Search Results for author:
Found 27 papers, 11 papers with code
Fine-grained Factual Consistency Assessment for Abstractive Summarization Models
Fact consistency assessment requires the reasoning capability to find subtle clues to identify whether a model-generated summary is consistent with the original document.
Towards Theoretical Understandings of Self-Consuming Generative Models
This paper tackles the emerging challenge of training generative models within a self-consuming loop, wherein successive generations of models are recursively trained on mixtures of real and synthetic data from previous generations.
Mitigating Reward Hacking via Information-Theoretic Reward Modeling
Inspired by this finding, we propose the Integrated Cluster Deviation Score (ICDS), which quantifies deviations in the latent space, as an indicator of reward overoptimization to facilitate the development of online mitigation strategies.
Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases
Then, we surprisingly discover that dormant neurons in our critic model act as a regularization against overoptimization, while active neurons reflect primacy bias in this setting.
FreDF: Learning to Forecast in Frequency Domain
Time series modeling is uniquely challenged by the presence of autocorrelation in both historical and label sequences.
S2M: Converting Single-Turn to Multi-Turn Datasets for Conversational Question Answering
To solve this problem, we propose a novel method to convert single-turn datasets to multi-turn datasets.
Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages
Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL).
The Importance of Multimodal Emotion Conditioning and Affect Consistency for Embodied Conversational Agents
We have conducted a user study with 199 participants to assess how the average person judges the affects perceived from multimodal behaviors that are consistent and inconsistent with respect to a driving affect.
Are Large Language Models Really Robust to Word-Level Perturbations?
Notably, we are surprised to discover that robustness tends to decrease as fine-tuning (SFT and RLHF) is conducted.
Instruction Tuning for Large Language Models: A Survey
This paper surveys research works in the quickly advancing field of instruction tuning (IT), a crucial technique to enhance the capabilities and controllability of large language models (LLMs).
Robust Audio Anti-Spoofing with Fusion-Reconstruction Learning on Multi-Order Spectrograms
Robust audio anti-spoofing has been increasingly challenging due to the recent advancements on deepfake techniques.
Fine-grained building roof instance segmentation based on domain adapted pretraining and composite dual-backbone
The diversity of building architecture styles of global cities situated on various landforms, the degraded optical imagery affected by clouds and shadows, and the significant inter-class imbalance of roof types pose challenges for designing a robust and accurate building roof instance segmentor.
HGDNet: A Height-Hierarchy Guided Dual-Decoder Network for Single View Building Extraction and Height Estimation
Unifying the correlative single-view satellite image building extraction and height estimation tasks indicates a promising way to share representations and acquire generalist model for large-scale urban 3D reconstruction.
Image Captions are Natural Prompts for Text-to-Image Models
With the rapid development of Artificial Intelligence Generated Content (AIGC), it has become common practice in many learning tasks to train or fine-tune large models on synthetic data due to the data-scarcity and privacy leakage problems.
ReGeneration Learning of Diffusion Models with Rich Prompts for Zero-Shot Image Translation
To ensure consistent preservation of the shape during image editing, we propose cross-attention guidance based on regeneration learning.
Event-based Simultaneous Localization and Mapping: A Comprehensive Survey
This paper presents a timely and comprehensive review of event-based vSLAM algorithms that exploit the benefits of asynchronous and irregular event streams for localization and mapping tasks.
Multi-task Adversarial Learning for Semi-supervised Trajectory-User Linking
We first project users and trajectories into the common latent feature space through learning a projection function (generator) to minimize the distance between the user distribution and the trajectory distribution.
Criteria Comparative Learning for Real-scene Image Super-Resolution
Inspired by the observation that the contrastive relationship could also exist between the criteria, in this work, we propose a novel training paradigm for RealSR, named Criteria Comparative Learning (Cria-CL), by developing contrastive losses defined on criteria instead of image patches.
JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes
A naive way is to accomplish them independently in a sequential or parallel manner, but there are many drawbacks, i. e., 1) the depth and VO results suffer from the inherent scale ambiguity issue; 2) the BEV layout is directly predicted from the front-view image without using any depth-related information, although the depth map contains useful geometry clues for inferring scene layouts.
Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics
Unsupervised monocular depth and ego-motion estimation has drawn extensive research attention in recent years.
Exploring Negatives in Contrastive Learning for Unpaired Image-to-Image Translation
Recently, contrastive learning (CL) has been used to further investigate the image correspondence in unpaired image translation by using patch-based positive/negative learning.
Information-Theoretic Odometry Learning
In this paper, we propose a unified information theoretic framework for learning-motivated methods aimed at odometry estimation, a crucial component of many robotics and vision tasks such as navigation and virtual reality where relative camera poses are required in real time.
Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World
In this work, we propose VRVO, a novel framework for retrieving the absolute scale from virtual data that can be easily obtained from modern simulation environments, whereas in the real domain no stereo or ground-truth data are required in either the training or inference phases.
Multimodal Representations Learning Based on Mutual Information Maximization and Minimization and Identity Embedding for Multimodal Sentiment Analysis
Multimodal sentiment analysis (MSA) is a fundamental complex research problem due to the heterogeneity gap between different modalities and the ambiguity of human emotional expression.
Continuation Newton methods with deflation techniques for global optimization problems
The global minimum point of an optimization problem is of interest in engineering fields and it is difficult to be found, especially for a nonconvex large-scale optimization problem.
GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer
Non-parallel text style transfer has attracted increasing research interests in recent years.
Community Preserved Social Graph Publishing with Node Differential Privacy
Community structure, which is an important global pattern of nodes, is a crucial data utility as it serves as fundamental operations for many graph analysis tasks.
Cryptography and Security
