about/
Hi, I'm Vishesh (he/him) :)
I'm a junior in CS at the University of Cincinnati (graduating April 2027). I'm a student researcher in the CincyNLP Lab, advised by Dr. Tianyu Jiang.
I like building things other people can actually use. Startups and VC are kind of wild to me, huge fast-moving ways to ship real value, which is partly why I'm an associate at Bearcat Ventures, UC's student-run ~$1M fund (due diligence, deals, the usual chaos).
I also like hackathons to build cool stuff and meet even cooler people. In one semester that was MIT, Harvard, Cloudflare, and Berkeley, usually around agents / MCP / whatever sounds fun. If you want to chat research, startups, or random ideas: anandvh@mail.uc.edu.
news/
2026-04: "Rhetorical Questions in LLM Representations" accepted to ACL Main.
2025-11: 2nd place, VCIC (Venture Capital Investment Competition) Regionals at CMU.
2025-10: Cal Hacks, 3rd place, Snap AR track (memARy).
2025-06: Startup Weekend, winner, Edge AI track.
2024-05: TA and Sophomore of the Year (UC).
research/
I'm pretty obsessed with what goes on inside LLMs, the "biology" of weights and activations, and how far we can interpret that stuff in a pragmatic way. I care a lot about alignment and safety too, not as buzzwords but as "what is this model actually doing?" The Anthropic piece Toy models of superposition is what pulled me into the field, still one of the clearest explanations of a model I've read.
I work with Dr. Tianyu Jiang in the CincyNLP Lab. Unrelated but equally nerdy, I love reading about how operating systems actually work under the hood.
- Louie Hong Yao, Vishesh Anand, Yuan Zhuang, and Tianyu Jiang.Rhetorical Questions in LLM Representations: A Linear Probing Study.Accepted to the main conference of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026). San Diego, CA, USA. Main conference July 5–7, 2026. PDF.
projects/
Selected builds. More on GitHub and Devpost.
Kite, "Cursor for GitHub", SoarAI Labs, OpenAI OSS Hackathon (Aug 2025 to present).
Agentic CLI and dashboard for natural language git work, PRs, commits, branches, merge conflicts. MCP tooling, Go agent, RAG over commits. github, site.
memARy, Cal Hacks 2025, 3rd place, Snap AR track.
Wearable-ish memory, vision and audio to structured search (Reka, ChromaDB RAG, MCP on Render). devpost.
XStream, MCP Server Hackathon 2025.
TypeScript MCP server on Cloudflare Workers, post to X with OAuth, D1, Workers AI images, built in about two hours. Public repo link coming, happy to share if you ask.
Just-Hurry!, Hack Harvard 2024.
Hurricane impact zones and volunteer coordination in under 36 hours. Next.js, Flask, MongoDB. devpost.
experience/
ML (CV) Intern, Kinetic Vision, Jan 2026 to present.
Research Assistant, CincyNLP Lab, Dr. Tianyu Jiang, Aug 2025 to present.
LLM eval on math and code, RL fine-tuning on Qwen 7.5B, ensemble BERT for six-way embodied emotion detection, mix of training runs and figuring out what actually generalizes.
VC Associate, Bearcat Ventures ($1M Student Fund), Jan 2025 to present.
Seed and pre-seed diligence, helped shape $25K SAFEs, led a $100K Series A for a TBI headset company. Built scraping and LinkedIn tooling that roughly doubled our deal flow pipeline.
AI Solutions Co-op, Kinetic Vision, Apr to Jul 2024.
Voice kiosk "Lucy" for UC's 1819 Innovation Hub, shipped end to end. Also YOLOv5 for product ID and B2B testing platform work. UC write-up.
Software Engineering Co-op, Kinetic Vision, Aug to Dec 2023.
Production volunteer portal (TypeScript, Keystone, React). Resource map and Google Calendar on Docker and EC2.
Research Assistant, Bioinformatics, Dr. Danny Wu, Jan 2024 to Jan 2025.
Full-stack dashboard for Cincinnati Children's HIRC (200+ researchers), Flask, SQL tuning, a lot of tickets closed.
tidbits/
- Five hackathons in one semester, placed or won most of them. Apparently I still function on no sleep. (Do not try this at home.)
- The questions that keep me up: why do big neural nets work, and what do they actually "know"?
- When I'm not parked in front of a screen, rare, but I try, I like the gym.
- GitHub is usually where you'll find me late at night.