How should we evaluate generation systems that combine autoregressive (AR) and diffusion decoding? We study this question through Speculative Refinement (SpecRef), a training-free hybrid method that warm-starts a masked diffusion language model from an AR draft using entropy-guided selective masking. Evaluating SpecRef across six benchmarks (HumanEval, MBPP, GSM8K, BBH, ARC-Challenge, HellaSwag) with three distinct evaluation protocols (execution-based pass@1, exact-match, log-likelihood scoring), we surface several findings relevant beyond our specific system: (1) code benchmarks conflate structural discovery with logical correctness: providing a syntactic scaffold lifts accuracy from near zero to over 20

Distributed training of large neural networks is bottlenecked by full-precision gradient communication and by coordinatewise optimizers that ignore the matrix structure of weight tensors. We propose Sign-Muon, a 1-bit, matrix-aware optimizer that combines majority-vote sign aggregation from signSGD with the polar-step framework of Muon. Each worker forms a Muon-style direction by taking the polar factor of its momentum via a Newton–Schulz iteration, transmits only the entrywise signs, and aggregates by majority vote; an optional local polar step further enforces orthogonality at no extra communication cost. Under spectral-norm smoothness and bounded-variance stochastic gradients, the spectral-norm normalized sign step yields an 𝒪(1/√(T)) nonconvex rate for an ℓ_1-based stationarity measure. With unimodal symmetric noise, majority vote across M workers cuts the stochastic term by 1/√(M), matching signSGD. In the α-β model, distributed Sign-Muon needs only one integer sum-allreduce per iteration; all orthogonalization is local, giving a 32× bandwidth reduction over float32 (4× for int8). Across 330 CIFAR-10/ResNet-50 configurations Sign-Muon attains the best validation accuracy (92.15%); its 4-GPU majority-vote variant reaches 92.02% with 37% less training time at matched effective batch. On nanoGPT, Sign-Muon achieves lower perplexity and better anytime performance than other sign-based baselines, with favorable weak-scaling up to 16 GPUs.

We present dLLM-SetScore, a training-free method that uses discrete masked-diffusion language models for multi-label text classification. For each candidate label, it asks a short yes/no question and compares the probabilities of the two answer tokens at one masked position. The method uses no task-specific fine-tuning or training on textual-entailment datasets; a 200-example labelled validation slice selects thresholds, temperature, and prompt wording. We first show that placing all labels in one prompt creates a strong slot-position asymmetry: the first answer slot is predicted positive on 99.4% of GoEmotions examples and 100% of Reuters examples. Per-label scoring places every label in the same syntactic position, making predictions invariant to label order and avoiding this artifact. We evaluate LLaDA-8B and Dream-7B on six datasets against NLI models, an autoregressive LLM, SetFit, and supervised classifiers. On the five datasets shared by both diffusion families, Instruct checkpoints improve macro-F1 in 9 of 10 comparisons and micro-F1 in 8 of 10, although these comparisons do not identify the cause. Within our protocol, LLaDA-Instruct records the highest training-free values for both Reuters and ECtHR metrics. We prove permutation invariance, characterize thresholded decisions under weighted Hamming loss, and derive shortlist ceilings for recall and F1. An exploratory local Joint Set Refinement step lowers F1 from biased and unbiased initializations and is retained as a negative result.

Diffusion models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignment, safety, preference satisfaction, and robustness to misuse. This survey reviews recent progress on aligning text-to-image diffusion models through reinforcement learning, reward modeling, preference optimization, and safety-specific fine-tuning. We organize the literature along five axes: the source of feedback, the form of the reward or preference signal, the optimization mechanism, the treatment of distribution shift and reward overoptimization, and the extent to which safety is addressed as an explicit constraint rather than a generic preference. The review covers reinforcement learning from human feedback, KL-regularized policy optimization, direct preference optimization, binary utility optimization, differentiable reward fine-tuning, surrogate reward learning, region-aware fine-tuning, and safety-oriented DPO variants. To make the survey accessible, we include tutorial explanations of diffusion sampling, reward modeling, and preference optimization, and briefly connect image diffusion alignment to emerging text and masked language diffusion models. We also compare representative methods in terms of feedback requirements, computational cost, scalability, susceptibility to reward hacking, and suitability for safety-critical deployment. Finally, we synthesize the literature into a set of open challenges: multi-objective alignment, feedback-efficient preference learning, adversarially robust safety alignment, continual alignment under changing norms, and interpretable reward modeling. The goal of this survey is to provide a coherent technical map of the emerging area of diffusion model alignment and to identify the methodological gaps that must be addressed before aligned generative models can be reliably deployed.

Safe Reinforcement Learning (SafeRL) is the subfield of reinforcement learning that explicitly deals with safety constraints during the learning and deployment of agents. This survey provides a mathematically rigorous overview of SafeRL formulations based on Constrained Markov Decision Processes (CMDPs) and extensions to Multi-Agent Safe RL (SafeMARL). We review theoretical foundations of CMDPs, covering definitions, constrained optimization techniques, and fundamental theorems. We then summarize state-of-the-art algorithms in SafeRL for single agents, including policy gradient methods with safety guarantees and safe exploration strategies, as well as recent advances in SafeMARL for cooperative and competitive settings. Additionally, we propose five open research problems to advance the field, with three focusing on SafeMARL. Each problem is described with motivation, key challenges, and related prior work. This survey is intended as a technical guide for researchers interested in SafeRL and SafeMARL, highlighting key concepts, methods, and open future research directions.

Background: Bone metastases are a common manifestation of many malignancies. External beam radiotherapy (EBRT) provides successful palliation of painful bone metastases. In the present study, we compared three schedules of palliative EBRT in painful bony metastasis. Objective: To evaluate pain relief and performance status improvement in these patients. Method: This prospective, study was conducted on patients of painful bone metastases from any primary. Patients were randomly divided into three groups to received palliative EBRT either 6Gy single-session (group-I), or 8Gy single-session (group-II) or 10Gy/2-fractions/1-week apart (group-III) to the involved site. Primary objective was to assess overall pain response, assessed using Glasgow pain scale and improvement in performance status, assessed using Eastern Cooperative Oncology Group (ECOG) performance status score. Secondary objectives measured were complete pain relief, duration of overall pain response, analgesic requirement and need of re-irradiation. Results: A total of 60-patients were equally randomized into 3 groups. Conclusion: Pain relief was observed maximum in group-III. In all three groups, mean baseline pain score was significantly reduced, and mean ECOG performance status improve 1-month post-EBRT.

A novel first-order method is proposed for training generative adversarial networks (GANs). It modifies the Gauss-Newton method to approximate the min-max Hessian and uses the Sherman-Morrison inversion formula to calculate the inverse. The method corresponds to a fixed-point method that ensures necessary contraction. To evaluate its effectiveness, numerical experiments are conducted on various datasets commonly used in image generation tasks, such as MNIST, Fashion MNIST, CIFAR10, FFHQ, and LSUN. Our method is capable of generating high-fidelity images with greater diversity across multiple datasets. It also achieves the highest inception score for CIFAR10 among all compared methods, including state-of-the-art second-order methods. Additionally, its execution time is comparable to that of first-order min-max methods.

This paper presents a promising avenue of Radio Frequency (RF) biosensors for sensitive and real-time monitoring of creatinine detection. Knowing creatinine levels in the human body is related to its possible association with renal, muscular, and thyroid dysfunction. The detection was performed using an Inter-Digitated Capacitor (IDC) made of copper (Cu) metal over an FR4 substrate. To demonstrate our methodology, we have chosen Phosphate Buffer (PB) as our solvent for making the creatinine solutions of different concentrations. Moreover, Assayed Chemistry Control (ACC), a reference control consisting of human serum-based solutions has been mixed with the different concentrations of creatinine in a ratio of 1:9 to spike the creatinine value in the ACC solution. The sensor has been designed using a High-Frequency Structure Simulator (HFSS) tool with an operating frequency of 2.53 GHz. Then the design is fabricated over the FR4 printed circuit board (PCB) and tested using a Vector Network Analyzer (VNA). However, the sensitive area of the IDC is introduced to grade 4 Whatman filter paper for the Sample Under Test (SUT) handling unit. The main advantage of using Whatman filter paper is that the uniform spreading of liquid reduces experimental error, and less volume is required for testing the sample. The principal idea implemented in the biosensor design is to track the shift in the operating frequency in the presence of different concentrations of creatinine mix in ACC solution with Phosphate Buffer (PB) solution as a reference.

Various studies have shown the advantages of using Machine Learning (ML) techniques for analog and digital IC design automation and optimization. Data scarcity is still an issue for electronic designs, while training highly accurate ML models. This work proposes generating and evaluating artificial data using generative adversarial networks (GANs) for circuit data to aid and improve the accuracy of ML models trained with a small training data set. The training data is obtained by various simulations in the Cadence Virtuoso, HSPICE, and Microcap design environment with TSMC 180 nm and 22 nm CMOS technology nodes. The artificial data is generated and tested for an appropriate set of analog circuits and digital cells. The experimental results show that the proposed artificial data generation significantly improves ML models and reduces the percentage error by more than 50% of the original percentage error, which were previously trained with insufficient data. Furthermore, this research aims to contribute to the extensive application of AI/ML in the field of VLSI design and technology by relieving the training data availability-related challenges.

Generative AI has seen remarkable growth over the past few years, with diffusion models being state-of-the-art for image generation. This study investigates the use of diffusion models in generating artificial data generation for electronic circuits for enhancing the accuracy of subsequent machine learning models in tasks such as performance assessment, design, and testing when training data is usually known to be very limited. We utilize simulations in the HSPICE design environment with 22nm CMOS technology nodes to obtain representative real training data for our proposed diffusion model. Our results demonstrate the close resemblance of synthetic data using diffusion model to real data. We validate the quality of generated data, and demonstrate that data augmentation certainly effective in predictive analysis of VLSI design for digital circuits.

Radio frequency (RF) biosensors, in particular those based on inter-digitated capacitors (IDCs), are pivotal in areas like biomedical diagnosis, remote sensing, and wireless communication. Despite their advantages of low cost and easy fabrication, their sensitivity can be hindered by design imperfections, environmental factors, and circuit noise. This paper investigates enhancing the sensitivity of IDC-based RF sensors using novel reinforcement learning based Binary Particle Swarm Optimization (RLBPSO), and it is compared to Ant Colony Optimization (ACO), and other state-of-the-art methods. By focusing on optimizing design parameters like electrode design and finger width, the proposed study found notable improvements in sensor sensitivity. The proposed RLBPSO method shows best optimized design for various frequency ranges when compared to current state-of-the-art methods.

Recent advances in Reinforcement Learning (RL) have led to many exciting applications. These advancements have been driven by improvements in both algorithms and engineering, which have resulted in faster training of RL agents. We present marl-jax, a multi-agent reinforcement learning software package for training and evaluating social generalization of the agents. The package is designed for training a population of agents in multi-agent environments and evaluating their ability to generalize to diverse background agents. It is built on top of DeepMind's JAX ecosystem~\cite{deepmind2020jax} and leverages the RL ecosystem developed by DeepMind. Our framework marl-jax is capable of working in cooperative and competitive, simultaneous-acting environments with multiple agents. The package offers an intuitive and user-friendly command-line interface for training a population and evaluating its generalization capabilities. In conclusion, marl-jax provides a valuable resource for researchers interested in exploring social generalization in the context of MARL. The open-source code for marl-jax is available at: \href{https://github.com/kinalmehta/marl-jax}{https://github.com/kinalmehta/marl-jax}

Recent advances in Reinforcement Learning (RL) have led to many exciting applications. These advancements have been driven by improvements in both algorithms and engineering, which have resulted in faster training of RL agents. We present marl-jax, a multi-agent reinforcement learning software package for training and evaluating social generalization of the agents. The package is designed for training a population of agents in multi-agent environments and evaluating their ability to generalize to diverse background agents. It is built on top of DeepMind’s JAX ecosystem [2] and leverages the RL ecosystem developed by DeepMind. Our framework marl-jax is capable of working in cooperative and competitive, simultaneous-acting environments with multiple agents. The package offers an intuitive and user-friendly command-line interface for training a population and evaluating its generalization capabilities. In conclusion, marl-jax provides a valuable resource for researchers interested in exploring social generalization in the context of MARL. The open-source code for marl-jax is available at: https://github.com/kinalmehta/marl-jax .

A large number of computational and scientific methods commonly require decomposing a sparse matrix into triangular factors as LU decomposition. A common problem faced during this decomposition is that even though the given matrix may be very sparse, the decomposition may lead to a denser triangular factors due to fill-in. A significant fill-in may lead to prohibitively larger computational costs and memory requirement during decomposition as well as during the solve phase. To this end, several heuristic sparse matrix reordering methods have been proposed to reduce fill-in before the decomposition. However, finding an optimal reordering algorithm that leads to minimal fill-in during such decomposition is known to be a NP-hard problem. A reinforcement learning based approach is proposed for this problem. The sparse matrix reordering problem is formulated as a single player game. More specifically, Monte-Carlo tree search in combination with neural network is used as a decision making algorithm to search for the best move in our game. The proposed method, Alpha Elimination is found to produce significantly lesser non-zeros in the LU decomposition as compared to existing state-of-the-art heuristic algorithms with little to no increase in overall running time of the algorithm. The code for the project is publicly available ( https://github.com/misterpawan/alphaEliminationPaper ).

In this paper, we study min-max optimization problems on Riemannian manifolds. We introduce a Riemannian Hamiltonian function, minimization of which serves as a proxy for solving the original min-max problems. Under the Riemannian Polyak--{\L}ojasiewicz condition on the Hamiltonian function, its minimizer corresponds to the desired min-max saddle point. We also provide cases where this condition is satisfied. For geodesic-bilinear optimization in particular, solving the proxy problem leads to the correct search direction towards global optimality, which becomes challenging with the min-max formulation. To minimize the Hamiltonian function, we propose Riemannian Hamiltonian methods (RHM) and present their convergence analyses. We extend RHM to include consensus regularization and to the stochastic setting. We illustrate the efficacy of the proposed RHM in applications such as subspace robust Wasserstein distance, robust training of neural networks, and generative adversarial networks.

A reliable critic is central to on-policy actor-critic learning. But it becomes challenging to learn a reliable critic in a multi-agent sparse reward scenario due to two factors: 1) The joint action space grows exponentially with the number of agents 2) This, combined with the reward sparseness and environment noise, leads to large sample requirements for accurate learning. We show that regularising the critic with spectral normalization (SN) enables it to learn more robustly, even in multi-agent on-policy sparse reward scenarios. Our experiments show that the regularised critic is quickly able to learn from the sparse rewarding experience in the complex SMAC and RWARE domains. These findings highlight the importance of regularisation in the critic for stable learning.

In our work, we propose a novel yet simple approach to obtain an adaptive learning rate for gradient-based descent methods on classification tasks. Instead of the traditional approach of selecting adaptive learning rates via the decayed expectation of gradient-based terms, we use the angle between the current gradient and the new gradient: this new gradient is computed from the direction orthogonal to the current gradient, which further helps us in determining a better adaptive learning rate based on angle history, thereby, leading to relatively better accuracy compared to the existing state-of-the-art optimizers. On a wide variety of benchmark datasets with prominent image classification architectures such as ResNet, DenseNet, Efficient-Net, and VGG, we find that our method leads to the highest accuracy in most of the datasets. Moreover, we prove that our method is convergent.

Extreme multi-label (XML) classification refers to the task of supervised multi-label learning that involves a large number of labels. Hence, scalability of the classifier with increasing label dimension is an important consideration. In this paper, we develop a method called LightDXML which modifies the recently developed deep learning based XML framework by using label embeddings instead of feature embedding for negative sampling and iterating cyclically through three major phases: (1) proxy training of label embeddings (2) shortlisting of labels for negative sampling and (3) final classifier training using the negative samples. Consequently, LightDXML also removes the requirement of a re-ranker module, thereby, leading to further savings on time and memory requirements. The proposed method achieves the best of both worlds: while the training time, model size and prediction times are on par or better compared to the tree-based methods, it attains much better prediction accuracy that is on par with the deep learning based methods. Moreover, the proposed approach achieves the best tail-label prediction accuracy over most state-of-the-art XML methods on some of the large datasets.

This paper illustrates a label-free, low-cost, fast detection of creatinine using a noninvasive lab-on-a-chip (LoC) Interdigitated capacitor (IDC) based sensor. Creatinine is a metabolic product of creatine phosphate in muscles, which provides energy to muscle tissues. The detection is done on an IDC made of copper (Cu) metal over an FR4 substrate. The sensor has been designed using a high-frequency structure simulator (HFSS) tool. Then the design is fabricated over the FR4 printed circuit board (PCB) and tested using a Vector Network Analyzer (VNA). The creatinine sample under the test is confined using a Polylactic Acid (PLA) wall attached to the sensor. A 52 MHz difference is observed between the simulated and experimental operating frequencies. The principal idea implemented in the biosensor design is to track the shift in the operating frequency in the presence of different concentrations of creatinine diluted in water and compare it with the operating frequency of the sensor with water as a reference. The testing is done in the medical range of 0.5 mg/dL to 2 mg/dL of creatinine solution.