Recent advances in medical multi-modal models focus on specialized image analysis like dermatology, pathology, or radiology. However, they do not fully capture the complexity of real-world clinical diagnostics, which involve heterogeneous inputs and require ongoing contextual understanding during patient-physician interactions. To bridge this gap, we introduce PulseMind, a new family of multi-modal diagnostic models that integrates a systematically curated dataset, a comprehensive evaluation benchmark, and a tailored training framework. Specifically, we first construct a diagnostic dataset, MediScope, which comprises 98,000 real-world multi-turn consultations and 601,500 medical images, spanning over 10 major clinical departments and more than 200 sub-specialties. Then, to better reflect the requirements of real-world clinical diagnosis, we develop the PulseMind Benchmark, a multi-turn diagnostic consultation benchmark with a four-dimensional evaluation protocol comprising proactiveness, accuracy, usefulness, and language quality. Finally, we design a training framework tailored for multi-modal clinical diagnostics, centered around a core component named Comparison-based Reinforcement Policy Optimization (CRPO). Compared to absolute score rewards, CRPO uses relative preference signals from multi-dimensional comparisons to provide stable and human-aligned training guidance. Extensive experiments demonstrate that PulseMind achieves competitive performance on both the diagnostic consultation benchmark and public medical benchmarks.

Long-term network packet traces (e.g., pcaps), if available, can enable and inform lots of management tasks. However, storing packet data at scale is very expensive, forcing operators to choose between coarse historical summaries or short retention windows. In this context, deep generative compression (DGC) offers a new hope to store compact model parameters and regenerate structurally accurate traces on demand. We evaluate the suitability of recent deep generative approaches [21, 24] for packet trace modeling and generation. We find that their fidelity metrics are disconnected from the domain-specific queries/use cases, and they have bad cost-fidelity trade-off. We propose DeePCAP, an end-to-end trace storage system to close this gap. DeePCAP introduces a query-driven fidelity framework spanning packet- and flow-level queries to tackle the fidelity disconnection, and proposes a novel dimensionality reduction approach using frequency domain encoding to improve cost-fidelity trade-off. Our preliminary results show that DeePCAP achieves the best fidelity on the 100+ query suite and the strongest cost-fidelity trade-off.

Global Positioning System (GPS) signals, though critical to numerous civilian and industrial applications, remain susceptible to spoofing due to their unencrypted nature. While many existing defenses focus on single-antenna spoofing, multi-antenna spoofing has been theorized as a significantly more potent threat. However, practical realizations of multi-antenna spoofing have been limited by the stringent requirement of nanosecond-level synchronization.

Recently, much attention has been devoted to the development of generative network traces and their potential use in supplementing real-world data for a variety of data-driven networking tasks. Yet, the utility of existing synthetic traffic approaches are limited by their low fidelity: low feature granularity, insufficient adherence to task constraints, and subpar class coverage. As effective network tasks are increasingly reliant on raw packet captures, we advocate for a paradigm shift from coarse-grained to fine-grained traffic generation compliant to constraints. We explore this path employing controllable diffusion-based methods. Our preliminary results suggest its effectiveness in generating realistic and fine-grained network traces that mirror the complexity and variety of real network traffic required for accurate service recognition. We further outline the challenges and opportunities of this approach, and discuss a research agenda towards text-to-traffic synthesis.

Video crowd localization is a crucial yet challenging task, which aims to estimate exact locations of human heads in the given crowded videos. To model spatial-temporal dependencies of human mobility, we propose a multi-focus Gaussian neighborhood attention (GNA), which can effectively exploit long-range correspondences while maintaining the spatial topological structure of the input videos. In particular, our GNA can also capture the scale variation of human heads well using the equipped multi-focus mechanism. Based on the multi-focus GNA, we develop a unified neural network called GNANet to accurately locate head centers in video clips by fully aggregating spatial-temporal information via a scene modeling module and a context cross-attention module. Moreover, to facilitate future researches in this field, we introduce a large-scale crowd video benchmark named VSCrowd (https://github.com/HopLee6/VSCrowd), which consists of 60K+ frames captured in various surveillance scenes and 2M+ head annotations. Finally, we conduct extensive experiments on three datasets including our VSCrowd, and the experiment results show that the proposed method is capable to achieve state-of-the-art performance for both video crowd localization and counting.

Group activity recognition is a crucial yet challenging problem, whose core lies in fully exploring spatial-temporal interactions among individuals and generating reasonable group representations. However, previous methods either model spatial and temporal information separately, or directly aggregate individual features to form group features. To address these issues, we propose a novel group activity recognition network termed GroupFormer. It captures spatial-temporal contextual information jointly to augment the individual and group representations effectively with a clustered spatial-temporal transformer. Specifically, our GroupFormer has three appealing advantages: (1) A tailor-modified Transformer, Clustered Spatial-Temporal Transformer, is proposed to enhance the individual representation and group representation. (2) It models the spatial and temporal dependencies integrally and utilizes decoders to build the bridge between the spatial and temporal information. (3) A clustered attention mechanism is utilized to dynamically divide individuals into multiple clusters for better learning activity-aware semantic representations. Moreover, experimental results show that the proposed framework outperforms state-of-the-art methods on the Volleyball dataset and Collective Activity dataset. Code is available at https://github.com/xueyee/GroupFormer