Multimodal LLMs: five student project ideas beyond 'chat with a PDF'

Presenting KrishGyan, farming advice in your voice and language
Presenting KrishGyan, farming advice in your voice and language

Originally published at https://pranjulrathour.scult.in/blog/multimodal-llms-for-students-projects. That copy is the canonical version and gets updates first.

Every third portfolio I review has a PDF chatbot. It is a fine first project and a weak fifth one. Multimodal models — text, images, audio — open up problems that are harder, more interesting and far less crowded. Here are five I would be glad to see from a student, each with the part that will actually be difficult.

1. Lecture-to-notes with slide alignment

Record a lecture, transcribe it live (see real-time speech-to-text architecture), OCR the slides, and align transcript segments to the slide being shown. The hard part is alignment; the payoff is searchable notes with the slide beside every paragraph.

Taking questions during a session
Taking questions during a session

2. Receipt and expense auditor

Photograph receipts, extract fields into a strict schema, validate the arithmetic, and flag anomalies. The hard part is the validation layer, exactly as in document AI for invoices. Evaluate on field-level accuracy, not on "looks right".

3. Accessibility describer for campus notices

Photos of notice boards become structured announcements with dates and venues, read aloud on request. The hard part is handling handwritten and skewed text; the value is real for visually impaired students.

4. Privacy-preserving attendance

Browser-side face detection and embedding with liveness, embeddings-only storage, no photos retained — the FaceVision pattern. The hard part is the threshold and bias measurement across your actual classmates. Document the error rates; that is what makes it a serious project.

Pranjul Rathour
Pranjul Rathour

5. Voice-first assistant for a regional language

Speech in, retrieval over a small document set, speech out — the shape of Krishi Gyan, the agribot that won Changethon 2025 at IIT Roorkee. The hard part is evaluation in a language you may not have benchmarks for; build a small test set with native speakers.

How to make any of these count

  • Ship a working demo, not a notebook.
  • Publish the evaluation numbers, including failures.
  • Write a two-page README that a recruiter can read in three minutes.

Pick the one whose hard part you find interesting. That is the one you will finish.

From my carousels
5 Production AI Apps, All Open Source
5 Production AI Apps, All Open Source, slide 15 Production AI Apps, All Open Source, slide 2
5 Production AI Apps, All Open Source, slide 35 Production AI Apps, All Open Source, slide 4
Full carousel on Instagram and LinkedIn.
Pranjul Rathour
Pranjul Rathour
GenAI engineer, Kanpur · 3x first-prize hackathon winner · campus mentor
I ship production RAG pipelines, fine-tune LLMs and build agentic AI products end to end. I lead engineering at SCULT INDIA for a 14-member team and have mentored 200+ students through TechVerse Enclave.
Open to: GenAI roles, hackathon judging, mentorship sessions and guest talks at colleges.
On stage, at hackathons and on campus
Presenting Annapurna on stage
Presenting Annapurna on stage
Presenting to a room
Presenting to a room
Requirements gathering and user flows, on stage
Requirements gathering and user flows, on stage

Comments

Post a Comment

Popular posts from this blog

Forming a hackathon team: roles, skills and the mistake most teams make

Image
At an Integral Startup Foundation hackathon Originally published at https://pranjulrathour.scult.in/blog/hackathon-team-roles-and-formation . That copy is the canonical version and gets updates first. Team TechVerse — Raman Shukla, Saksham Gupta and me — won three first prizes in 2025 not because we were the strongest coders in the room, but because we had stopped overlapping. When I mentor teams before a hackathon, formation is the first thing I fix. In a packed college auditorium The four roles Builder — owns the core feature and the demo path. Usually backend or the AI piece. Interface — owns what the judge sees: the front end, the flow, the seeded data. Storyteller — owns the problem statement, the pitch, the slides and the Q&A plan; also does user research in hour one. Integrator — keeps the pieces working together, manages the repo, runs the demo rehearsals. In a team of three, the builder or interface person takes this. The mistake Five friends who all write R...
Read more

Hello from Kanpur: what I build, and what I'll write about here

Image
On the mic Originally published at https://dev.to/pranjulrathour/hello-from-kanpur-what-i-build-and-what-ill-write-about-here-f2j . That copy is the canonical version and gets updates first. I'm Pranjul Rathour, a GenAI engineer from Kanpur, India. This is the first post on this blog, so here is who is writing, what I have actually shipped, and what you can expect if you follow along. What I build Between February and July 2026, at Next Upgrad Web Solutions, I designed, built and shipped five production AI applications end to end, alone, and deployed all of them with Docker, CI and observability: RAG.NextUpgrad : a retrieval-augmented generation service with hybrid dense plus BM25 retrieval, cross-encoder reranking, streaming cited answers, and a confidence gate that refuses to call the model when the evidence is weak. It runs in about 220 MB of memory, inside a free 512 MB instance. FineTune Studio : fine-tune open models with QLoRA in a browser. Upload a dataset, validate ...
Read more

I built 15 free tools, 1,211 prompts and a 50,000-skill library — here's what's inside tools.scult.in

Image
Carousel · 12 slides I built every part of tools.scult.in myself — 15 browser tools, 1,211 version-stamped prompts, a 50,000+ agent-skills library, a public MCP server, and 40 retro photo prompts where I'm the face in every example. All of it free. No signup, no ads, no upload step. Swipe through for what's inside and why I built it this way. Link in the last slide. Slide 1 of 12 Slide 2 of 12 Slide 3 of 12 Slide 4 of 12 Slide 5 of 12 Slide 6 of 12 Slide 7 of 12 Slide 8 of 12 Slide 9 of 12 Slide 10 of 12 Slide 11 of 12 Slide 12 of 12 Pranjul Rathour GenAI engineer, Kanpur · 3x first-prize hackathon winner · campus mentor I ship production RAG pipelines, fine-tune LLMs and build agentic AI products end to end. I lead engineering at SCULT INDIA for a 14-member team and have mentored 200+ students through TechVerse Enclave. Open to: GenAI roles, hackathon judging, mentorship sessions and guest talks at colleges. Email: pranjulrathour41@gmail.com Portfolio & ...
Read more