Satellite Communication (SatCom) networks represent a fundamental pillar in modern global connectivity, facilitating reliable service and extensive coverage across a plethora of applications. The expanding demand for high-bandwidth services and the proliferation of mega satellite constellations highlight the limitations of traditional exclusive satellite spectrum allocation approaches. Cognitive Radio (CR) leading to Cognitive Satellite (CogSat) networks through Dynamic Spectrum Management (DSM), which enables the dynamic adaptability of radio equipment to environmental conditions for optimal performance, presents a promising solution for the emerging spectrum scarcity. In this survey, we explore the adaptation of intelligent DSM methodologies to SatCom, leveraging satellite network integrations. We discuss contributions and hurdles in regulations and standardizations in realizing intelligent DSM in SatCom, and deep dive into DSM techniques, which enable CogSat networks. Furthermore, we extensively evaluate and categorize state-of-the-art Artificial Intelligence (AI)/Machine Learning (ML) methods leveraged for DSM while exploring operational resilience and robustness of such integrations. In addition, performance evaluation metrics critical for adaptive resource management and system optimization in CogSat networks are thoroughly investigated. This survey also identifies open challenges and outlines future research directions in regulatory frameworks, network architectures, and intelligent spectrum management, paving the way for sustainable and scalable SatCom networks for enhanced global connectivity.

In this work, we present a language-guided generative vision system for remnant contour detection in manufacturing, designed to achieve CADlevel precision. The system is organized into three phases: (1) data preprocessing, (2) contour generation using a conditional GAN, and (3) multimodal contour refinement through vision-language modeling, where standardized prompts are crafted in a human-in-the-loop process and applied through image-text guided synthesis. On proprietary FabTrack datasets, the proposed system improved contour fidelity, enhancing edge continuity and geometric alignment while reducing manual tracing. For the refinement phase, we bench-marked several VLMs, including Google's Gemini 2.0 Flash, OpenAI's GPT-image-1 integrated within a VLM-guided workflow, and open-source baselines. Under standardized conditions, GPT-image-1 consistently outperformed Gemini 2.0 Flash in both structural accuracy and perceptual quality. These findings demonstrate the promise of VLM-guided generative workflows for advancing industrial CV beyond the limitations of classical pipelines and moving contour detection closer to CAD-level precision.

Tensor decomposition (TD) is essential for analyzing high-dimensional sparse data, yet its irregular computations and memory-access patterns pose major performance challenges on modern parallel processors. Prior works rely on expert-designed sparse tensor formats that fail to adapt to irregular tensor shapes and/or highly variable data distributions. We present the reinforcement-learned adaptive tensor encoding (ReLATE) framework, a novel learning-augmented method that automatically constructs efficient sparse tensor representations without labeled training samples. ReLATE employs an autonomous agent that discovers optimized tensor encodings through direct interaction with the TD environment, leveraging a hybrid model-free and model-based algorithm to learn from both real and imagined actions. Moreover, ReLATE introduces rule-driven action masking and dynamics-informed action filtering mechanisms that ensure functionally correct tensor encoding with bounded execution time, even during early learning stages. By automatically adapting to both irregular tensor shapes and data distributions, ReLATE generates sparse tensor representations that consistently outperform expert-designed formats across diverse sparse tensor data sets, achieving up to 2X speedup compared to the best sparse format, with a geometric-mean speedup of 1.4-1.46X.

Long-range time series forecasting remains challenging, as it requires capturing non-stationary and multi-scale temporal dependencies while maintaining noise robustness, efficiency, and stability. Transformer-based architectures such as Autoformer and Informer improve generalization but suffer from quadratic complexity and degraded performance on very long time horizons. State space models, notably S-Mamba, provide linear-time updates but often face unstable training dynamics, sensitivity to initialization, and limited robustness for multivariate forecasting. To address such challenges, we propose the Quantum-Optimized Selective State Space Model (Q-SSM), a hybrid quantum-optimized approach that integrates state space dynamics with a variational quantum gate. Instead of relying on expensive attention mechanisms, Q-SSM employs a simple parametrized quantum circuit (RY-RX ansatz) whose expectation values regulate memory updates adaptively. This quantum gating mechanism improves convergence stability, enhances the modeling of long-term dependencies, and provides a lightweight alternative to attention. We empirically validate Q-SSM on three widely used benchmarks, i.e., ETT, Traffic, and Exchange Rate. Results show that Q-SSM consistently improves over strong baselines (LSTM, TCN, Reformer), Transformer-based models, and S-Mamba. These findings demonstrate that variational quantum gating can address current limitations in long-range forecasting, leading to accurate and robust multivariate predictions.

Distributed LLM inference requires careful coordination of parallelization strategies across hundreds to thousands of NPUs to meet production SLOs. Current systems like Megatron-LM rely on static heuristics that separately configure parallelism degrees and per-operator sharding dimensions, leaving significant performance on the table as models scale and hardware topologies diversify. We introduce Learn to Shard, to our knowledge, the first RL-based approach to co-optimize both coarse-grained parallelism degrees and fine-grained per-operator sharding dimensions for distributed LLM inference. Our method employs an attention-based policy over an elite history that learns from high-performing strategies to efficiently navigate the vast combinatorial search space. Evaluated on H100 clusters with MoE models up to 1.6T parameters, Learn to Shard achieves up to 3.5x throughput improvement over metaheuristic baselines and 1.06x over Megatron heuristics.

Achieving human-like reasoning in deep learning models for complex tasks in unknown environments remains a critical challenge in embodied intelligence. While advanced vision-language models (VLMs) excel in static scene understanding, their limitations in spatio-temporal reasoning and adaptation to dynamic, open-set tasks like task-oriented navigation and embodied question answering (EQA) persist due to inadequate modeling of fine-grained spatio-temporal cues and physical world comprehension. To address this, we propose VEME, a novel cross-modal alignment method that enhances generalization in unseen scenes by learning an ego-centric, experience-centered world model. Our framework integrates three key components: (1) a cross-modal alignment framework bridging objects, spatial representations, and visual semantics with spatio-temporal cues to enhance VLM in-context learning; (2) a dynamic, implicit cognitive map activated by world embedding to enable task-relevant geometric-semantic memory recall; and (3) an instruction-based navigation and reasoning framework leveraging embodied priors for long-term planning and efficient exploration. By embedding geometry-aware spatio-temporal episodic experiences, our method significantly improves reasoning and planning in dynamic environments. Experimental results on VSI-Bench and VLN-CE demonstrate 1%-3% accuracy and exploration efficiency improvement compared to traditional approaches.

Solving elliptic partial differential equations (PDEs) is a fundamental step in various scientific and engineering studies. As a classic stochastic solver, the Walk-on-Spheres (WoS) method is a well-established and efficient algorithm that provides accurate local estimates for PDEs. In this paper, by integrating machine learning techniques with WoS and space discretization approaches, we develop a novel stochastic solver, WoS-NN. This new method solves elliptic problems with Dirichlet boundary conditions, facilitating precise and rapid global solutions and gradient approximations. The method inherits excellent characteristics from the original WoS method, such as being meshless and robust to irregular regions. By integrating neural networks, WoS-NN also gives instant local predictions after training without re-sampling, which is especially suitable for intense requests on a static region. A typical experimental result demonstrates that the proposed WoS-NN method provides accurate field estimations, reducing errors by around $75\%$ while using only $8\%$ of path samples compared to the conventional WoS method, which saves abundant computational time and resource consumption.

Deploying agentic AI on edge devices is crucial for privacy and responsiveness, but memory constraints typically relegate these systems to smaller Large Language Models (LLMs) with inferior reasoning capabilities. Test-Time Scaling (TTS) can bridge this reasoning gap by dedicating more compute during inference, but existing methods incur prohibitive overhead on edge hardware. To overcome this, we introduce FlashTTS, a serving system that makes TTS practical for memory-constrained LLM reasoning. FlashTTS introduces three synergistic optimizations: (i) Speculative Beam Extension to mitigate system stragglers from irregular reasoning paths; (ii) Asymmetric Multi-Model Memory Allocation to dynamically balance memory between generation and verification; and (iii) Dynamic Prefix-Aware Scheduling to maximize KV-cache reuse. Built as a plug-and-play library for vLLM, FlashTTS enables edge LLMs on a single consumer GPU (24 GB) to match the accuracy and latency of large cloud models. Our evaluation demonstrates that FlashTTS achieves an average 2.2x higher goodput and reduces latency by 38%-68% compared to a vLLM baseline, paving the way for democratized, high-performance agentic AI on edge devices.

Recent advancements in Large Language Models (LLMs) have paved the way for Vision Large Language Models (VLLMs) capable of performing a wide range of visual understanding tasks. While LLMs have demonstrated impressive performance on standard natural images, their capabilities have not been thoroughly explored in cluttered datasets where there is complex environment having deformed shaped objects. In this work, we introduce a novel dataset specifically designed for waste classification in real-world scenarios, characterized by complex environments and deformed shaped objects. Along with this dataset, we present an in-depth evaluation approach to rigorously assess the robustness and accuracy of VLLMs. The introduced dataset and comprehensive analysis provide valuable insights into the performance of VLLMs under challenging conditions. Our findings highlight the critical need for further advancements in VLLM's robustness to perform better in complex environments. The dataset and code for our experiments will be made publicly available.

The rapid growth of statutory corpora and judicial decisions requires scalable legal AI systems capable of classification and retrieval over extremely long contexts. Transformer-based architectures (e.g., Longformer, DeBERTa) dominate current legal NLP benchmarks but struggle with quadratic attention costs, limiting efficiency and scalability. In this work, we present the first comprehensive benchmarking of Mamba, a state-space model (SSM) with linear-time selective mechanisms, against leading transformer models for statutory classification and case law retrieval. We evaluate models on open-source legal corpora including LexGLUE, EUR-Lex, and ILDC, covering statutory tagging, judicial outcome prediction, and case retrieval tasks. Metrics include accuracy, recall at k, mean reciprocal rank (MRR), and normalized discounted cumulative gain (nDCG), alongside throughput measured in tokens per second and maximum context length. Results show that Mamba's linear scaling enables processing of legal documents several times longer than transformers, while maintaining or surpassing retrieval and classification performance. This study introduces a new legal NLP benchmark suite for long-context modeling, along with open-source code and datasets to support reproducibility. Our findings highlight trade-offs between state-space models and transformers, providing guidance for deploying scalable legal AI in statutory analysis, judicial decision support, and policy research.