Transformer architecture has become the fundamental element of the widespread natural language processing~(NLP) models. With the trends of large NLP models, the increasing memory and computation costs hinder their efficient deployment on resource-limited devices. Therefore, transformer quantization attracts wide research interest. Recent work recognizes that structured outliers are the critical bottleneck for quantization performance. However, their proposed methods increase the computation overhead and still leave the outliers there. To fundamentally address this problem, this paper delves into the inherent inducement and importance of the outliers. We discover that $\boldsymbol \gamma$ in LayerNorm (LN) acts as a sinful amplifier for the outliers, and the importance of outliers varies greatly where some outliers provided by a few tokens cover a large area but can be clipped sharply without negative impacts. Motivated by these findings, we propose an outlier suppression framework including two components: Gamma Migration and Token-Wise Clipping.

Time series forecasting is essential across diverse domains. While MLP-based methods have gained attention for achieving Transformer-comparable performance with fewer parameters and better robustness, they face critical limitations including loss of weak seasonal signals, capacity constraints in weight-sharing MLPs, and insufficient channel fusion in channel-independent strategies. To address these challenges, we propose MDMLP-EIA (Multi-domain Dynamic MLPs with Energy Invariant Attention) with three key innovations. First, we develop an adaptive fused dual-domain seasonal MLP that categorizes seasonal signals into strong and weak components. It employs an adaptive zero-initialized channel fusion strategy to minimize noise interference while effectively integrating predictions. Second, we introduce an energy invariant attention mechanism that adaptively focuses on different feature channels within trend and seasonal predictions across time steps. This mechanism maintains constant total signal energy to align with the decomposition-prediction-reconstruction framework and enhance robustness against disturbances. Third, we propose a dynamic capacity adjustment mechanism for channel-independent MLPs. This mechanism scales neuron count with the square root of channel count, ensuring sufficient capacity as channels increase. Extensive experiments across nine benchmark datasets demonstrate that MDMLP-EIA achieves state-of-the-art performance in both prediction accuracy and computational efficiency.

In recent years, the guitar has received increased attention from the music information retrieval (MIR) community driven by the challenges posed by its diverse playing techniques and sonic characteristics. Mainly fueled by deep learning approaches, progress has been limited by the scarcity and limited annotations of datasets. To address this, we present the Guitar On Audio and Tablatures (GOAT) dataset, comprising 5.9 hours of unique high-quality direct input audio recordings of electric guitars from a variety of different guitars and players. We also present an effective data augmentation strategy using guitar amplifiers which delivers near-unlimited tonal variety, of which we provide a starting 29.5 hours of audio. Each recording is annotated using guitar tablatures, a guitar-specific symbolic format supporting string and fret numbers, as well as numerous playing techniques. For this we utilise both the Guitar Pro format, a software for tablature playback and editing, and a text-like token encoding. Furthermore, we present competitive results using GOAT for MIDI transcription and preliminary results for a novel approach to automatic guitar tablature transcription. We hope that GOAT opens up the possibilities to train novel models on a wide variety of guitar-related MIR tasks, from synthesis to transcription to playing technique detection.

--Accurately predicting the performance of active radio frequency (RF) circuits is essential for modern wireless systems but remains challenging due to highly nonlinear, layout-sensitive behavior and the high computational cost of traditional simulation tools. Existing machine learning (ML) surrogates often require large datasets to generalize across various topologies or to accurately model skewed and multi-modal performance metrics. In this work, a lightweight, data-efficient, and topology-aware graph neural network (GNN) model is proposed for predicting key performance metrics of multiple topologies of active RF circuits such as low noise amplifiers (LNAs), mixers, voltage-controlled oscillators (VCOs), and PAs. T o capture transistor-level symmetry and preserve fine-grained connectivity details, circuits are modeled at the device-terminal level, enabling scalable message passing while reducing data requirements. Masked autoregressive flow (MAF) output heads are incorporated to improve robustness in modeling complex target distributions. Experiments on datasets demonstrate high prediction accuracy, with symmetric mean absolute percentage error (sMAPE) and mean relative error (MRE) averaging 2.40% and 2.91%, respectively. Owing to the pin-level conversion of circuit to graph and ML architecture robust to modeling complex densities of RF metrics, the MRE is improved by 3.14 while using 2.24 fewer training samples compared to prior work, demonstrating the method's effectiveness for rapid and accurate RF circuit design automation. Index T erms--Graph neural network (GNN), RF circuit modeling, masked autoregressive flow (MAF), electronic design automation (EDA), machine learning. With the growing importance of modern wireless systems (e.g., the Internet of Things [1], 5G [2] RADAR [3], and Li-DAR [4]) accurate modeling and optimization of RF integrated circuits (RFICs) is more critical than ever. The performance of key building blocks of such systems, ranging from power amplifiers (P A) to transmitters, directly affects the fidelity, efficiency, and robustness of modern systems. This work was supported in part by the CogniSense: Center on Cognitive Multi-spectral Sensors, one of seven centers in Joint University Microelectronics Program (JUMP) 2.0, a Semiconductor Research Corporation (SRC) program sponsored by the Defense Advance Research Project Agency (DARP A). While highly accurate, traditional simulators (e.g., SPICE, ADS, ANSYS) are computationally expensive, especially when sweeping process-voltage-temperature (PVT) corners or performing extensive design-space exploration.

Interest in miniature radar systems has grown dramatically in recent years as they enable rich interaction and health monitoring in everyday settings. By 2025, industrial radar applications are anticipated to encompass 10 million devices, whereas the consumer market will reach a substantial 250 million. The applications are diverse--for example, Google's Pixel phones incorporated radar for gesture control, while small radar sensors are being deployed in homes to monitor elderly residents' movements and detect falls, offering more privacy than camera-based solutions. However, conventional radar architectures rely on complex RF front ends with power amplifiers, low-noise amplifiers, and phase-locked loops, collectively consuming hundreds of milliwatts of power. This makes radar sensing impractical for battery-powered or self-powered Internet of Things (IoT) devices and wearables.

Understanding and interpreting the internal representations of large language models (LLMs) remains an open challenge. Patchscopes introduced a method for probing internal activations by patching them into new prompts, prompting models to self-explain their hidden representations. We introduce Superscopes, a technique that systematically amplifies superposed features in MLP outputs (multilayer perceptron) and hidden states before patching them into new contexts. Inspired by the "features as directions" perspective and the Classifier-Free Guidance (CFG) approach from diffusion models, Superscopes amplifies weak but meaningful features, enabling the interpretation of internal representations that previous methods failed to explain-all without requiring additional training. This approach provides new insights into how LLMs build context and represent complex concepts, further advancing mechanistic interpretability.

Self-mixing interferometry (SMI) has been lauded for its sensitivity in detecting microvibrations, while requiring no physical contact with its target. In robotics, microvibrations have traditionally been interpreted as a marker for object slip, and recently as a salient indicator of extrinsic contact. We present the first-ever robotic fingertip making use of SMI for slip and extrinsic contact sensing. The design is validated through measurement of controlled vibration sources, both before and after encasing the readout circuit in its fingertip package. Then, the SMI fingertip is compared to acoustic sensing through four experiments. The results are distilled into a technology decision map. SMI was found to be more sensitive to subtle slip events and significantly more resilient against ambient noise. We conclude that the integration of SMI in robotic fingertips offers a new, promising branch of tactile sensing in robotics. Design and data files are available at https://github.com/RemkoPr/icra2025-SMI-tactile-sensing.

Large language models (LLMs) have shown significant promise in question-answering (QA) tasks, particularly in retrieval-augmented generation (RAG) scenarios and long-context applications. However, their performance is hindered by noisy reference documents, which often distract from essential information. Despite fine-tuning efforts, Transformer-based architectures struggle to prioritize relevant content. This is evidenced by their tendency to allocate disproportionate attention to irrelevant or later-positioned documents. Recent work proposes the differential attention mechanism to address this issue, but this mechanism is limited by an unsuitable common-mode rejection ratio (CMRR) and high computational costs. Inspired by the operational amplifier (OpAmp), we propose the OpAmp adaptation to address these challenges, which is implemented with adapters efficiently. By integrating the adapter into pre-trained Transformer blocks, our approach enhances focus on the golden context without costly training from scratch. Empirical evaluations on noisy-context benchmarks reveal that our Qwen2.5-OpAmp-72B model, trained with our OpAmp adaptation, surpasses the performance of state-of-the-art LLMs, including DeepSeek-V3 and GPT-4o.

The design of analog circuits is a cornerstone of integrated circuit (IC) development, requiring the optimization of complex, interconnected sub-structures such as amplifiers, comparators, and buffers. Traditionally, this process relies heavily on expert human knowledge to refine design objectives by carefully tuning sub-components while accounting for their interdependencies. Existing methods, such as Bayesian Optimization (BO), offer a mathematically driven approach for efficiently navigating large design spaces. However, these methods fall short in two critical areas compared to human expertise: (i) they lack the semantic understanding of the sizing solution space and its direct correlation with design objectives before optimization, and (ii) they fail to reuse knowledge gained from optimizing similar sub-structures across different circuits. To overcome these limitations, we propose the Large Language Model-based Universal Sizing Optimizer (LLM-USO), which introduces a novel method for knowledge representation to encode circuit design knowledge in a structured text format. This representation enables the systematic reuse of optimization insights for circuits with similar sub-structures. LLM-USO employs a hybrid framework that integrates BO with large language models (LLMs) and a learning summary module. This approach serves to: (i) infuse domain-specific knowledge into the BO process and (ii) facilitate knowledge transfer across circuits, mirroring the cognitive strategies of expert designers. Specifically, LLM-USO constructs a knowledge summary mechanism to distill and apply design insights from one circuit to related ones. It also incorporates a knowledge summary critiquing mechanism to ensure the accuracy and quality of the summaries and employs BO-guided suggestion filtering to identify optimal design points efficiently.

We propose an energy amplification technique to address the issue that existing models easily overlook low-energy components in time series forecasting. This technique comprises an energy amplification block and an energy restoration block. The energy amplification block enhances the energy of low-energy components to improve the model's learning efficiency for these components, while the energy restoration block returns the energy to its original level. Moreover, considering that the energy-amplified data typically displays two distinct energy peaks in the frequency spectrum, we integrate the energy amplification technique with a seasonal-trend forecaster to model the temporal relationships of these two peaks independently, serving as the backbone for our proposed model, Amplifier. Additionally, we propose a semi-channel interaction temporal relationship enhancement block for Amplifier, which enhances the model's ability to capture temporal relationships from the perspective of the commonality and specificity of each channel in the data. Extensive experiments on eight time series forecasting benchmarks consistently demonstrate our model's superiority in both effectiveness and efficiency compared to state-of-the-art methods.