Search Results for author:
Found 63 papers, 22 papers with code
ZhichunRoad at SemEval-2022 Task 2: Adversarial Training and Contrastive Learning for Multiword Representations
This paper presents our contribution to the SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding. We explore the impact of three different pre-trained multilingual language models in the SubTaskA. By enhancing the model generalization and robustness, we use the exponential moving average (EMA) method and the adversarial attack strategy. In SubTaskB, we add an effective cross-attention module for modeling the relationships of two sentences. We jointly train the model with a contrastive learning objective and employ a momentum contrast to enlarge the number of negative pairs. Additionally, we use the alignment and uniformity properties to measure the quality of sentence embeddings. Our approach obtained competitive results in both subtasks.
Example-Guided Image Synthesis using Masked Spatial-Channel Attention and Self-Supervision
Example-guided image synthesis has recently been attempted to synthesize an image from a semantic label map and an exemplary image.
A Multi-modal one-class generative adversarial network for anomaly detection in manufacturing
Since the generated samples simulate the low density area for each modal, the discriminator could directly detect anomalies from normal data.
EvTTC: An Event Camera Dataset for Time-to-Collision Estimation
To explore the potential of event cameras in the above-mentioned challenging cases, we propose EvTTC, which is, to the best of our knowledge, the first multi-sensor dataset focusing on TTC tasks under high-relative-speed scenarios.
DIVE: Taming DINO for Subject-Driven Video Editing
Specifically, to ensure temporal motion consistency, DIVE employs DINO features to align with the motion trajectory of the source video.
MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis
MetaShadow combines the strengths of two cooperative components: Shadow Analyzer, for object-centered shadow detection and removal, and Shadow Synthesizer, for reference-based controllable shadow synthesis.
RRM: Robust Reward Model Training Mitigates Reward Hacking
Our RRM improves the performance of a pairwise reward model trained on Gemma-2-9b-it, on RewardBench, increasing accuracy from 80. 61% to 84. 15%.
From Lists to Emojis: How Format Bias Affects Model Alignment
In this work, we extend the study of biases in preference learning beyond the commonly recognized length bias, offering a comprehensive analysis of a wider range of format biases.
Semantics Preserving Emoji Recommendation with Large Language Models
Existing emoji recommendation methods are primarily evaluated based on their ability to match the exact emoji a user chooses in the original text.
GroundingBooth: Grounding Text-to-Image Customization
In this work, we introduce GroundingBooth, a framework that achieves zero-shot instance-level spatial grounding on both foreground subjects and background objects in the text-to-image customization task.
Building Math Agents with Multi-Turn Iterative Preference Learning
Recent studies have shown that large language models' (LLMs) mathematical problem-solving capabilities can be enhanced by integrating external tools, such as code interpreters, and employing multi-turn Chain-of-Thought (CoT) reasoning.
Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts
The trained RM serves as a proxy for human preferences.
BeamVQ: Aligning Space-Time Forecasting Model via Self-training on Physics-aware Metrics
Data-driven deep learning has emerged as the new paradigm to model complex physical space-time systems.
RLHF Workflow: From Reward Modeling to Online RLHF
We present the workflow of Online Iterative Reinforcement Learning from Human Feedback (RLHF) in this technical report, which is widely reported to outperform its offline counterpart by a large margin in the recent large language model (LLM) literature.
DPO Meets PPO: Reinforced Token Optimization for RLHF
For its practical implementation, \texttt{RTO} innovatively integrates Direct Preference Optimization (DPO) and PPO.
SwapAnything: Enabling Arbitrary Object Swapping in Personalized Visual Editing
Compared with existing methods for personalized subject swapping, SwapAnything has three unique advantages: (1) precise control of arbitrary objects and parts rather than the main subject, (2) more faithful preservation of context pixels, (3) better adaptation of the personalized concept to the image.
IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation
Generative object compositing emerges as a promising new avenue for compositional image editing.
Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization
To mitigate this issue, we propose Bootstrapped Preference Optimization (BPO), which conducts preference learning with datasets containing negative responses bootstrapped from the model itself.
Ranked #100 on
Visual Question Answering
on MM-Vet
Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards
Additionally, DPA models user preferences as directions (i. e., unit vectors) in the reward space to achieve user-dependent preference control.
Diffusion Model-Based Image Editing: A Survey
In this survey, we provide an exhaustive overview of existing methods using diffusion models for image editing, covering both theoretical and practical aspects in the field.
Online Iterative Reinforcement Learning from Human Feedback with General Preference Model
We investigate Reinforcement Learning from Human Feedback (RLHF) in the context of a general preference oracle.
Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint
We investigate its behavior in three distinct settings -- offline, online, and hybrid -- and propose efficient algorithms with finite-sample theoretical guarantees.
Earthfarseer: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model
Efficiently modeling spatio-temporal (ST) physical processes and observations presents a challenging problem for the deep learning community.
Relightful Harmonization: Lighting-aware Portrait Background Replacement
Portrait harmonization aims to composite a subject into a new background, adjusting its lighting and color to ensure harmony with the background scene.
Windformer:Bi-Directional Long-Distance Spatio-Temporal Network For Wind Speed Prediction
History and future time information includes the trend of airflow changes, whether this dynamic information can be utilized will also affect the prediction effect.
Mitigating the Alignment Tax of RLHF
Building on the analysis and the observation that averaging different layers of the transformer leads to significantly different alignment-forgetting trade-offs, we propose Heterogeneous Model Averaging (HMA) to Heterogeneously find various combination ratios of model layers.
AI-GOMS: Large AI-Driven Global Ocean Modeling System
Here, we present AI-GOMS, a large AI-driven global ocean modeling system, for accurate and efficient global ocean daily prediction.
LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models
As the number of available foundation models and specialized tasks keeps growing, the job of training scientific language models becomes highly nontrivial.
Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources
Then, a novel HetPEVI algorithm is proposed, which simultaneously considers the sample uncertainties from a finite number of data samples per data source and the source uncertainties due to a finite number of available data sources.
Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration
To achieve this, existing sample-efficient online RL algorithms typically consist of three components: estimation, planning, and exploration.
Reward Teaching for Federated Multi-armed Bandits
Rigorous analyses demonstrate that when facing clients with UCB1, TWL outperforms TAL in terms of the dependencies on sub-optimality gaps thanks to its adaptive design.
RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
Utilizing a reward model and a sufficient number of samples, our approach selects the high-quality samples, discarding those that exhibit undesired behavior, and subsequently enhancing the model by fine-tuning on these filtered samples.
InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning
First, we learn the general concept of the input images by converting them to a textual token with a learnable image encoder.
Diffusion Personalization Tuning Free
Personalized Image Generation
+1
ZhichunRoad at Amazon KDD Cup 2022: MultiTask Pre-Training for E-Commerce Product Search
In this paper, we propose a robust multilingual model to improve the quality of search results.
Koopman neural operator as a mesh-free solver of non-linear partial differential equations
By approximating the Koopman operator, an infinite-dimensional operator governing all possible observations of the dynamic system, to act on the flow mapping of the dynamic system, we can equivalently learn the solution of a non-linear PDE family by solving simple linear prediction problems.
KoopmanLab: machine learning for solving complex physics equations
To overcome this challenge, we present KoopmanLab, an efficient module of the Koopman neural operator family, for learning PDEs without analytic solutions or closed forms.
Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes
In this paper, we consider the contextual bandit with general function approximation and propose a computationally efficient algorithm to achieve a regret of $\tilde{O}(\sqrt{T}+\zeta)$.
GEC: A Unified Framework for Interactive Decision Making in MDP, POMDP, and Beyond
The proposed algorithm modifies the standard posterior sampling algorithm in two aspects: (i) we use an optimistic prior distribution that biases towards hypotheses with higher values and (ii) a loglikelihood function is set to be the empirical loss evaluated on the historical data, where the choice of loss function supports both model-free and model-based learning.
A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games
Existing studies on provably efficient algorithms for Markov games (MGs) almost exclusively build on the "optimism in the face of uncertainty" (OFU) principle.
Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game
We also extend our techniques to the two-player zero-sum Markov games (MGs), and establish a new performance lower bound for MGs, which tightens the existing result, and verifies the nearly minimax optimality of the proposed algorithm.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Breast Cancer Induced Bone Osteolysis Prediction Using Temporal Variational Auto-Encoders
Its ability of predicting the development of bone lesions in cancer-invading bones can assist in assessing the risk of impending fractures and choosing proper treatments in breast cancer bone metastasis.
Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets
When the dataset does not have uniform coverage over all policy pairs, finding an approximate NE involves challenges in three aspects: (i) distributional shift between the behavior policy and the optimal policy, (ii) function approximation to handle large state space, and (iii) minimax optimization for equilibrium solving.
(Almost) Free Incentivized Exploration from Decentralized Learning Agents
In this work, we break this barrier and study incentivized exploration with multiple and long-term strategic agents, who have more complicated behaviors that often appear in real-world applications.
Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization
In this paper, we propose BEACON -- Batched Exploration with Adaptive COmmunicatioN -- that closes this gap.
Distributional Reinforcement Learning for Multi-Dimensional Reward Functions
To fully inherit the benefits of distributional RL and hybrid reward architectures, we introduce Multi-Dimensional Distributional DQN (MD3QN), which extends distributional RL to model the joint return distribution from multiple reward sources.
Distributional Reinforcement Learning
reinforcement-learning
+2
GANet: Glyph-Attention Network for Few-Shot Font Generation
Font generation is a valuable but challenging task, it is time consuming and costly to design font libraries which cover all glyphs with various styles.
Heterogeneous Network Embedding for Deep Semantic Relevance Match in E-commerce Search
We propose in this paper a novel Second-order Relevance, which is fundamentally different from the previous First-order Relevance, to improve result relevance prediction.
PMGT-VR: A decentralized proximal-gradient algorithmic framework with variance reduction
This paper considers the decentralized composite optimization problem.
BERT2DNN: BERT Distillation with Massive Unlabeled Data for Online E-Commerce Search
Relevance has significant impact on user experience and business profit for e-commerce search platform.
Image Sentiment Transfer
In this paper, we propose an effective and flexible framework that performs image sentiment transfer at the object level.
LinksIQ: Robust and Efficient Modulation Recognition with Imperfect Spectrum Scans
While critical for the practical progress of spectrum sharing, modulation recognition has so far been investigated under unrealistic assumptions: (i) a transmitter's bandwidth must be scanned alone and in full, (ii) prior knowledge of the technology must be available and (iii) a transmitter must be trustworthy.
Unsupervised Low-light Image Enhancement with Decoupled Networks
In this paper, we tackle the problem of enhancing real-world low-light images with significant noise in an unsupervised fashion.
Example-Guided Image Synthesis across Arbitrary Scenes using Masked Spatial-Channel Attention and Self-Supervision
Example-guided image synthesis has recently been attempted to synthesize an image from a semantic label map and an exemplary image.
Decentralized Multi-player Multi-armed Bandits with No Collision Information
The decentralized stochastic multi-player multi-armed bandit (MP-MAB) problem, where the collision information is not available to the players, is studied in this paper.
Fine-grained Image-to-Image Transformation towards Visual Recognition
In this paper, we aim at transforming an image with a fine-grained category to synthesize new images that preserve the identity of the input image, which can thereby benefit the subsequent fine-grained image recognition and few-shot learning tasks.
Example-Guided Scene Image Synthesis using Masked Spatial-Channel Attention and Patch-Based Self-Supervision
Example-guided image synthesis has been recently attempted to synthesize an image from a semantic label map and an exemplary image.
Foreground-aware Image Inpainting
We show that by such disentanglement, the contour completion model predicts reasonable contours of objects, and further substantially improves the performance of image inpainting.
CariGAN: Caricature Generation through Weakly Paired Adversarial Learning
Furthermore, an attention mechanism is introduced to encourage our model to focus on the key facial parts so that more vivid details in these regions can be generated.
Focus, Segment and Erase: An Efficient Network for Multi-Label Brain Tumor Segmentation
In multi-label brain tumor segmentation, class imbalance and inter-class interference are common and challenging problems.
Regional Interactive Image Segmentation Networks
The interactive image segmentation model allows users to iteratively add new inputs for refinement until a satisfactory result is finally obtained.
Ranked #10 on
Interactive Segmentation
on SBD
(NoC@85 metric)
Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks
The first stage generates videos of realistic contents for each frame.
