Kannada Named Entity & Morphological Segmentation Benchmark
Developing a standardized tokenization and morphological parsing pipeline for low-resource Kannada administrative documents with comparative subword vocabulary boundary metrics.
Explore active, validating, and proposed research projects conducted across our six pods. Every project follows transparent git revision lineages and reproducibility guidelines.
Developing a standardized tokenization and morphological parsing pipeline for low-resource Kannada administrative documents with comparative subword vocabulary boundary metrics.
Quantifying label noise transfer when bootstrapping regional Kannada sentiment classifiers from English instruction-tuned models with calibrated temperature bounds.
Profiling post-training calibration loss and FPS throughput of YOLOv8n on resource-constrained ARM/NVIDIA architectures with layer-wise sensitivity audits.
Designing a zero-copy frame ingestion buffer for temporal anomaly localization in campus perimeter feeds without CPU memory serialization bottleneck.
Formulating a deterministic voting protocol across specialized reviewer agents to identify logic errors and test gaps in Python code with state guardrails.
Evaluating hallucination reduction rates using sentence-level attribution graphs on university academic regulations and syllabus documentation.
Constructing an ultra-compact convolutional classifier for continuous beat classification on PhysioNet MIT-BIH datasets designed for wearable microcontroller deployment.
Investigating wavelet decomposition methods for removing ocular and muscle artifacts from low-channel headband recordings without losing spectral band signatures.
Benchmarking 7B parameter local models against OWASP Top 10 LLM prompt injection and system override vectors with automated boundary test harness.
Applying AIF360 disparate impact metrics to inspect gender and demographic balance in automated applicant evaluation heuristics.
Building lightweight GitHub Actions runners that automatically capture VRAM spikes, seed integrity, and model hash lineage per pull request.
Profiling network latency thresholds for splitting neural pipeline layers between mobile nodes and local GPU servers over varying bandwidth constraints.
No projects match your selected filters.