9 papers
Next Token or Vector? Learning How Far to Decode
Sai Sreenivas Chintha, Chidera Biringa, Rishab Sharma +6
Standard autoregressive decoding advances one token at a time, even when several upcoming tokens can be predicted together. We propose CADENCE (Context-Adaptive DEcoding), a genera…
Stashbird: Episode-Grounded Lifecycle Reconciliation for Conversational Agent Memory
Chidera Biringa, Lucas Yannul, Xiaowen Wang +5
AI agents require memory that remains consistent as conversational evidence changes. We present Stashbird, an episode-grounded memory system that uses provenance to reconcile deriv…
VulStyle: A Multi-Modal Pre-Training for Code Stylometry-Augmented Vulnerability Detection
Chidera Biringa, Ajmal Abbas, Vishnu Selvaraj +1
We present VulStyle, a multi-modal software vulnerability detection model that jointly encodes function-level source code, non-terminal Abstract Syntax Tree (AST) structure, and co…
CORPGEN: Simulating Corporate Environments with Autonomous Digital Employees in Multi-Horizon Task Environments
Abubakarr Jaye, Nigel Boachie Kumankumah, Chidera Biringa +8
Long-horizon reasoning is a key challenge for autonomous agents, yet existing benchmarks evaluate agents on single tasks in isolation. Real organizational work requires managing ma…
Detecting Hard-Coded Credentials in Software Repositories via LLMs
Chidera Biringa, Gokhan Kul
Software developers frequently hard-code credentials such as passwords, generic secrets, private keys, and generic tokens in software repositories, even though it is strictly advis…
PACE: A Program Analysis Framework for Continuous Performance Prediction
Chidera Biringa, Gokhan Kul
Software development teams establish elaborate continuous integration pipelines containing automated test cases to accelerate the development process of software. Automated tests h…
Short Paper: Static and Microarchitectural ML-Based Approaches For Detecting Spectre Vulnerabilities and Attacks
Chidera Biringa, Gaspard Baye, Gökhan Kul
Spectre intrusions exploit speculative execution design vulnerabilities in modern processors. The attacks violate the principles of isolation in programs to gain unauthorized priva…
A Secure Design Pattern Approach Toward Tackling Lateral-Injection Attacks
Chidera Biringa, Gökhan Kul
Software weaknesses that create attack surfaces for adversarial exploits, such as lateral SQL injection (LSQLi) attacks, are usually introduced during the design phase of software…
Automated User Experience Testing through Multi-Dimensional Performance Impact Analysis
Chidera Biringa, Gokhan Kul
Although there are many automated software testing suites, they usually focus on unit, system, and interface testing. However, especially software updates such as new security feat…