Search

The generation of spin-orbital currents is crucial for advancing energy-efficient spintronic devices. Here, the intricate process involved in the generation and conversion of spin and orbital to charge currents in Zr(t=2, 3, 4.5, 6, &10nm)/Co60Fe20B20(CFB), Zr/Pt/CFB, and Zr/Pt/CFB/Pt heterostructures are investigated using spin-orbital pumping ferromagnetic resonance and longitudinal spin-orbital Seebeck effect measurements. The moderate spin-orbit coupling (SOC) in the CFB layer facilitates the simultaneous generation of spin and orbital currents, which are transferred into adjacent Zr and Pt layers. Different spin-orbital to charge current contributions, namely, Inverse spin Hall effect (ISHE), Inverse orbital Hall effect (IOHE), and Inverse orbital Rashba-Edelstein effect (IOREE) are analyzed. Notably, introducing a single Pt layer increases the spin-orbital to charge current conversion via combined effects: ISHE in Pt, IOREE in Zr/Pt interface. An enhanced effective spin-orbital Hall angle ({\theta}_eff) of 0.120 {\pm} 0.004 is observed for Zr/Pt/CFB, compared to that of 0.065 {\pm} 0.002 for the Zr/CFB, and 0.077 {\pm} 0.003 for the Zr/Pt/CFB/Pt heterostructures. These findings provide new insights into orbital-moment dependent phenomena and offer promising avenues for developing advanced spintronic devices exploiting both spin and orbital degrees of freedom, even in materials with lower SOC., Comment: 21 pages, 5 figures

In this chapter, we introduce two interval observer designs for discrete-time (DT) and continuous-time (CT) nonlinear systems with bounded Jacobians that are affected by bounded uncertainties. Our proposed methods utilize the concepts of mixed-monotone decomposition and embedding systems to design correct-by-construction interval framers, i.e., the interval framers inherently bound the true state of the system without needing any additional constraints. Further, our methods leverage techniques for positive/cooperative systems to guarantee global uniform ultimate boundedness of the framer error, i.e., the proposed interval observer is input-to-state stable. Specifically, our two interval observer designs minimize the $\mathcal{H}_{\infty}$ and $L_1$ gains, respectively, of the associated linear comparison system of the framer error dynamics. Moreover, our designs adopt a multiple-gain observer structure, which offers additional degrees of freedom, along with coordinate transformations that may improve the feasibility of the resulting optimization programs. We will also discuss and propose computationally tractable optimization formulations to compute the observer gains. Finally, we compare the efficacy of the proposed designs against existing DT and CT interval observers., Comment: Submitted to Springer as a book chapter

Generative Artificial Intelligence (GenAI) is a field of AI that creates new data samples from existing ones. It utilizing deep learning to overcome the scarcity and regulatory constraints of healthcare data by generating new data points that integrate seamlessly with original datasets. This paper explores the background and motivation for GenAI, and introduces the Generally Nuanced Deep Learning Framework for Synthesis (GaNDLF-Synth) to address a significant gap in the literature and move towards democratizing the implementation and assessment of image synthesis tasks in healthcare. GaNDLF-Synth describes a unified abstraction for various synthesis algorithms, including autoencoders, generative adversarial networks, and diffusion models. Leveraging the GANDLF-core framework, it supports diverse data modalities and distributed computing, ensuring scalability and reproducibility through extensive unit testing. The aim of GaNDLF-Synth is to lower the entry barrier for GenAI, and make it more accessible and extensible by the wider scientific community.

Non-classical features of quantum systems can degrade when subjected to environment and noise. Here, we ask a fundamental question: What is the minimum amount of time it takes for a quantum system to exhibit non-classical features in the presence of noise? Here, we prove distinct speed limits on the quantumness of observable as the norm of the commutator of two given observables. The speed limit on such quantumness measures sets the fundamental upper bound on the rate of change of quantumness, which provides the lower bound on the time required to change the quantumness of a system by a given amount. Additionally, we have proved speed limit for the non-classical features such as quantum coherence that captures the amount of superposition in the quantum systems. We have demonstrated that obtained speed limits are attainable for physical processes of interest, and hence, these bounds can be considered to be tight., Comment: Latex, 11 Pages, 3 Figs

Quantum coherence, a fundamental resource in quantum computing and quantum information, often competes with localization effects that affects quantum states in disordered systems. In this work, we prove exact trade-off relations between quantum coherence and a measure of localization and many-body localization, namely, the inverse participation ratio (IPR).We prove that for a pure quantum state, l1-norm of quantum coherence and the relative entropy of coherence satisfy complementarity relations with IPR. For a mixed state, IPR and the l2-norm of quantum coherence as well as relative entropy of coherence satisfy trade-off inequalities. These relations suggest that quantum coherence, in disordered quantum systems is also an ideal characterization of the delocalisation to many-body localisation transition, much like IPR, which is a well-known diagnostic of MBL. These relations also provide insight into the unusual properties of bipartite entanglement entropy across the MBL transition. We believe that these trade-off relations can help in better understanding of how coherence can be preserved or lost in realistic many-body quantum systems, which is vital for developing robust quantum technologies and uncovering new phases of quantum matter., Comment: 6 pages, 1 figure+Supplementary Material

Modern accelerators like GPUs are increasingly executing independent operations concurrently to improve the device's compute utilization. However, effectively harnessing it on GPUs for important primitives such as general matrix multiplications (GEMMs) remains challenging. Although modern GPUs have significant hardware and software support for GEMMs, their kernel implementations and optimizations typically assume each kernel executes in isolation and can utilize all GPU resources. This approach is highly efficient when kernels execute in isolation, but causes significant resource contention and slowdowns when kernels execute concurrently. Moreover, current approaches often only statically expose and control parallelism within an application, without considering runtime information such as varying input size and concurrent applications -- often exacerbating contention. These issues limit performance benefits from concurrently executing independent operations. Accordingly, we propose GOLDYLOC, which considers the global resources across all concurrent operations to identify performant GEMM kernels, which we call globally optimized (GO)-Kernels. Moreover, GOLDYLOC introduces a lightweight dynamic logic which considers the dynamic execution environment for available parallelism and input sizes to execute performant combinations of concurrent GEMMs on the GPU. Overall, GOLDYLOC improves performance of concurrent GEMMs on a real GPU by up to 2$\times$ (18% geomean per workload) and provides up to 2.5$\times$ (43% geomean per workload) speedups over sequential execution.

Pediatric central nervous system tumors are the leading cause of cancer-related deaths in children. The five-year survival rate for high-grade glioma in children is less than 20%. The development of new treatments is dependent upon multi-institutional collaborative clinical trials requiring reproducible and accurate centralized response assessment. We present the results of the BraTS-PEDs 2023 challenge, the first Brain Tumor Segmentation (BraTS) challenge focused on pediatric brain tumors. This challenge utilized data acquired from multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. BraTS-PEDs 2023 aimed to evaluate volumetric segmentation algorithms for pediatric brain gliomas from magnetic resonance imaging using standardized quantitative performance evaluation metrics employed across the BraTS 2023 challenges. The top-performing AI approaches for pediatric tumor analysis included ensembles of nnU-Net and Swin UNETR, Auto3DSeg, or nnU-Net with a self-supervised framework. The BraTSPEDs 2023 challenge fostered collaboration between clinicians (neuro-oncologists, neuroradiologists) and AI/imaging scientists, promoting faster data sharing and the development of automated volumetric analysis techniques. These advancements could significantly benefit clinical trials and improve the care of children with brain tumors.

In this work, we study cosmological spacetime configurations in f(Q) gravity with nonvanishing symmetric teleparallel connections. It is known that the spatially flat, homogeneous and isotropic connections can be classified into three sets. Focusing on two of those, we explore the stability of cosmological background evolution near the general relativity regime across radiation, matter, dark energy, and geometric dark energy dominated eras. Our results show that for the standard connection set 1 the general relativity regime can be realized in two ways and both exhibit stable behavior throughout all evolutionary epochs. Conversely, for the alternative connection set 2 the trivial general relativity limit is stable, while the nontrivial option exhibits stability during the radiation era and marginal stability during the matter era, but for the dark energy and geometric dark energy eras our results are inconclusive. Furthermore, we discuss the general conditions on the function f(Q) that physically viable models should obey, and point out that for a generic f(Q) the alternative connection sets 2 and 3 are prone to trigger a sudden singularity. This can happen even near the otherwise good looking general relativity regime, as we demonstrate by an explicit numerical example. Hence the alternative configurations could be problematic already on the background level., Comment: 25 pages, 2 figures

Given the initial and final states of a quantum system, the speed of transportation of state vector in the projective Hilbert space governs the quantum speed limit. Here, we ask the question what happens to the quantum speed limit under continuous measurement process. We model the continuous measurement process by a non-Hermitian Hamiltonian which keeps the evolution of the system Schr{\"o}dinger-like even under the process of measurement. Using this specific measurement model, we prove that under continuous measurement, the speed of transportation of a quantum system tends to zero. Interestingly, we also find that for small time scale, there is an enhancement of quantum speed even if the measurement strength is finite. Our findings can have applications in quantum computing and quantum control where dynamics is governed by both unitary and measurement processes., Comment: 7 pages, 3 figures. Comments are welcome

Traditional quantum speed limits formulated in density matrix space perform poorly for dynamics beyond unitary, as they are generally unattainable and fail to characterize the fastest possible dynamics. To address this, we derive two distinct quantum speed limits in Liouville space for Completely Positive and Trace-Preserving (CPTP) dynamics that outperform previous bounds. The first bound saturates for time-optimal CPTP dynamics, while the second bound is exact for all states and all CPTP dynamics. Our bounds have a clear physical and geometric interpretation arising from the uncertainty of superoperators and the geometry of quantum evolution in Liouville space. They can be regarded as the generalization of the Mandelstam-Tamm bound, providing uncertainty relations between time, energy, and dissipation for open quantum dynamics. Additionally, our bounds are significantly simpler to estimate and experimentally more feasible as they require to compute or measure the overlap of density matrices and the variance of the Liouvillian. We have also obtained the form of the Liouvillian, which generates the time-optimal (fastest) CPTP dynamics for given initial and final states. We give two important applications of our bounds. First, we show that the speed of evolution in Liouville space bounds the growth of the spectral form factor and Krylov complexity of states, which are crucial for studying information scrambling and quantum chaos. Second, using our bounds, we explain the Mpemba effect in non-equilibrium open quantum dynamics., Comment: 6+13 pages and 1 Figure. Comments are welcome

The 2024 Brain Tumor Segmentation Meningioma Radiotherapy (BraTS-MEN-RT) challenge aims to advance automated segmentation algorithms using the largest known multi-institutional dataset of radiotherapy planning brain MRIs with expert-annotated target labels for patients with intact or postoperative meningioma that underwent either conventional external beam radiotherapy or stereotactic radiosurgery. Each case includes a defaced 3D post-contrast T1-weighted radiotherapy planning MRI in its native acquisition space, accompanied by a single-label "target volume" representing the gross tumor volume (GTV) and any at-risk postoperative site. Target volume annotations adhere to established radiotherapy planning protocols, ensuring consistency across cases and institutions. For preoperative meningiomas, the target volume encompasses the entire GTV and associated nodular dural tail, while for postoperative cases, it includes at-risk resection cavity margins as determined by the treating institution. Case annotations were reviewed and approved by expert neuroradiologists and radiation oncologists. Participating teams will develop, containerize, and evaluate automated segmentation models using this comprehensive dataset. Model performance will be assessed using an adapted lesion-wise Dice Similarity Coefficient and the 95% Hausdorff distance. The top-performing teams will be recognized at the Medical Image Computing and Computer Assisted Intervention Conference in October 2024. BraTS-MEN-RT is expected to significantly advance automated radiotherapy planning by enabling precise tumor segmentation and facilitating tailored treatment, ultimately improving patient outcomes., Comment: 14 pages, 9 figures, 1 table

Glioblastoma is the most common primary adult brain tumor, with a grim prognosis - median survival of 12-18 months following treatment, and 4 months otherwise. Glioblastoma is widely infiltrative in the cerebral hemispheres and well-defined by heterogeneous molecular and micro-environmental histopathologic profiles, which pose a major obstacle in treatment. Correctly diagnosing these tumors and assessing their heterogeneity is crucial for choosing the precise treatment and potentially enhancing patient survival rates. In the gold-standard histopathology-based approach to tumor diagnosis, detecting various morpho-pathological features of distinct histology throughout digitized tissue sections is crucial. Such "features" include the presence of cellular tumor, geographic necrosis, pseudopalisading necrosis, areas abundant in microvascular proliferation, infiltration into the cortex, wide extension in subcortical white matter, leptomeningeal infiltration, regions dense with macrophages, and the presence of perivascular or scattered lymphocytes. With these features in mind and building upon the main aim of the BraTS Cluster of Challenges https://www.synapse.org/brats2024, the goal of the BraTS-Path challenge is to provide a systematically prepared comprehensive dataset and a benchmarking environment to develop and fairly compare deep-learning models capable of identifying tumor sub-regions of distinct histologic profile. These models aim to further our understanding of the disease and assist in the diagnosis and grading of conditions in a consistent manner.

We describe the design and results from the BraTS 2023 Intracranial Meningioma Segmentation Challenge. The BraTS Meningioma Challenge differed from prior BraTS Glioma challenges in that it focused on meningiomas, which are typically benign extra-axial tumors with diverse radiologic and anatomical presentation and a propensity for multiplicity. Nine participating teams each developed deep-learning automated segmentation models using image data from the largest multi-institutional systematically expert annotated multilabel multi-sequence meningioma MRI dataset to date, which included 1000 training set cases, 141 validation set cases, and 283 hidden test set cases. Each case included T2, T2/FLAIR, T1, and T1Gd brain MRI sequences with associated tumor compartment labels delineating enhancing tumor, non-enhancing tumor, and surrounding non-enhancing T2/FLAIR hyperintensity. Participant automated segmentation models were evaluated and ranked based on a scoring system evaluating lesion-wise metrics including dice similarity coefficient (DSC) and 95% Hausdorff Distance. The top ranked team had a lesion-wise median dice similarity coefficient (DSC) of 0.976, 0.976, and 0.964 for enhancing tumor, tumor core, and whole tumor, respectively and a corresponding average DSC of 0.899, 0.904, and 0.871, respectively. These results serve as state-of-the-art benchmarks for future pre-operative meningioma automated segmentation algorithms. Additionally, we found that 1286 of 1424 cases (90.3%) had at least 1 compartment voxel abutting the edge of the skull-stripped image edge, which requires further investigation into optimal pre-processing face anonymization steps., Comment: 16 pages, 11 tables, 10 figures, MICCAI

The rapid advancement of machine learning techniques has led to their widespread application in various domains including water resources. However, snowmelt modeling remains an area that has not been extensively explored. In this study, we propose a state-of-the-art (SOTA) deep learning sequential model, leveraging the Temporal Convolutional Network (TCN), for snowmelt-driven discharge modeling in the Himalayan basin of the Hindu Kush Himalayan Region. To evaluate the performance of our proposed model, we conducted a comparative analysis with other popular models including Support Vector Regression (SVR), Long Short Term Memory (LSTM), and Transformer. Furthermore, Nested cross-validation (CV) is used with five outer folds and three inner folds, and hyper-parameter tuning is performed on the inner folds. To evaluate the performance of the model mean absolute error (MAE), root mean square error (RMSE), R square ($R^{2}$), Kling-Gupta Efficiency (KGE), and Nash-Sutcliffe Efficiency (NSE) are computed for each outer fold. The average metrics revealed that TCN outperformed the other models, with an average MAE of 0.011, RMSE of 0.023, $R^{2}$ of 0.991, KGE of 0.992, and NSE of 0.991. The findings of this study demonstrate the effectiveness of the deep learning model as compared to traditional machine learning approaches for snowmelt-driven streamflow forecasting. Moreover, the superior performance of TCN highlights its potential as a promising deep learning model for similar hydrological applications., Comment: 17 pages, 4 Tables, 7 figures

We report the electrochemical sodium-ion kiinetics and distribution of relaxation time (DRT) analysis of a newly designed mixed polyanionic NaFe$_{1.6}$V$_{0.4}$(PO$_{4}$)(SO$_{4}$)$_{2}$@CNT composite as a cathode. The specific capacity of 104 mAhg$^{-1}$ is observed at 0.1~C with the average working voltage of $\sim$3~V. Intriguingly, a remarkable rate capability and reversibility are demonstrated up to very high current rate of 25~C. The long cycling test up to 10~C shows high capacity retention even after 2000 cycles. The detailed analysis of galvanostatic intermittent titration technique (GITT) and cyclic voltammetry (CV) data reveal the diffusion coefficient of 10$^{-8}$--10$^{-11}$ cm$^{2}$s$^{-1}$. We find excellent stability in the thermal testing between 25--55$^\circ$C temperatures and 80\% capacity retention up to 100 cycles at 5~C. Further, we analyse the individual electrochemical processes in the time domain using the novel DRT technique at different temperatures. The {\it ex-situ} investigation shows the stable and reversible structure, morphology and electronic states of the long cycled cathode material. More importantly, we demonstrate relatively high specific energy of $\approx$155 Wh kg$^{-1}$ (considering the total active material loading of both the electrodes) at 0.2~C for full cell battery having excellent rate capability up to 10~C and long cyclic stability at 1~C., Comment: submitted

How fast an observable can evolve in time is answered by so-called the observable speed limit. Here, we prove a stronger version of the observable speed limit and show that the previously obtained bound is a special case of the new bound. The stronger quantum speed limit for the state also follows from the stronger quantum speed limit for observables (SQSLO). We apply this to prove a stronger bound for the entanglement rate using the notion of capacity of entanglement (the quantum information theoretic counterpart of the heat capacity) and show that it outperforms previous bounds. Furthermore, we apply the SQSLO for the rate of modular Hamiltonian and in the context of interacting qubits in a quantum battery. These illustrative examples reveal that the speed limit for the modular energy and the time required to charge the battery can be exactly predicted using the new bound. This shows that for estimating the charging time of quantum battery SQSLO is actually tight, i.e., it saturates. Our findings can have important applications in quantum thermodynamics, the complexity of operator growth, predicting the time rate of quantum correlation growth and quantum technology, in general.

Text continues to remain a relevant form of representation for information. Text documents are created either in digital native platforms or through the conversion of other media files such as images and speech. While the digital native text is invariably obtained through physical or virtual keyboards, technologies such as OCR and speech recognition are utilized to transform the images and speech signals into text content. All these variety of mechanisms of text generation also introduce errors into the captured text. This project aims at analyzing different kinds of error that occurs in text documents. The work employs two of the advanced deep neural network-based language models, namely, BART and MarianMT, to rectify the anomalies present in the text. Transfer learning of these models with available dataset is performed to finetune their capacity for error correction. A comparative study is conducted to investigate the effectiveness of these models in handling each of the defined error categories. It is observed that while both models can bring down the erroneous sentences by 20+%, BART can handle spelling errors far better (24.6%) than grammatical errors (8.8%).

Cyber-physical and autonomous systems are often equipped with mechanisms that provide predictions/projections of future disturbances, e.g., road curvatures, commonly referred to as preview or lookahead, but this preview information is typically not leveraged in the context of deriving control barrier functions (CBFs) for safety. This paper proposes a novel limited preview control barrier function (LPrev-CBF) that avoids both ends of the spectrum, where on one end, the standard CBF approach treats the (previewable) disturbances simply as worst-case adversarial signals and on the other end, a recent Prev-CBF approach assumes that the disturbances are previewable and known for the entire future. Moreover, our approach applies to input-delay systems and has recursive feasibility guarantees since we explicitly take input constraints/bounds into consideration. Thus, our approach provides strong safety guarantees in a less conservative manner than standard CBF approaches while considering a more realistic setting with limited preview and input delays., Comment: 8 Pages, 3 figures. This paper was submitted and accepted to the American Controls Conference 2024, we are in the process of final manuscript submission to ACC after addressing the reviewers. In this Arxiv version of the paper, most of the comments from ACC reviewers have been addressed

Large Language Models increasingly rely on distributed techniques for their training and inference. These techniques require communication across devices which can reduce scaling efficiency as the number of devices increases. While some distributed techniques can overlap, and thus, hide this communication with independent computations, techniques such as Tensor Parallelism (TP) inherently serialize communication with model execution. One approach to hide this serialized communication is to interleave it with the producer operation (of the communicated data) in a fine-grained manner. However, this fine-grained interleaving of communication and computation in software can be difficult. Furthermore, as with any concurrent execution, it requires compute and memory resources to be shared between computation and communication, causing resource contention that reduces overlapping efficacy. To overcome these challenges, we propose T3 which applies hardware-software co-design to transparently overlap serialized communication while minimizing resource contention with compute. T3 transparently fuses producer operations with the subsequent communication via a simple configuration of the producer's output address space and requires minor software changes. At the hardware level, T3 adds a lightweight track and trigger mechanism to orchestrate the producer's compute, and communication. It further uses compute-enhanced memories for communication's attendant compute. As a result, T3 reduces resource contention, and efficiently overlaps serialized communication with computation. For important Transformer models like T-NLG, T3 speeds up communication-heavy sublayers by 30% geomean (max 47%) and reduces data movement by 22% geomean (max 36%). Furthermore, T3's benefits persist as models scale: geomean 29% for sublayers in $\sim$500-billion parameter models, PALM and MT-NLG., Comment: To appear at the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2024

Grover's quantum search algorithm promises a quadratic speedup for unstructured search over its classical counterpart. But this advantage is gradually reduced with noise acting on the search space. In this article, we demonstrate that a quantum switch can act as a resource operation in mitigating the effect of the noise in the search space. In this scenario, fault-tolerant model quantum computing is costly. In addition to the noise modeled by a depolarizing channel, which coherently acts on the entire quantum register, such an error correction method can not be trivially implemented. We show that a quantum switch can significantly add value by reducing this error. In particular, we propose two frameworks for the application of switches. In the first framework, we apply the superposition of channels' orders in the form of a switch and do a post-selection at every iteration of the applications of the Grover operator. In the second framework, we delay the post-selection until the very end. In other words, if we want to look at the switch's action at the kth step, we already have k-1 post-selection measurements in place for the first framework. In the second case, we only have a single measurement. The number of post selections is minimal in the second scenario, so its effect is more credited to the switch. It also gives a significant advantage regarding the success probability of Grover's algorithm. We take the success probability as the sole quantifier of the switch's action in diminishing the effect of noise in search space., Comment: 26 pages (14 + 12), 7 figures

Quantum machine learning with quantum kernels for classification problems is a growing area of research. Recently, quantum kernel alignment techniques that parameterise the kernel have been developed, allowing the kernel to be trained and therefore aligned with a specific dataset. While quantum kernel alignment is a promising technique, it has been hampered by considerable training costs because the full kernel matrix must be constructed at every training iteration. Addressing this challenge, we introduce a novel method that seeks to balance efficiency and performance. We present a sub-sampling training approach that uses a subset of the kernel matrix at each training step, thereby reducing the overall computational cost of the training. In this work, we apply the sub-sampling method to synthetic datasets and a real-world breast cancer dataset and demonstrate considerable reductions in the number of circuits required to train the quantum kernel while maintaining classification accuracy., Comment: Paper as accepted on Quantum on 2024-09-18. The method showcased in this work is also available as a Jupyter notebook at https://github.com/qiskit-community/qiskit-machine-learning/tree/IEEE2024

The notions of predictability and visibility are essential in the mathematical formulation of wave particle duality. The work of Jakob and Bergou [Phys. Rev. A 76, 052107] generalises these notions for higher-dimensional quantum systems, which were initially defined for qubits, and subsequently proves a complementarity relation between predictability and visibility. By defining the single-party information content of a quantum system as the addition of predictability and visibility, and assuming that entanglement in a bipartite system in the form of concurrence mutually excludes the single-party information, the authors have proposed a complementarity relation between the concurrence and the single-party information content. We show that the information content of a quantum system defined by Jakob and Bergou is nothing but the Hilbert-Schmidt distance between the state of the quantum system of our consideration and the maximally mixed state. Motivated by the fact that the trace distance is a good measure of distance as compared to the Hilbert-Schmidt distance from the information theoretic point of view, we, in this work, define the information content of a quantum system as the trace distance between the quantum state and the maximally mixed state. We then employ the quantum Pinsker's inequality and the reverse Pinsker's inequality to derive a new complementarity and a reverse complementarity relation between the single-party information content and the entanglement present in a bipartite quantum system in a pure state. As a consequence of our findings, we show that for a bipartite system in a pure state, its entanglement and the predictabilities and visibilities associated with the subsystems cannot be arbitrarily small as well as arbitrarily large., Comment: 9 pages, no figures

Introducing interpretability and reasoning into Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) analysis is challenging, given the complexity of gigapixel slides. Traditionally, MIL interpretability is limited to identifying salient regions deemed pertinent for downstream tasks, offering little insight to the end-user (pathologist) regarding the rationale behind these selections. To address this, we propose Self-Interpretable MIL (SI-MIL), a method intrinsically designed for interpretability from the very outset. SI-MIL employs a deep MIL framework to guide an interpretable branch grounded on handcrafted pathological features, facilitating linear predictions. Beyond identifying salient regions, SI-MIL uniquely provides feature-level interpretations rooted in pathological insights for WSIs. Notably, SI-MIL, with its linear prediction constraints, challenges the prevalent myth of an inevitable trade-off between model interpretability and performance, demonstrating competitive results compared to state-of-the-art methods on WSI-level prediction tasks across three cancer types. In addition, we thoroughly benchmark the local and global-interpretability of SI-MIL in terms of statistical analysis, a domain expert study, and desiderata of interpretability, namely, user-friendliness and faithfulness.