14 citations · 16 across the 6 of their papers we have counts for
8 papers
Temporal Specification Guidance for Text-to-Video Generation
Avishree Khare, Hideki Okamoto, Bardh Hoxha +2
Text-to-video models often generate the visual concepts requested in natural language prompts but fail to satisfy their intended ordering, timing, and persistence requirements. We…
Meta-Reflective Evolution Effectively Improves Production AI Systems
Seung Won Wilson Yoo, Chang Zeng, Aditi Somayajula +7
Large Language Model (LLM)-guided evolutionary optimization has successfully improved prompts, programs, and even entire AI systems. Most optimization methods select a candidate fr…
LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval
Avishree Khare, Hideki Okamoto, Bardh Hoxha +2
Neural models such as YOLO and HuBERT can be used to detect local properties such as objects ("car") and emotions ("angry") in individual frames of videos and audio clips respectiv…
Instruction Following by Principled Boosting Attention of Large Language Models
Vitoria Guardieiro, Avishree Khare, Adam Stein +1
Large language models' behavior is often shaped by instructions such as system prompts, refusal boundaries, privacy constraints, and tool-use rules that must hold at inference time…
Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference
Anton Xue, Avishree Khare, Rajeev Alur +2
We study how to subvert large language models (LLMs) from following prompt-specified rules. We first formalize rule-following as inference in propositional Horn logic, a mathematic…
Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities
Avishree Khare, Saikat Dutta, Ziyang Li +3
While automated vulnerability detection techniques have made promising progress in detecting security vulnerabilities, their scalability and applicability remain challenging. The r…
GrACE: Generation using Associated Code Edits
Priyanshu Gupta, Avishree Khare, Yasharth Bajpai +6
Developers expend a significant amount of time in editing code for a variety of reasons such as bug fixing or adding new features. Designing effective methods to predict code edits…
KD-Lib: A PyTorch library for Knowledge Distillation, Pruning and Quantization
Het Shah, Avishree Khare, Neelay Shah +1
In recent years, the growing size of neural networks has led to a vast amount of research concerning compression techniques to mitigate the drawbacks of such large sizes. Most of t…