and LoRA-based methods in math datasets, the integration of matrix decomposition and MoE in PT-MoE yields complementary benefits: decomposition enables efficient parameter sharing across experts while MoE provides dynamic adaptation, collectively enabling PT-MoE to demonstrate cross-task consistency and generalization abilities. These findings, along with ablation studies on routing mechanisms and architectural components, provide insights for future PEFT methods.

The integration of foundation models (FMs) into robotics has enabled robots to understand natural language and reason about the semantics in their environments. However, existing FM-enabled robots primary operate in closed-world settings, where the robot is given a full prior map or has a full view of its workspace. This paper addresses the deployment of FM-enabled robots in the field, where missions often require a robot to operate in large-scale and unstructured environments. To effectively accomplish these missions, robots must actively explore their environments, navigate obstacle-cluttered terrain, handle unexpected sensor inputs, and operate with compute constraints. We discuss recent deployments of SPINE, our LLM-enabled autonomy framework, in field robotic settings. To the best of our knowledge, we present the first demonstration of large-scale LLM-enabled robot planning in unstructured environments with several kilometers of missions. SPINE is agnostic to a particular LLM, which allows us to distill small language models capable of running onboard size, weight and power (SWaP) limited platforms. Via preliminary model distillation work, we then present the first language-driven UAV planner using on-device language models. We conclude our paper by proposing several promising directions for future research.

In the 2000s, artificial intelligence and deep learning - based systems became prevalent and took over the world by storm . Many modern multilingual state - of - the - art [ 1 ] networks and cloud - based translation services like Google Translate, Microsoft Translator, ChatGPT [ 2 ], DeepSeek [ 3 ] emerged and became available during this era . These Multilingual Large Language Networks are architected around Gated Recurrent Unit Networks ( GRU) [ 4 ], Long Short - Term Memory ( LSTM) [ 5 ], Bidirectional Encoder Representations from Transformers ( BERT) [ 6 ], Generative pre - trained transformer ( GPT) [ 7 ], Text - to - Text Transfer Transformer ( T5) [ 8 ] and similar attention - based transformers [ 9 ] networks with finer and improve d amendments to architectures. W hile m ost academicians, researchers, and organisations focused on these classical computing realm aspects and less emphasis was put on multilingual machine tr a nslation in the quantum computing realm . S ome practitioners and scholars who emphasis ed quantum computing for machine tr a nslation and their associated works are discussed in the Related Works section later. However, these researches under - u tilize d simulat ion and execution on quantum computing hardware along with under - exploit ing the novel perceptions of quantum convolution [ 10 ], quantum pooling [ 11 ], quantum variational circuit [ 12 ] and quantum attention [ 13 ] as quantum - based software amendments that are studie d, demonstrate d and stunned as shortcomings in QEDACVC system .

In this work, we present Qwen3, the latest version of the Qwen model family. Qwen3 comprises a series of large language models (LLMs) designed to advance performance, efficiency, and multilingual capabilities. The Qwen3 series includes models of both dense and Mixture-of-Expert (MoE) architectures, with parameter scales ranging from 0.6 to 235 billion. A key innovation in Qwen3 is the integration of thinking mode (for complex, multi-step reasoning) and non-thinking mode (for rapid, context-driven responses) into a unified framework. This eliminates the need to switch between different models--such as chat-optimized models (e.g., GPT-4o) and dedicated reasoning models (e.g., QwQ-32B)--and enables dynamic mode switching based on user queries or chat templates. Meanwhile, Qwen3 introduces a thinking budget mechanism, allowing users to allocate computational resources adaptively during inference, thereby balancing latency and performance based on task complexity. Moreover, by leveraging the knowledge from the flagship models, we significantly reduce the computational resources required to build smaller-scale models, while ensuring their highly competitive performance. Empirical evaluations demonstrate that Qwen3 achieves state-of-the-art results across diverse benchmarks, including tasks in code generation, mathematical reasoning, agent tasks, etc., competitive against larger MoE models and proprietary models. Compared to its predecessor Qwen2.5, Qwen3 expands multilingual support from 29 to 119 languages and dialects, enhancing global accessibility through improved cross-lingual understanding and generation capabilities. To facilitate reproducibility and community-driven research and development, all Qwen3 models are publicly accessible under Apache 2.0.

This study evaluates and extends the findings made by Piatti et al. (2024), who introduced GovSim, a simulation framework designed to assess the cooperative decision-making capabilities of large language models (LLMs) in resource-sharing scenarios. By replicating key experiments, we validate claims regarding the performance of large models, such as GPT-4-turbo, compared to smaller models. The impact of the universalization principle is also examined, with results showing that large models can achieve sustainable cooperation, with or without the principle, while smaller models fail without it. In addition, we provide multiple extensions to explore the applicability of the framework to new settings. We evaluate additional models, such as DeepSeek-V3 and GPT-4o-mini, to test whether cooperative behavior generalizes across different architectures and model sizes. Furthermore, we introduce new settings: we create a heterogeneous multi-agent environment, study a scenario using Japanese instructions, and explore an "inverse environment" where agents must cooperate to mitigate harmful resource distributions. Our results confirm that the benchmark can be applied to new models, scenarios, and languages, offering valuable insights into the adaptability of LLMs in complex cooperative tasks. Moreover, the experiment involving heterogeneous multi-agent systems demonstrates that high-performing models can influence lower-performing ones to adopt similar behaviors. This finding has significant implications for other agent-based applications, potentially enabling more efficient use of computational resources and contributing to the development of more effective cooperative AI systems.