Unified Multimodal Models (UMMs) have shown impressive performance in both understanding and generation with a single architecture. However, UMMs still exhibit a fundamental inconsistency: understanding favors compact embeddings, whereas generation favors reconstruction-rich representations. This structural trade-off produces misaligned decision boundaries, degraded cross-modal coherence, and heightened vulnerability under distributional and adversarial shifts. In this paper, we present UniGame, a self-adversarial post-training framework that directly targets the inconsistencies. By applying a lightweight perturber at the shared token interface, UniGame enables the generation branch to actively seek and challenge fragile understanding, turning the model itself into its own adversary. Experiments demonstrate that UniGame significantly improves the consistency (+4.6%). Moreover, it also achieves substantial improvements in understanding (+3.6%), generation (+0.02), out-of-distribution and adversarial robustness (+4.8% and +6.2% on NaturalBench and AdVQA). The framework is architecture-agnostic, introduces less than 1% additional parameters, and is complementary to existing post-training methods. These results position adversarial self-play as a general and effective principle for enhancing the coherence, stability, and unified competence of future multimodal foundation models. The official code is available at: https://github.com/AIFrontierLab/UniGame

Monocular Simultaneous Localization and Mapping (SLAM) aims to estimate a robot's pose while simultaneously reconstructing an unknown 3D scene using a single camera. While existing monocular SLAM systems generate detailed 3D geometry through dense scene representations, they are computationally expensive due to the need for iterative optimization. To address this challenge, MASt3R-SLAM utilizes learned 3D reconstruction priors, enabling more efficient and accurate estimation of both 3D structures and camera poses. However, MASt3R-SLAM is limited to single-agent operation. In this paper, we extend MASt3R-SLAM to introduce the first multi-agent monocular dense SLAM system. Each agent performs local SLAM using a 3D reconstruction prior, and their individual maps are fused into a globally consistent map through a loop-closure-based map fusion mechanism. Our approach improves computational efficiency compared to state-of-the-art methods, while maintaining similar mapping accuracy when evaluated on real-world datasets.

Recent progress in video generative models has enabled the creation of high-quality videos from multimodal prompts that combine text and images. While these systems offer enhanced controllability, they also introduce new safety risks, as harmful content can emerge from individual modalities or their interaction. Existing safety methods are often text-only, require prior knowledge of the risk category, or operate as post-generation auditors, struggling to proactively mitigate such compositional, multimodal risks. To address this challenge, we present ConceptGuard, a unified safeguard framework for proactively detecting and mitigating unsafe semantics in multimodal video generation. ConceptGuard operates in two stages: First, a contrastive detection module identifies latent safety risks by projecting fused image-text inputs into a structured concept space; Second, a semantic suppression mechanism steers the generative process away from unsafe concepts by intervening in the prompt's multimodal conditioning. To support the development and rigorous evaluation of this framework, we introduce two novel benchmarks: ConceptRisk, a large-scale dataset for training on multimodal risks, and T2VSafetyBench-TI2V, the first benchmark adapted from T2VSafetyBench for the Text-and-Image-to-Video (TI2V) safety setting. Comprehensive experiments on both benchmarks show that ConceptGuard consistently outperforms existing baselines, achieving state-of-the-art results in both risk detection and safe video generation. Our code is available at https://github.com/Ruize-Ma/ConceptGuard.

Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but still suffers from long contexts and disjoint retrieval-generation optimization. In this work, we propose CLaRa (Continuous Latent Reasoning), a unified framework that performs embedding-based compression and joint optimization in a shared continuous space. To obtain semantically rich and retrievable compressed vectors, we introduce SCP, a key-preserving data synthesis framework using QA and paraphrase supervision. CLaRa then trains the reranker and generator end-to-end via a single language modeling loss, with gradients flowing through both modules using a differentiable top-k estimator. Theoretically, this unified optimization aligns retrieval relevance with answer quality. Experiments across multiple QA benchmarks show that CLaRa achieves state-of-the-art compression and reranking performance, often surpassing text-based fine-tuned baselines.

Three-dimensional rigid-body transforms, i.e. rotations and translations, are central to modern differentiable machine learning pipelines in robotics, vision, and simulation. However, numerically robust and mathematically correct implementations, particularly on SO(3), are error-prone due to issues such as axis conventions, normalizations, composition consistency and subtle errors that only appear in edge cases. SciPy's spatial$.$transform module is a rigorously tested Python implementation. However, it historically only supported NumPy, limiting adoption in GPU-accelerated and autodiff-based workflows. We present a complete overhaul of SciPy's spatial$.$transform functionality that makes it compatible with any array library implementing the Python array API, including JAX, PyTorch, and CuPy. The revised implementation preserves the established SciPy interface while enabling GPU/TPU execution, JIT compilation, vectorized batching, and differentiation via native autodiff of the chosen backend. We demonstrate how this foundation supports differentiable scientific computing through two case studies: (i) scalability of 3D transforms and rotations and (ii) a JAX drone simulation that leverages SciPy's Rotation for accurate integration of rotational dynamics. Our contributions have been merged into SciPy main and will ship in the next release, providing a framework-agnostic, production-grade basis for 3D spatial math in differentiable systems and ML.

Most applications of generative AI involve a sequential interaction in which a person inputs a prompt and waits for a response, and where reaction time and adaptiv-ity are not important factors. In contrast, live jamming is a collaborative interaction that requires real-time coordination and adaptation without access to the other player's future moves, while preserving diversity to sustain a creative flow. Reinforcement learning post-training enables effective adaptation through on-policy interaction, yet it often reduces output diversity by exploiting coherence-based rewards. This collapse, known as "reward hacking", affects many RL post-training pipelines, but is especially harmful in live jamming, where musical creativity relies on dynamic variation and mutual responsiveness. In this paper, we propose a novel adversarial training method on policy-generated trajectories to mitigate reward hacking in RL post-training for melody-to-chord accompaniment. A co-evolving discriminator separates policy trajectories from the data distribution, while the policy maximizes the discriminator output in addition to coherence rewards to prevent collapse to trivial outputs. We evaluate accompaniment quality and output diversity in simulation with both fixed test melodies and learned melody agents, and we conduct a user study with the model deployed in a real-time interactive system with expert musicians. Quantitative evaluation and user feedback demonstrate improved output diversity, harmonic coherence, adaptation speed and user agency. Our results demonstrate a simple yet effective method to mitigate reward hacking in RL post-training of generative sequence models. The combination of large-scale transformer-based models and reinforcement learning (RL) post-training has revolutionized AI, with over 1 billion people now using large language models (LLMs) trained with these techniques (OpenAI, 2025; Perez, 2025). However, most applications of generative AI still involve a slow back-and-forth interaction, where the user inputs a request, and then waits--sometimes several minutes--for a response.

Beyond a simple notification of incoming calls or messages, more complex information such as alphabets and digits can be delivered through spatiotemporal tactile patterns (STPs) on a wrist-worn tactile display (WTD) with multiple tactors. However, owing to the limited skin area and spatial acuity of the wrist, frequent confusions occur between closely located tactors, resulting in a low recognition accuracy. Furthermore, the accuracies reported in previous studies have mostly been measured for a specific posture and could further decrease with free arm postures in real life. Herein, we present Heterogeneous Stroke, a design concept for improving the recognition accuracy of STPs on a WTD. By assigning unique vibrotactile stimuli to each tactor, the confusion between tactors can be reduced. Through our implementation of Heterogeneous Stroke, the alphanumeric characters could be delivered with high accuracy (93.8% for 26 alphabets and 92.4% for 10 digits) across different arm postures.

Clinical antimicrobial therapy requires the dynamic integration of pathogen profiles, host factors, pharmacological properties of antimicrobials, and the severity of infection.This complexity imposes fundamental limitations on the applicability of Large Language Models (LLMs) in high-stakes clinical decision-making including knowledge gaps, data privacy concerns, high deployment costs, and limited reasoning capabilities. This is the first author footnote. A hierarchical evaluation employing diverse teacher-model proxies reduces assessment costs, while modular interface design facilitates seamless system updates. Experimental results demonstrate that KRAL significantly outperforms traditional Retrieval-Augmented Generation (RAG) and Supervised Fine-Tuning (SFT) methods. It improves knowledge question-answering capability (Accuracy@1 on the external open-source benchmark MEDQA increased by 1.8% vs. SFT and 3.6% vs. RAG) and reasoning capability (Pass@1 on the external benchmark PUMCH Antimicrobial increased by 27% vs. SFT and 27.2% vs. RAG), achieved at 20% of SFT's long-term training costs. This establishes KRAL as an effective solution for enhancing local LLMs' clinical diagnostic capabilities, enabling low-cost, high-safety deployment in complex medical decision support. Introduction Antimicrobial therapy constitutes a cornerstone of modern clinical practice. The formulation of an effective regimen necessitates the integration of pathogen-specific factors, host characteristics, pharmacokinetic pharma-codynamic (PK/PD) properties of antimicrobials, and infection severity, all of which are dynamic and interrelated. This places significant cognitive load on clinicians, especially for non-infectious disease specialists or in situations where pathogens are unknown and time is limited, which may result in sub-optimal prescribing decisions, thereby increasing the likelihood of therapeutic failure, antimicrobial toxicity, and the emergence of multidrug-resistant (MDR) pathogens. Large language models (LLMs) have recently emerged as promising tools for enhancing clinical decision support systems (CDSS), owing to their advanced natural language understanding and generation capabilities. Nevertheless, the direct deployment of general-purpose LLMs in high-stakes clinical domains such as antimicrobial therapy is fraught with limitations, including: Knowledge bias: Medical content constitutes <0.3 % of the pre-training corpora[1] in mainstream LLMs (e.g., GPT-3), resulting in limited coverage of rare or emerging pathogens[2-4], outdated guideline adherence[5-9](Appendix A1), and suboptimal performance on atypical presentations. 2 Data privacy and compliance risks: The use of closed-source, cloud-based LLMs (e.g., GPT-4) for processing unencrypted protected health information (PHI) may violate HIPAA/GDPR-equivalent regulations, even under private deployment scenarios if online guideline updates are required[10-12].

reasoning from minimal examples remains a core unsolved problem for frontier foundation models such as GPT-5 and Grok 4. These models still fail to infer structured transformation rules from a handful of examples, which is a key hallmark of human intelligence. The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) provides a rigorous testbed for this capability, demanding conceptual rule induction and transfer to novel tasks. Most existing methods treat ARC-AGI as a purely textual reasoning task, overlooking the fact that humans rely heavily on visual abstraction when solving such puzzles. However, our pilot experiments reveal a paradox: naively rendering ARC-AGI grids as images degrades performance due to imprecise rule execution. This leads to our central hypothesis that vision and language possess complementary strengths across distinct reasoning stages: vision supports global pattern abstraction and verification, whereas language specializes in symbolic rule formulation and precise execution. Building on this insight, we introduce two synergistic strategies: (1) Vision-Language Synergy Reasoning (VLSR), which decomposes ARC-AGI into modality-aligned subtasks; and (2) Modality-Switch Self-Correction (MSSC), which leverages vision to verify text-based reasoning for intrinsic error correction. Extensive experiments demonstrate that our approach yields up to a 4.33% improvement over text-only baselines across diverse flagship models and multiple ARC-AGI tasks. Our findings suggest that unifying visual abstraction with linguistic reasoning is a crucial step toward achieving general-izable, human-like intelligence in future foundation models. Source code is released at https://github.com/

Quantum computing promises transformative advances, but remains constrained by recurring misconceptions and methodological pitfalls. This paper demonstrates a fundamental incompatibility between traditional agent-based modeling (ABM) implementations and quantum optimization frameworks like Quadratic Unconstrained Binary Optimization (QUBO). Using Schelling's segregation model as a case study, we show that the standard practice of directly translating ABM state observations into QUBO formulations not only fails to deliver quantum advantage, but actively undermines computational efficiency. The fundamental issue is architectural. Traditional ABM implementations entail observing the state of the system at each iteration, systematically destroying the quantum superposition required for computational advantage. Through analysis of Schelling's segregation dynamics on lollipop networks, we demonstrate how abandoning the QUBO reduction paradigm and instead reconceptualizing the research question, from "simulate agent dynamics iteratively until convergence" to "compute minimum of agent moves required for global satisfaction", enables a faster classical solution. This structural reconceptualization yields an algorithm that exploits network symmetries obscured in traditional ABM simulations and QUBO formulations. It establishes a new lower bound which quantum approaches must outperform to achieve advantage. Our work emphasizes that progress in quantum agent-based modeling does not require forcing classical ABM implementations into quantum frameworks. Instead, it should focus on clarifying when quantum advantage is structurally possible, developing best-in-class classical baselines through problem analysis, and fundamentally reformulating research questions rather than preserving classical iterative state change observation paradigms.