Search Results for author:
Found 22 papers, 12 papers with code
Dissecting Human and LLM Preferences
As a relative quality comparison of model responses, human and Large Language Model (LLM) preferences serve as common alignment goals in model fine-tuning and criteria in evaluation.
TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation
Despite remarkable advancements in emulating human-like behavior through Large Language Models (LLMs), current textual simulations do not adequately address the notion of time.
Extending LLMs' Context Window with 100 Samples
Large Language Models (LLMs) are known to have limited extrapolation ability beyond their pre-trained context window, constraining their application in downstream tasks with lengthy inputs.
Learning to Abstain From Uninformative Data
Learning and decision-making in domains with naturally high noise-to-signal ratio, such as Finance or Healthcare, is often challenging, while the stakes are very high.
Can Large Language Models Understand Real-World Complex Instructions?
To bridge this gap, we propose CELLO, a benchmark for evaluating LLMs' ability to follow complex instructions systematically.
Learning to Segment from Noisy Annotations: A Spatial Correction Approach
However, segmentation label noise usually has strong spatial correlation and has prominent bias in distribution.
HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation
Similes play an imperative role in creative writing such as story and dialogue generation.
Topology-Aware Uncertainty for Image Segmentation
Segmentation of curvilinear structures such as vasculature and road networks is challenging due to relatively weak signals and complex geometry/topology.
C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models
We present C-Eval, the first comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context.
Provably Convergent Schrödinger Bridge with Applications to Probabilistic Time Series Imputation
We show that optimizing the transport cost improves the performance and the proposed algorithm achieves the state-of-the-art result in healthcare and environmental data while exhibiting the advantage of exploring both temporal and feature patterns in probabilistic time series imputation.
In-situ monitoring additive manufacturing process with AI edge computing
Inference time of ViTSR and FCN was optimized to 50. 97 ms and 67. 86 ms on AI edge board after operator fusion and model pruning.
On the Convergence of Optimizing Persistent-Homology-Based Losses
Topological loss based on persistent homology has shown promise in various applications.
A Manifold View of Adversarial Risk
Assuming data lies in a manifold, we investigate two new types of adversarial risk, the normal adversarial risk due to perturbation along normal direction, and the in-manifold adversarial risk due to perturbation within the manifold.
Learning to Abstain in the Presence of Uninformative Data
Learning and decision making in domains with naturally high noise-to-signal ratios – such as Finance or Public Health – can be challenging and yet extremely important.
Topological Detection of Trojaned Neural Networks
Deep neural networks are known to have security issues.
Learning with Feature-Dependent Label Noise: A Progressive Approach
Label noise is frequently observed in real-world large-scale datasets.
Ranked #12 on
Learning with noisy labels
on ANIMAL
Stability of SGD: Tightness Analysis and Improved Bounds
This raises the question: is the stability analysis of [18] tight for smooth functions, and if not, for what kind of loss functions and data distributions can the stability analysis be improved?
Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach
A federatedGAN jointly trains a centralized generator and multiple private discriminators hosted at different sites.
Revisiting the Stability of Stochastic Gradient Descent: A Tightness Analysis
We provide empirical evidence that this condition holds for several loss functions, and provide theoretical evidence that the known tight SGD stability bounds for convex and non-convex loss functions can be circumvented by HC loss functions, thus partially explaining the generalization of deep neural networks.
Multi-modal AsynDGAN: Learn From Distributed Medical Image Data without Sharing Private Information
As deep learning technologies advance, increasingly more data is necessary to generate general and robust models for various tasks.
Learn distributed GAN with Temporary Discriminators
Our proposed method tackles the challenge of training GAN in the federated learning manner: How to update the generator with a flow of temporary discriminators?
Synthetic Learning: Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image Data
In this paper, we propose a data privacy-preserving and communication efficient distributed GAN learning framework named Distributed Asynchronized Discriminator GAN (AsynDGAN).
