papers

Publications (6)

cs.CV2025

Towards Fine-Grained Video Question Answering

Wei Dai, Alan Luo, Zane Durante +5

In the rapidly evolving domain of video understanding, Video Question Answering (VideoQA) remains a focal point. However, existing datasets exhibit gaps in temporal and spatial gra…

cs.CR2023

A Review of zk-SNARKs

Thomas Chen, Hui Lu, Teeramet Kunpittaya +1

A zk-SNARK is a protocol that lets one party, the prover, prove to another party, the verifier, that a statement about some privately-held information is true without revealing the…

cs.LG2025

Quantize What Counts: More for Keys, Less for Values

Mohsen Hariri, Alan Luo, Weicong Chen +6

Large Language Models (LLMs) suffer inference-time memory bottlenecks dominated by the attention Key-Value (KV) cache, which scales with model size and context length. While KV-cac…

cs.CL2026

OpenAI GPT-5 System Card

Aaditya Singh, Adam Fry, Adam Perelman +483

This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reason…

cs.CV2026

Simple Self Organizing Map with Vision Transformers

Alan Luo, Kaiwen Yuan

Vision Transformers (ViTs) have demonstrated exceptional performance in various vision tasks. However, they tend to underperform on smaller datasets due to their inherent lack of i…

cs.CL2026

Trust The Typical

Debargha Ganguly, Sreehari Sankar, Biyao Zhang +8

Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We argue for a fresh approach: robust…