Search Results for author:
Found 20 papers, 9 papers with code
Are Reasoning Models More Prone to Hallucination?
This discrepancy naturally raises the following research question: Are reasoning models more prone to hallucination?
Stability and Controllability of Revenue Systems via the Bode Approach
In online revenue systems, e. g. an advertising system, budget pacing plays a critical role in ensuring that the spend aligns with desired financial objectives.
Finding Safety Neurons in Large Language Models
In this paper, we explore the inner mechanisms of safety alignment from the perspective of mechanistic interpretability, focusing on identifying and analyzing safety neurons within LLMs that are responsible for safety behaviors.
Root Causing Prediction Anomalies Using Explainable AI
We have found this technique to be a model-agnostic, cheap and effective way to monitor complex data pipelines in production and have deployed a system for continuously analyzing the global feature importance distribution of continuously trained models.
When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks
In this paper, we find that ICL falls short of handling specification-heavy tasks, which are tasks with complicated and extensive task specifications, requiring several hours for ordinary humans to master, such as traditional information extraction tasks.
MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation
Understanding events in texts is a core objective of natural language understanding, which requires detecting event occurrences, extracting event arguments, and analyzing inter-event relationships.
KoLA: Carefully Benchmarking World Knowledge of Large Language Models
The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations.
BabelCalib: A Universal Approach to Calibrating Central Cameras
A lot of the difficulties of general camera calibration lie in the use of a forward projection model.
Adapting Grad-CAM for Embedding Networks
Then, we develop an efficient weight-transfer method to explain decisions for any image without back-propagation.
Sports Camera Calibration via Synthetic Data
Here we propose a highly automatic method for calibrating sports cameras from a single image using synthetic data.
Learning Sports Camera Selection from Internet Videos
This work addresses camera selection, the task of predicting which camera should be "on air" from multiple candidate cameras for soccer broadcast.
A Two-point Method for PTZ Camera Calibration in Sports
We also propose a fast random forest method to predict pan-tilt angles without image-to-image feature matching, leading to an efficient calibration method for new images.
Backtracking Regression Forests for Accurate Camera Relocalization
Camera relocalization plays a vital role in many robotics and computer vision tasks, such as global localization, recovery from tracking failure, and loop closure detection.
Light Cascaded Convolutional Neural Networks for Accurate Player Detection
Vision based player detection is important in sports applications.
Learning Online Smooth Predictors for Realtime Camera Planning Using Recurrent Decision Trees
We study the problem of online prediction for realtime camera planning, where the goal is to predict smooth trajectories that correctly track and frame objects of interest (e. g., players in a basketball game).
Convex Factorization Machine for Regression
We propose the convex factorization machine (CFM), which is a convex variant of the widely used Factorization Machines (FMs).
Optimal Stochastic Strongly Convex Optimization with a Logarithmic Number of Projections
We consider stochastic strongly convex optimization with a complex inequality constraint.
Clustered Multi-Task Learning Via Alternating Structure Optimization
We further establish the equivalence relationship between the proposed convex relaxation of CMTL and an existing convex relaxation of ASO, and show that the proposed convex CMTL formulation is significantly more efficient especially for high-dimensional data.
Efficient Recovery of Jointly Sparse Vectors
MMV is an extension of the single measurement vector (SMV) model employed in standard compressive sensing (CS).
