Related papers: Beamline Steering Using Deep Learning Models
Autonomous driving technology is progressing rapidly, largely due to complex End To End systems based on deep neural networks. While these systems are effective, their complexity can make it difficult to understand their behavior, raising…
Biases can filter into AI technology without our knowledge. Oftentimes, seminal deep learning networks champion increased accuracy above all else. In this paper, we attempt to alleviate biases encountered by semantic segmentation models in…
Light beams carrying orbital-angular-momentum (OAM) play an important role in optical manipulation and communication owing to their unbounded state space. However, it is still challenging to efficiently discriminate OAM modes with large…
In this paper, we propose BeamLLM, a vision-aided millimeter-wave (mmWave) beam prediction framework leveraging large language models (LLMs) to address the challenges of high training overhead and latency in mmWave communication systems. By…
This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…
Activation steering is a method for controlling Large Language Model (LLM) behavior by intervening in its internal representations to increase the alignment with a specific target feature direction. However, standard interventions, such as…
While vision models are highly capable, their internal mechanisms remain poorly understood -- a challenge which sparse autoencoders (SAEs) have helped address in language, but which remains underexplored in vision. We address this gap by…
In recent years, deep generative models have gained significance due to their ability to synthesize natural-looking images with applications ranging from virtual reality to data augmentation for training computer vision models. While…
This article investigates beam alignment for multi-user millimeter wave (mmWave) massive multi-input multi-output system. Unlike the existing works using machine learning (ML), an alignment method with partial beams using ML (AMPBML) is…
In the Large Hadron Collider, the beam losses are continuously measured for machine protection. By design, most of the particle losses occur in the collimation system, where the particles with high oscillation amplitudes or large momentum…
Controlling multiple behavioral attributes in large language models (LLMs) at inference time is a challenging problem due to interference between attributes and the limitations of linear steering methods, which assume additive behavior in…
The cerebellum plays a distinctive role within our motor control system to achieve fine and coordinated motions. While cerebellar lesions do not lead to a complete loss of motor functions, both action and perception are severally impacted.…
Alignment of the ILC main linac will be more critical than for any currently existing accelerators due to its long length and the ultra low emittance required. There are several techniques for measuring the ILC reference network; in this…
Benefiting from huge bandwidth resources, millimeter-wave (mmWave) communications provide one of the most promising technologies for next-generation wireless networks. To compensate for the high pathloss of mmWave signals, large-scale…
Semantic segmentation using deep neural networks has been widely explored to generate high-level contextual information for autonomous vehicles. To acquire a complete $180^\circ$ semantic understanding of the forward surroundings, we…
In this paper, we present a novel end-to-end deep neural network model for autonomous driving that takes monocular image sequence as input, and directly generates the steering control angle. Firstly, we model the end-to-end driving problem…
Large Language Models (LLMs) exhibit remarkable capabilities across various tasks, yet guiding them to follow desired behaviours during inference remains a significant challenge. Activation steering offers a promising method to control the…
Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a practical middle ground between prompting and fine-tuning. Yet SVs can be unreliable in…
These lectures aim to describe instruments and methods used for measuring beam parameters in particle accelerators. Emphasis will be given to new detection and analysis techniques in each field of accelerator instrumentation. A clear…
The Adam optimizer is a cornerstone of modern deep learning, yet the empirical necessity of each of its individual components is often taken for granted. This paper presents a focused investigation into the role of bias-correction, a…