Bishwash Khanal

Bishwash Khanal, Sanjay Rijal, Manish Awale et al.

This paper presents a novel approach for structure-preserving planar simplification of indoor scene point clouds for both simulated and real-world environments. Initially, the scene point cloud undergoes preprocessing steps, including noise reduction and Manhattan world alignment, to ensure robustness and coherence in subsequent analyses. We segment each captured scene into structured (walls-ceiling-floor) and non-structured (indoor objects) scenes. Leveraging a RANSAC algorithm, we extract primitive planes from the input point cloud, facilitating the segmentation and simplification of the structured scene. The best-fitting wall meshes are then generated from the primitives, followed by adjacent mesh merging with the vertex-translation algorithm which preserves the mesh layout. To accurately represent ceilings and floors, we employ the mesh clipping algorithm which clips the ceiling and floor meshes with respect to wall normals. In the case of indoor scenes, we apply a surface reconstruction technique to enhance the fidelity. This paper focuses on the intricate steps of the proposed scene simplification methodology, addressing complex scenarios such as multi-story and slanted walls and ceilings. We also conduct qualitative and quantitative performance comparisons against popular surface reconstruction, shape approximation, and floorplan generation approaches.

Bishwash Khanal, Jeffery M. Capone

Large language models (LLMs) offer powerful capabilities but incur substantial computational costs, driving the need for efficient compression techniques. This study evaluates the impact of popular compression methods - Magnitude Pruning, SparseGPT, and Wanda - on the LLaMA-2-7B model, focusing on the trade-offs between model size reduction, downstream task performance, and the role of calibration data. Our findings reveal that while SparseGPT and Wanda preserve perplexity even at 50% sparsity, they suffer significant degradation on downstream tasks, highlighting the inadequacy of perplexity as the sole evaluation metric. To address this, we introduce Jensen-Shannon (JS) Divergence as a more comprehensive metric that captures nuanced changes in model behavior post-compression. We further demonstrate that task-specific calibration data significantly enhances the downstream performance of compressed models compared to general calibration data. This research underscores the necessity for diverse evaluation metrics and careful calibration data selection to fully understand the complexities of LLM compression and its implications for practical applications.

Tarlan Hasanli, Shahbaz Siddeeq, Bishwash Khanal et al.

Large language models (LLMs) accelerate software development but often exhibit instability, non-determinism, and weak adherence to development discipline in unconstrained workflows. While test-driven development (TDD) provides a structured Red-Green-Refactor process, existing LLM-based approaches typically use tests as auxiliary inputs rather than enforceable process constraints. We present an AI-native TDD framework that operationalizes classical TDD principles as structured prompt-level and workflow-level governance mechanisms. Extracted principles are formalized in a machine-readable manifesto and distributed across planning, generation, repair, and validation stages within a layered architecture that separates model proposal from deterministic engine authority. The system enforces phase ordering, bounded repair loops, validation gates, and atomic mutation control to improve stability and reproducibility. We describe architecture and discuss encoding software engineering discipline directly into prompt orchestration, which we think offers a promising direction for reliable LLM-assisted development.