Research
Research
Research
Research
2,187+ open-access research outputs.
Long-context large language models (LLMs)-for example, Gemini-3.1-Pro and Qwen-3.5-are widely used to empower many real-world applications, such as retrieval-augmented generation, autonomous agents, a…
Autonomous agents act through sandboxed containers and microVMs whose state spans filesystems, processes, and runtime artifacts. Checkpoint and restore (C/R) of this state is needed for fault toleranc…
Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack pa…
AI chatbots are becoming a primary interface for seeking information. As their popularity grows, chatbot providers are starting to deploy advertising and analytics. Despite this, tracking on AI chatbo…
Large Language Models (LLMs) have become an integral part of many real-world workflows. However, LLMs consume a lot of energy, which becomes a large concern in the scale of the demand for these tools.…
When multiple people share a single voice assistant, the system conflates their histories: one resident's preferences can leak into another's responses, eroding utility and trust. We call this failure…
In daily life, there are many scenarios that people need to tackle data-related tasks, such as filling out forms, analyzing Excel files, and visualize data report. However, the tools available for the…
Large language models can generate code and call tools with remarkable fluency, yet deploying them as practical software engineering assistants still expose stubborn gaps: finite context windows, sing…
The emergence of large language models has enabled vibe coding, a natural language approach to programming in which users describe intent and AI generates or revises code, potentially broadening acces…
The capabilities of AI-assisted coding are progressing at breakneck speed. Chat-based vibe coding has evolved into fully fledged AI-assisted, agentic software development using agent scaffolds where t…
We designed and implemented InvestChat, a multimodal tablet-based application that supports stock market exploration with multiple coordinated views and an LLM-powered chat. We evaluated the applicati…
Intergenerational linguistic differences pose challenges to effective and intimate family communication. This paper presents GenSync, a chat-based interface that supports intergenerational understandi…
Developing Visual Analytics (VA) applications requires integrating complex machine learning models with expressive interactive interfaces. Developers face a stark trade-off: building tightly-coupled m…
Current AI-assisted programming tools are predominantly linear and chat-based, which deviates from the iterative and branching nature of programming itself. Our preliminary study with developers using…
Vibe coding produces correct, executable code at speed, but leaves no record of the structural commitments, dependencies, or evidence behind it. Reviewers cannot determine what invariants were assumed…
Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving. Current systems suffer from three compounding inefficienc…
Serendipity-oriented recommender systems expose users to unfamiliar items to counter filter bubbles, yet mere exposure does not ensure that users will understand or appreciate the content they encount…
Extracting actionable insights from long-duration urban videos is often labor-intensive: analysts must manually sift through raw footage to pinpoint target events or uncover broader behavioral trends.…
Private set intersection (PSI) enables a sender holding a set $Q$ of size $m$ and a receiver holding a set $W$ of size $n$ to securely compute the intersection $Q \cap W$. Fuzzy PSI (FPSI) is a PSI va…
Complex visual interfaces are powerful yet have a steep learning curve, as users must navigate feature-rich visual interfaces while reasoning about domain-specific operations. Existing approaches eith…
Free open-access publishing with Google Scholar indexing.
Submission Guide →