Significant progress has been made inthepast decade thanks to the availability of pedestrian trajectory datasets, which enable trajectory prediction methods to learn from pedestrians' past movements and predict future trajectories. However, these datasets and methods typically assume that theobservedtrajectory sequence iscomplete, ignoring real-world issues such as sensor failure, occlusion, and limited fields of view that can result in missing valuesinobservedtrajectories.

Diffusion models, though successful, are known to suffer from hallucinations that create incoherent or unrealistic samples. Recent works have attributed this to the phenomenon of mode interpolation and score smoothening, but they lack a method to prevent their generation during sampling. In this paper, we propose a post-hoc adjustment to the score function during inference that leverages the Laplacian (or sharpness) of the score to reduce mode interpolation hallucination in unconditional diffusion models across 1D, 2D, and high-dimensional image data. We derive an efficient Laplacian approximation for higher dimensions using a finite-difference variant of the Hutchinson trace estimator. We show that this correction significantly reduces the rate of hallucinated samples across toy 1D/2D distributions and a high-dimensional image dataset. Furthermore, our analysis explores the relationship between the Laplacian and uncertainty in the score.

Muskan Sharma stood up to men who tried to bully her over her clothes - and went on to win hearts and a beauty pageant. The 23-year-old, who was crowned Miss Rishikesh 2025 last week in the northern Indian state of Uttarakhand, told the BBC that even though it was a small local pageant, it made me feel like Miss Universe. Sharma's win has made headlines in India as it came after a viral video that showed her spiritedly arguing with a man who barged into their rehearsals just a day before the 4 October contest. Sharma, who wanted to be a model and participate in a pageant since I was in school, said the intruders came in just as they broke for lunch. We were sitting around, chilling, having a laugh when they walked in, she said.

Datasets and code files are publicly accessible at Link. Our dataset will be hosted on both the GitHub and cloud storage drive. Code for the TimesNet Link Code for the SAITS Link 5.2 Trajectory Prediction Codes The following are the codes for the trajectory prediction methods used in our work. The dataset is primarily created by an academic team (students and faculty). The data statistics are shown in Section 4 of the main paper.

Significant progress has been made in the past decade thanks to the availability of pedestrian trajectory datasets, which enable trajectory prediction methods to learn from pedestrians' past movements and predict future trajectories.

Contemporary transformer architectures apply identical processing depth to all inputs, creating inefficiencies and limiting reasoning quality. Simple factual queries are subjected to the same multilayered computation as complex logical problems, wasting resources while constraining deep inference. To overcome this, we came up with a concept of Dynamic Reasoning Chains through Depth Specialised Mixture of Experts (DS-MoE), a modular framework that extends the Mixture of Experts paradigm from width-based to depth specialised computation. DS-MoE introduces expert modules optimised for distinct reasoning depths, shallow pattern recognition, compositional reasoning, logical inference, memory integration, and meta-cognitive supervision. A learned routing network dynamically assembles custom reasoning chains, activating only the necessary experts to match input complexity. The dataset on which we trained and evaluated DS-MoE is on The Pile, an 800GB corpus covering diverse domains such as scientific papers, legal texts, programming code, and web content, enabling systematic assessment across reasoning depths. Experimental results demonstrate that DS-MoE achieves up to 16 per cent computational savings and 35 per cent faster inference compared to uniform-depth transformers, while delivering 2.8 per cent higher accuracy on complex multi-step reasoning benchmarks. Furthermore, routing decisions yield interpretable reasoning chains, enhancing transparency and scalability. These findings establish DS-MoE as a significant advancement in adaptive neural architectures, demonstrating that depth-specialised modular processing can simultaneously improve efficiency, reasoning quality, and interpretability in large-scale language models.

Transformer architectures have achieved state-of-the-art performance across natural language tasks, yet they fundamentally misrepresent the hierarchical nature of human language by processing text as flat token sequences. This results in quadratic computational cost, weak computational cost, weak compositional generalization, and inadequate discourse-level modeling. We propose Hierarchical Resolution Transformer (HRT), a novel wavelet-inspired neural architecture that processes language simultaneously across multiple resolutions, from characters to discourse-level units. HRT constructs a multi-resolution attention, enabling bottom-up composition and top-down contextualization. By employing exponential sequence reduction across scales, HRT achieves O(nlogn) complexity, offering significant efficiency improvements over standard transformers. We evaluated HRT on a diverse suite of benchmarks, including GLUE, SuperGLUE, Long Range Arena, and WikiText-103, and results demonstrated that HRT outperforms standard transformer baselines by an average of +3.8% on GLUE, +4.5% on SuperGLUE, and +6.1% on Long Range Arena, while reducing memory usage by 42% and inference latency by 37% compared to BERT and GPT style models of similar parameter count. Ablation studies confirm the effectiveness of cross-resolution attention and scale-specialized modules, showing that each contributes independently to both efficiency and accuracy. Our findings establish HRT as the first architecture to align computational structure with the hierarchical organization of human language, demonstrating that multi-scale, wavelet-inspired processing yields both theoretical efficiency gains and practical improvements in language understanding.

In multilingual healthcare environments, automatic disease diagnosis from clinical text remains a challenging task due to the scarcity of annotated medical data in low-resource languages and the linguistic variability across populations. This paper proposes SwasthLLM, a unified, zero-shot, cross-lingual, and multi-task learning framework for medical diagnosis that operates effectively across English, Hindi, and Bengali without requiring language-specific fine-tuning. At its core, SwasthLLM leverages the multilingual XLM-RoBERTa encoder augmented with a language-aware attention mechanism and a disease classification head, enabling the model to extract medically relevant information regardless of the language structure. To align semantic representations across languages, a Siamese contrastive learning module is introduced, ensuring that equivalent medical texts in different languages produce similar embeddings. Further, a translation consistency module and a contrastive projection head reinforce language-invariant representation learning. SwasthLLM is trained using a multi-task learning strategy, jointly optimizing disease classification, translation alignment, and contrastive learning objectives. Additionally, we employ Model-Agnostic Meta-Learning (MAML) to equip the model with rapid adaptation capabilities for unseen languages or tasks with minimal data. Our phased training pipeline emphasizes robust representation alignment before task-specific fine-tuning. Extensive evaluation shows that SwasthLLM achieves high diagnostic performance, with a test accuracy of 97.22% and an F1-score of 97.17% in supervised settings. Crucially, in zero-shot scenarios, it attains 92.78% accuracy on Hindi and 73.33% accuracy on Bengali medical text, demonstrating strong generalization in low-resource contexts.

Hyper-parameter Tuning (HPT) is a necessary step in machine learning (ML) pipelines but becomes computationally expensive and opaque with larger models. Recently, Large Language Models (LLMs) have been explored for HPT, yet most rely on models exceeding 100 billion parameters. We propose an Expert Block Framework for HPT using Small LLMs. At its core is the Trajectory Context Summarizer (TCS), a deterministic block that transforms raw training trajectories into structured context, enabling small LLMs to analyze optimization progress with reliability comparable to larger models.

Large language models (LLMs) are known to memorize parts of their training data, raising important concerns around privacy and security. While previous research has focused on studying memorization in pre-trained models, much less is known about how knowledge distillation (KD) affects memorization.In this study, we explore how different KD methods influence the memorization of fine-tuned task data when a large teacher model is distilled into smaller student variants.This study demonstrates that distilling a larger teacher model, fine-tuned on a dataset, into a smaller variant not only lowers computational costs and model size but also significantly reduces the memorization risks compared to standard fine-tuning approaches.