Skip to main content
AIACResearch Centre
BMSIT · CSE
Research practice ↗
AIACRESEARCH CENTRE
HomeResearchProjectsPeopleOutputsUpdatesReproducibility
Apply→
HomeResearchProjectsPeopleOutputsUpdatesReproducibility
Apply to Research Division →
Home / Projects

Research Projects

Explore active, validating, and proposed research projects conducted across our six pods. Every project follows transparent git revision lineages and reproducibility guidelines.

activeRegional NLP & Indic LLMs · Cycle 2026.1

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.

PyTorchHugging FacespaCyIndicBERT
View Details→
CodePaper
validatingRegional NLP & Indic LLMs · Cycle 2026.1

Cross-Lingual Pseudo-Labeling for Regional Sentiment Analysis

Quantifying label noise transfer when bootstrapping regional Kannada sentiment classifiers from English instruction-tuned models with calibrated temperature bounds.

PyTorchLoRAHugging Face DatasetsWeights & Biases
View Details→
CodePaper
activeEdge AI & Vision Systems · Cycle 2026.1

Low-Latency INT8 Quantized Object Detection on Embedded Jetson

Profiling post-training calibration loss and FPS throughput of YOLOv8n on resource-constrained ARM/NVIDIA architectures with layer-wise sensitivity audits.

TensorRTYOLOv8CUDAOpenCVONNX
View Details→
CodePaper
proposedEdge AI & Vision Systems · Cycle 2026.2

Multi-Camera Video Stream Anomaly Detection Pipeline

Designing a zero-copy frame ingestion buffer for temporal anomaly localization in campus perimeter feeds without CPU memory serialization bottleneck.

DeepStreamGStreamerPyTorchC++
View Details→
activeAgentic AI & Autonomous Loops · Cycle 2026.1

Deterministic Multi-Agent Consensus for Automated Pull Request Triage

Formulating a deterministic voting protocol across specialized reviewer agents to identify logic errors and test gaps in Python code with state guardrails.

LangGraphFastAPIOllamaPydanticDocker
View Details→
CodePaper
validatingAgentic AI & Autonomous Loops · Cycle 2026.1

Grounded RAG Pipeline with Semantic Source Verification

Evaluating hallucination reduction rates using sentence-level attribution graphs on university academic regulations and syllabus documentation.

LlamaIndexChromaDBLangChainSentence-Transformers
View Details→
Code
activeHealthcare & Bio-Signals · Cycle 2026.1

Lightweight 1D-CNN for Real-Time Single-Lead ECG Anomaly Detection

Constructing an ultra-compact convolutional classifier for continuous beat classification on PhysioNet MIT-BIH datasets designed for wearable microcontroller deployment.

PyTorchWFDBNeuroKit2SciPy
View Details→
Code
proposedHealthcare & Bio-Signals · Cycle 2026.2

Artifact Removal and Spectral Power Tracking in Mobile EEG Feeds

Investigating wavelet decomposition methods for removing ocular and muscle artifacts from low-channel headband recordings without losing spectral band signatures.

MNE-PythonNumPyPyTorch
View Details→
activeSecure AI & Model Ethics · Cycle 2026.1

Systematic Jailbreak Taxonomy and Automated Evaluation for Small LLMs

Benchmarking 7B parameter local models against OWASP Top 10 LLM prompt injection and system override vectors with automated boundary test harness.

GarakMITRE ATLASPyTorchHugging Face
View Details→
Code
proposedSecure AI & Model Ethics · Cycle 2026.2

Algorithmic Parity Audit of Student Merit Screening Baselines

Applying AIF360 disparate impact metrics to inspect gender and demographic balance in automated applicant evaluation heuristics.

AIF360FairlearnSHAPScikit-Learn
View Details→
activeSystems, HPC & MLOps · Cycle 2026.1

Automated Experiment Lineage & GPU Telemetry Testbed

Building lightweight GitHub Actions runners that automatically capture VRAM spikes, seed integrity, and model hash lineage per pull request.

DockerMLflowGitHub ActionsPrometheusPython
View Details→
Code
proposedSystems, HPC & MLOps · Cycle 2026.2

Heterogeneous Edge-to-Server Model Offloading Benchmarks

Profiling network latency thresholds for splitting neural pipeline layers between mobile nodes and local GPU servers over varying bandwidth constraints.

KubernetesgRPCTriton ServerC++
View Details→

No projects match your selected filters.

AIAC

AI & Analytics Club — Research Division. An autonomous student-led research collective exploring applied AI, systems, and theoretical foundations.

Affiliated with the Department of Computer Science & Engineering.
Open research, peer accountability, computational rigor.

Navigation

  • Home
  • Research
  • Projects
  • People
  • Outputs
  • Updates
  • Reproducibility

Research Themes

  • 01 · Regional NLP & Indic LLMs
  • 02 · Edge AI & Vision Systems
  • 03 · Agentic AI & Autonomous Loops
  • 04 · Healthcare & Bio-Signals
  • 05 · Secure AI & Model Ethics
  • 06 · Systems, HPC & MLOps

Engagement

  • Apply as Researcher
  • Research Collaboration
  • Reproducibility Standards
  • Staff Portal

Inquiries

research@aiac.example.edu

© 2026 AIAC Research Centre. All original research outputs licensed under CC BY 4.0 unless otherwise noted.

Open Source artifacts licensed under MIT / Apache 2.0.

Cycle 2026.1 Active
ESC
No matching records found.
↑↓ to navigate↵ to selectesc to close