Echo: Decoupling Inference and Training for Large-Scale RL Alignment on Heterogeneous Swarms

Modern RL-based post-training for large language models (LLMs) co-locate trajectory sampling and policy optimisation on the same GPU cluster, forcing the system to switch between inference and training workloads. This serial context switching violates the single-program-multiple-data (SPMD) assumption underlying today's distributed training systems. We present Echo, the RL system that cleanly decouples these two phases across heterogeneous "inference" and "training" swarms while preserving statistical efficiency. Echo introduces two lightweight synchronization protocols: a sequential pull mode that refreshes sampler weights on every API call for minimal bias, and an asynchronous push-pull mode that streams version-tagged rollouts through a replay buffer to maximise hardware utilisation. Training three representative RL workloads with Qwen3-4B, Qwen2.5-7B and Qwen3-32B on a geographically distributed cluster, Echo matches a fully co-located Verl baseline in convergence speed and final reward while off-loading trajectory generation to commodity edge hardware. These promising results demonstrate that large-scale RL for LLMs could achieve datacentre-grade performance using decentralised, heterogeneous resources.

xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations

We introduce xbench, a dynamic, profession-aligned evaluation suite designed to bridge the gap between AI agent capabilities and real-world productivity. While existing benchmarks often focus on isolated technical skills, they may not accurately reflect the economic value agents deliver in professional settings. To address this, xbench targets commercially significant domains with evaluation tasks defined by industry professionals. Our framework creates metrics that strongly correlate with productivity value, enables prediction of Technology-Market Fit (TMF), and facilitates tracking of product capabilities over time. As our initial implementations, we present two benchmarks: Recruitment and Marketing. For Recruitment, we collect 50 tasks from real-world headhunting business scenarios to evaluate agents' abilities in company mapping, information retrieval, and talent sourcing. For Marketing, we assess agents' ability to match influencers with advertiser needs, evaluating their performance across 50 advertiser requirements using a curated pool of 836 candidate influencers. We present initial evaluation results for leading contemporary agents, establishing a baseline for these professional domains. Our continuously updated evalsets and evaluations are available at https://xbench.org.

Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis

For autonomous vehicles, safe navigation in complex environments depends on handling a broad range of diverse and rare driving scenarios. Simulation- and scenario-based testing have emerged as key approaches to development and validation of autonomous driving systems. Traditional scenario generation relies on rule-based systems, knowledge-driven models, and data-driven synthesis, often producing limited diversity and unrealistic safety-critical cases. With the emergence of foundation models, which represent a new generation of pre-trained, general-purpose AI models, developers can process heterogeneous inputs (e.g., natural language, sensor data, HD maps, and control actions), enabling the synthesis and interpretation of complex driving scenarios. In this paper, we conduct a survey about the application of foundation models for scenario generation and scenario analysis in autonomous driving (as of May 2025). Our survey presents a unified taxonomy that includes large language models, vision-language models, multimodal large language models, diffusion models, and world models for the generation and analysis of autonomous driving scenarios. In addition, we review the methodologies, open-source datasets, simulation platforms, and benchmark challenges, and we examine the evaluation metrics tailored explicitly to scenario generation and analysis. Finally, the survey concludes by highlighting the open challenges and research questions, and outlining promising future research directions. All reviewed papers are listed in a continuously maintained repository, which contains supplementary materials and is available at https://github.com/TUM-AVS/FM-for-Scenario-Generation-Analysis.

UFM: A Simple Path towards Unified Dense Correspondence with Flow

Dense image correspondence is central to many applications, such as visual odometry, 3D reconstruction, object association, and re-identification. Historically, dense correspondence has been tackled separately for wide-baseline scenarios and optical flow estimation, despite the common goal of matching content between two images. In this paper, we develop a Unified Flow & Matching model (UFM), which is trained on unified data for pixels that are co-visible in both source and target images. UFM uses a simple, generic transformer architecture that directly regresses the (u,v) flow. It is easier to train and more accurate for large flows compared to the typical coarse-to-fine cost volumes in prior work. UFM is 28% more accurate than state-of-the-art flow methods (Unimatch), while also having 62% less error and 6.7x faster than dense wide-baseline matchers (RoMa). UFM is the first to demonstrate that unified training can outperform specialized approaches across both domains. This result enables fast, general-purpose correspondence and opens new directions for multi-modal, long-range, and real-time correspondence tasks.

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

This paper aims to overcome a major obstacle in scaling RL for reasoning with LLMs, namely the collapse of policy entropy. Such phenomenon is consistently observed across vast RL runs without entropy intervention, where the policy entropy dropped sharply at the early training stage, this diminished exploratory ability is always accompanied with the saturation of policy performance. In practice, we establish a transformation equation R=-a*e^H+b between entropy H and downstream performance R. This empirical law strongly indicates that, the policy performance is traded from policy entropy, thus bottlenecked by its exhaustion, and the ceiling is fully predictable H=0, R=-a+b. Our finding necessitates entropy management for continuous exploration toward scaling compute for RL. To this end, we investigate entropy dynamics both theoretically and empirically. Our derivation highlights that, the change in policy entropy is driven by the covariance between action probability and the change in logits, which is proportional to its advantage when using Policy Gradient-like algorithms. Empirical study shows that, the values of covariance term and entropy differences matched exactly, supporting the theoretical conclusion. Moreover, the covariance term stays mostly positive throughout training, further explaining why policy entropy would decrease monotonically. Through understanding the mechanism behind entropy dynamics, we motivate to control entropy by restricting the update of high-covariance tokens. Specifically, we propose two simple yet effective techniques, namely Clip-Cov and KL-Cov, which clip and apply KL penalty to tokens with high covariances respectively. Experiments show that these methods encourage exploration, thus helping policy escape entropy collapse and achieve better downstream performance.

The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts

The detection and grounding of multimedia manipulation has emerged as a critical challenge in combating AI-generated disinformation. While existing methods have made progress in recent years, we identify two fundamental limitations in current approaches: (1) Underestimation of MLLM-driven deception risk: prevailing techniques primarily address rule-based text manipulations, yet fail to account for sophisticated misinformation synthesized by multimodal large language models (MLLMs) that can dynamically generate semantically coherent, contextually plausible yet deceptive narratives conditioned on manipulated images; (2) Unrealistic misalignment artifacts: currently focused scenarios rely on artificially misaligned content that lacks semantic coherence, rendering them easily detectable. To address these gaps holistically, we propose a new adversarial pipeline that leverages MLLMs to generate high-risk disinformation. Our approach begins with constructing the MLLM-Driven Synthetic Multimodal (MDSM) dataset, where images are first altered using state-of-the-art editing techniques and then paired with MLLM-generated deceptive texts that maintain semantic consistency with the visual manipulations. Building upon this foundation, we present the Artifact-aware Manipulation Diagnosis via MLLM (AMD) framework featuring two key innovations: Artifact Pre-perception Encoding strategy and Manipulation-Oriented Reasoning, to tame MLLMs for the MDSM problem. Comprehensive experiments validate our framework's superior generalization capabilities as a unified architecture for detecting MLLM-powered multimodal deceptions.

Enhanced Multimodal Hate Video Detection via Channel-wise and Modality-wise Fusion

The rapid rise of video content on platforms such as TikTok and YouTube has transformed information dissemination, but it has also facilitated the spread of harmful content, particularly hate videos. Despite significant efforts to combat hate speech, detecting these videos remains challenging due to their often implicit nature. Current detection methods primarily rely on unimodal approaches, which inadequately capture the complementary features across different modalities. While multimodal techniques offer a broader perspective, many fail to effectively integrate temporal dynamics and modality-wise interactions essential for identifying nuanced hate content. In this paper, we present CMFusion, an enhanced multimodal hate video detection model utilizing a novel Channel-wise and Modality-wise Fusion Mechanism. CMFusion first extracts features from text, audio, and video modalities using pre-trained models and then incorporates a temporal cross-attention mechanism to capture dependencies between video and audio streams. The learned features are then processed by channel-wise and modality-wise fusion modules to obtain informative representations of videos. Our extensive experiments on a real-world dataset demonstrate that CMFusion significantly outperforms five widely used baselines in terms of accuracy, precision, recall, and F1 score. Comprehensive ablation studies and parameter analyses further validate our design choices, highlighting the model's effectiveness in detecting hate videos. The source codes will be made publicly available at https://github.com/EvelynZ10/cmfusion.

Tri-Hybrid Multi-User Precoding Using Pattern-Reconfigurable Antennas: Fundamental Models and Practical Algorithms

The integration of pattern-reconfigurable antennas into hybrid multiple-input multiple-output (MIMO) architectures presents a promising path toward high-efficiency and low-cost transceiver solutions. Pattern-reconfigurable antennas can dynamically steer per-antenna radiation patterns, enabling more efficient power utilization and interference suppression. In this work, we study a tri-hybrid MIMO architecture for multi-user communication that integrates digital, analog, and antenna-domain precoding using pattern-reconfigurable antennas. For characterizing the reconfigurability of antenna radiation patterns, we develop two models -- Model~I and Model~II. Model~I captures realistic hardware constraints through limited pattern selection, while Model~II explores the performance upper bound by assuming arbitrary pattern generation. Based on these models, we develop two corresponding tri-hybrid precoding algorithms grounded in the weighted minimum mean square error (WMMSE) framework, which alternately optimize the digital, analog, and antenna precoders under practical per-antenna power constraints. Realistic simulations conducted in ray-tracing generated environments are utilized to evaluate the proposed system and algorithms. The results demonstrate the significant potential of the considered tri-hybrid architecture in enhancing communication performance and hardware efficiency. However, they also reveal that the existing hardware is not yet capable of fully realizing these performance gains, underscoring the need for joint progress in antenna design and communication theory development.

Tri-Hybrid Multi-User Precoding Based on Electromagnetically Reconfigurable Antennas

The tri-hybrid precoding architecture based on electromagnetically reconfigurable antennas (ERAs) is a promising solution for overcoming key limitations in multiple-input multiple-output communication systems. Aiming to further understand its potential, this paper investigates the tri-hybrid multi-user precoding problem using pattern reconfigurable ERAs. To reduce model complexity and improve practicality, we characterize each antenna's radiation pattern using a spherical harmonics decomposition. While mathematically tractable, this approach may lead to over-optimized patterns that are physically unrealizable. To address this, we introduce a projection step that maps the optimized patterns onto a realizable set. Simulation results demonstrate that spherical harmonics-based radiation pattern optimization significantly enhances sum rate performance. However, after projection onto a realizable set obtained from real ERA hardware, the performance gain is notably reduced or even negligible, underscoring the need for more effective projection techniques and improved reconfigurable antenna hardware.

Association between nutritional factors, inflammatory biomarkers and cancer types: an analysis of NHANES data using machine learning

Background. Diet and inflammation are critical factors influencing cancer risk. However, the combined impact of nutritional status and inflammatory biomarkers on cancer status and type, using machine learning (ML), remains underexplored. Objectives. This study investigates the association between nutritional factors, inflammatory biomarkers, and cancer status, and whether these relationships differ across cancer types using National Health and Nutrition Examination Survey (NHANES) data. Methods. We analyzed 24 macro- and micronutrients, C-reactive protein (CRP), and the advanced lung cancer inflammation index (ALI) in 26,409 NHANES participants (2,120 with cancer). Multivariable logistic regression assessed associations with cancer prevalence. We also examined whether these features differed across the five most common cancer types. To evaluate predictive value, we applied three ML models - Logistic Regression, Random Forest, and XGBoost - on the full feature set. Results. The cohort's mean age was 49.1 years; 34.7% were obese. Comorbidities such as anemia and liver conditions, along with nutritional factors like protein and several vitamins, were key predictors of cancer status. Among the models, Random Forest performed best, achieving an accuracy of 0.72. Conclusions. Higher-quality nutritional intake and lower levels of inflammation may offer protective effects against cancer. These findings highlight the potential of combining nutritional and inflammatory markers with ML to inform cancer prevention strategies.