Token Communication for Multimodal Large Language Model

With the broad success of the Transformer architecture, token is becoming a new basic information processing unit. This trend is especially evident in multimodal large language models (MLLMs), where both visual and textual information are represented and processed as tokens. With the rapid deployment of MLLMs, the efficient transmission of tokens has become increasingly important. This paper investigates how to reduce the amount of transmitted data during interactions with MLLMs while preserving their multimodal understanding performance. To address this problem, we propose a token communication framework tailored to MLLMs. In the proposed framework, a neural codec is integrated into the vision tokenizer to control the number of transmitted bits. At the receiver, the decoded latents are processed through two paths. The decoder reconstructs image as a reconstruction prior, while the adapter converts latents into visual tokens and injects them into an intermediate layer of the vision tokenizer. To make the injected tokens suitable for MLLMs, we further design a two-stage visual-language semantic alignment training scheme. The adapter is first warmed up by a distillation loss and then aligned with textual semantics through an alignment loss. An adaptive adapter is also introduced through feature-wise linear modulation, allowing one adapter to support multiple codec rates. Extensive simulations on various MLLM benchmarks show that, under the same amount of transmitted data, the proposed scheme achieves better task performance than other image processing schemes for MLLMs.

SynPre-FL: Synthetic data-driven pretraining integrated Federated Learning training framework

Federated learning (FL) offers a promising approach to privacy-preserving clinical risk prediction, but its deployment remains limited by restricted data sharing, client heterogeneity, class imbalance, and the lack of realistic tabular electronic health record (EHR) benchmarks. Synthetic data generation may alleviate data scarcity, yet its integration with federated optimisation has received limited systematic study. We propose SynPre-FL, a unified framework combining high-fidelity synthetic EHR generation with synthetic-pretrained FL for robust prediction under non-IID conditions. A latent autoencoder-diffusion model generates privacy-preserving synthetic cohorts, which are used to warm-start federated training. This pretraining is followed by heterogeneity-aware optimisation using class-balanced local objectives, proximal regularisation, and adaptive server aggregation. Post-hoc calibration and federated-safe explainability support reliable and interpretable risk estimates. Experiments show that the synthetic generator preserves univariate, bivariate, and multivariate structure while protecting against membership-inference and reconstruction attacks. The generated data achieve strong downstream utility under TSTR, TRTS, and model-based evaluations. Across federated settings with 5, 10, and 15 heterogeneous clients, SynPre-FL consistently improves robustness and scalability over baseline methods, especially under severe non-IID fragmentation. Calibration improves probability reliability, while SHAP analysis produces stable and clinically coherent feature attributions across federation sizes. SynPre-FL therefore provides a practical and reproducible framework for combining synthetic data with FL to enable privacy-aware, interpretable, and robust clinical prediction from distributed tabular EHR data.

Data-Aided Target Localization in Multistatic ISAC Systems With Communication Constraints

Integrated sensing and communication (ISAC) enables future wireless networks to perform sensing and communication (S&C) over a shared waveform. In multistatic ISAC systems, however, the sensing receivers do not know the realizations of transmitted data symbols, making it challenging to exploit communication signals for sensing. In this paper, we propose a data-aided framework for target localization with two receiver strategies, namely statistical data-aided sensing and joint data-aided sensing and decoding, where the former marginalizes the random unknown data symbols and the latter reuses the reliably decoded data symbols as known virtual pilots. Under orthogonal frequency division multiplexing (OFDM) signaling, we derive the performance limits for target localization in both strategies and adopt the achievable ergodic data rate as the communication metric. Then, we formulate a joint time-allocation and transmit data-covariance design problem for target localization under communication constraints, which characterizes the joint S&C bound and quantifies the sensing gain provided by data symbols. In addition, we develop two target localization algorithms that implement the proposed data-aided receiver processing, and extend the framework to finite-alphabet signaling. Simulation results validate theoretical analysis and the effectiveness of the proposed data-aided schemes.

Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation

While recent Vision-Language-Action (VLA) models show promise toward generalist manipulation policies, they struggle with long-horizon tasks due to their Markovian nature-relying solely on current observations. Hierarchical dual-system methods address this but suffer from a gap between high-level planning semantics and low-level execution kinematics. We introduce Cortex, a bidirectionally aligned embodied agent framework with a customized planning interface that conveys executable and tractable subtask plans from high-level VLM to low-level VLA. Specifically, we standardize manipulation subtasks into 32 canonical skill primitives and inject tractability principles, such as representative object attributes and improved trajectory reachability, into the data generation pipeline. This enables automatic annotation of over 4k hours of open-source video data and generation of 30 hours of simulation data. We further devise an event-balanced sampling strategy to construct training data for fine-tuning the framework to better handle planning ambiguity during subtask transitions, enhanced by carefully designed harness engineering from task contexts to skill constraints during inference. Both open-loop VLM and closed-loop system evaluations demonstrate Cortex's efficacy, e.g., it outperforms monolithic baselines by 3.1% on Libero-long and 4.1% on RoboTwin. Notably, Cortex's generalist VLM enables zero-shot completion of unseen real-world long-horizon tasks, such as multi-stage chemistry experiments, by simply combining with a fine-tuned VLA-a capability infeasible through VLA fine-tuning alone.

Stress-testing medical large language models reveals latent safety pathology beyond benchmark accuracy

Large language models (LLMs) are entering clinical practice based on benchmark accuracy that may fail to detect safety-relevant failure modes. Here we present AI-MASLD, a stress-audit framework that adapts the logic of metabolic stress testing from hepatology to the evaluation of clinical LLMs. Using 240 clinical cases across six narrative perturbation probes, we subjected seven models to double-stress testing and quantified performance through three indices: metabolic index (MI), perturbation flip rate (PFR), and counterfactual fairness index (CFI). Under clean baseline conditions, all models performed uniformly well. Under realistic narrative stress, performance diverged sharply, revealing two distinct stress-response phenotypes. Quantized models exhibited pseudonormalization, in which low flip rates hid functional collapse. Medical supervised fine-tuning systematically degraded logical stability, fairness, and information extraction. An open-weight model matched or exceeded proprietary alternatives on every safety dimension. These findings establish narrative stress auditing as a necessary complement to accuracy-based evaluation.

Instantaneous Risk Minimization for Secure Integrated Sensing and Communication

To ensure worst-case physical layer security, this paper proposes a robust beamforming framework for secure integrated sensing and communication (ISAC) systems. Different from conventional designs that focus on maximizing the ergodic secrecy rate, the proposed method aims to minimize instantaneous information leakage risk. We formulate a multi-objective optimization problem that jointly suppresses the worst-case eavesdropper signal-to-interference-plus-noise ratio (SINR), improving sensing accuracy, and ensuring the quality of service (QoS) for legitimate users. To address the resulting non-convex problem, we develop a hierarchical iterative algorithm, in which the outer loop refines the continuous uncertainty regions based on the updated sensing performance, and the inner loop optimizes beamforming under the refined uncertainty regions. Theoretical analysis and simulation results demonstrate that the proposed method achieves per-transmission security guarantees with practical complexity.

Provably Guaranteed Polytopic Uncertainty Quantification for SLAM

In safety-critical robotics applications, guaranteed and practical uncertainty quantification (UQ) in perception is vital. Many existing works either offer no formal containment guarantee, rely on restrictive modeling assumptions, or focus only on pose estimation rather than a complete SLAM pipeline. This paper presents provably guaranteed UQ algorithms for 3D-3D landmark-based SLAM. The algorithms consist of three basic UQ modules: forward UQ for mapping, backward UQ for pose tracking, and pose compound. Each module produces a certified uncertainty set; when the input uncertainty bounds are deterministic, the output sets inherit deterministic guarantees, i.e., they provably contain the true poses and landmarks. Specifically, we use polytopes to represent uncertainty sets, enabling tractable computations and a unified treatment of pose uncertainty. To enhance algorithms' practical usability, we incorporate conformal prediction to calibrate measurement uncertainty from data with prescribed probability. Simulations and experiments demonstrate that the proposed algorithms provide both strong theoretical guarantees and practical usability. The code is open-sourced at https://github.com/LIAS-CUHKSZ/Polytopic-SLAM-Uncertainty-Quantification.

Sensing-Constrained Diversity-Multiplexing Tradeoff in MIMO ISAC: A Geometric Approach

Diversity and multiplexing are the two fundamental gains of multiple-input and multiple-output (MIMO) communications, enabling systems to simultaneously achieve increased reliability and higher data rates. The intricate interplay between these two metrics is captured by the celebrated diversity-multiplexing tradeoff (DMT). With the rapid evolution of wireless technologies, low-latency integrated sensing and communication (ISAC) has emerged as a key enabler for 6G applications, including extended reality (XR) and massive digital twins. Consequently, understanding the DMT within MIMO ISAC systems becomes critical. In this paper, we investigate the communication DMT in a mono-static MIMO ISAC system under Rayleigh fading, specifically when the transmitter is constrained to emit sensing-optimal waveforms. By unveiling the geometric properties of generalized Stiefel manifolds and employing large-deviation analysis, we characterize the asymptotic outage probability of this typical ISAC channel. This formulation yields an elegant converse bound on the sensing-constrained DMT. Ultimately, our work provides an answer to a pivotal unanswered question in ISAC system design: How much MIMO gain is fundamentally sacrificed in communication to integrate optimal sensing capabilities?

Fully-analog array signal processor using 3D aperture engineering

The rapid progress in radar and communication places increasing demands on low-latency and energy-efficiency array signal processing methods. There is an emerging direction of constructing analog computing processors for directly processing electromagnetic (EM) waves. However, the existing methods are constrained by 2D physical aperture and imprecise design process with inefficient computing architecture, resulting in limited sensing resolution and number of separated sources. Here, we present a fully-analog array signal processor (FASP) using 3D aperture engineering framework to perform super-resolution direction-of-arrival estimation, source number estimation, and multi-channel source separation in parallel for both coherent and incoherent sources. 3D aperture engineering is realized by constructing deep cascaded metasurface layers so that the diffractive propagation from oblique incident fields can be layer-wise modulated and piecewise encoded for perceiving EM fields far exceeding physical aperture limits. The multi-dimensional synthetic aperture (MSA) training is developed to characterize the metasurface modulation and optimize the neuro-augmented physical model for extending system aperture and generating high-order nonlinear angular response. FASP orthogonalizes the array response vectors of communication channels to map them into antenna detectors in the analog domain. The $N$-layer FASP has the capability to achieve ~N times higher angular resolution than the Rayleigh diffraction limit. Experiments further validate the source number estimation and independent channel separation of 10-target that can suppress radar jamming signals by ~20 dB and enhance channel communication capacity by 13.5 times at 36~41 GHz. FASP heralds a paradigm shift in signal processing for super-resolution optics, advanced radar, and 6G communications.

EGAM: Extended Graph Attention Model for Solving Routing Problems

Neural combinatorial optimization (NCO) solvers, implemented with graph neural networks (GNNs), have introduced new approaches for solving routing problems. Trained with reinforcement learning (RL), the state-of-the-art graph attention model (GAM) achieves near-optimal solutions without requiring expert knowledge or labeled data. In this work, we generalize the existing graph attention mechanism and propose the extended graph attention model (EGAM). Our model utilizes multi-head dot-product attention to update both node and edge embeddings, addressing the limitations of the conventional GAM, which considers only node features. We employ an autoregressive encoder-decoder architecture and train it with policy gradient algorithms that incorporate a specially designed baseline. Experiments show that EGAM matches or outperforms existing methods across various routing problems. Notably, the proposed model demonstrates exceptional performance on highly constrained problems, highlighting its efficiency in handling complex graph structures.