Search Results for author:
Found 102 papers, 45 papers with code
Recovering a Molecule's 3D Dynamics from Liquid-phase Electron Microscopy Movies
To our knowledge, our work is the first attempt to directly recover 3D structures of a temporally-varying particle from liquid-phase EM movies.
Cryogenic Electron Microscopy (cryo-EM)
Object Reconstruction
+1
Enhancing Performance on Seen and Unseen Dialogue Scenarios using Retrieval-Augmented End-to-End Task-Oriented System
End-to-end task-oriented dialogue (TOD) systems have achieved promising performance by leveraging sophisticated natural language understanding and natural language generation capabilities of pre-trained models.
BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents
The massive successes of large language models (LLMs) encourage the emerging exploration of LLM-augmented Autonomous Agents (LAAs).
Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
This demonstrates that using policy gradient optimization to improve language agents, for which we believe our work is one of the first, seems promising and can be applied to optimize other models in the agent architecture to enhance agent performances over time.
DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI
Despite advancements in conversational AI, language models encounter challenges to handle diverse conversational tasks, and existing dialogue dataset collections often lack diversity and comprehensiveness.
REX: Rapid Exploration and eXploitation for AI Agents
In this paper, we propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX.
Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight
This paper studies the sample-efficiency of learning in Partially Observable Markov Decision Processes (POMDPs), a challenging problem in reinforcement learning that is known to be exponentially hard in the worst-case.
Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection
As an example, we use the post-ICL validation mechanism to construct a transformer that can perform nearly Bayes-optimal ICL on a challenging task -- noisy linear models with mixed noise levels.
SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds
We achieve so by introducing efficient network architecture and improving step distillation.
UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
Visual generative foundation models such as Stable Diffusion show promise in navigating these goals, especially when prompted with arbitrary languages.
Zero-shot Item-based Recommendation via Multi-task Product Knowledge Graph Pre-Training
This paper presents a novel paradigm for the Zero-Shot Item-based Recommendation (ZSIR) task, which pre-trains a model on product knowledge graph (PKG) to refine the item features from PLMs.
ChatGPT-Like Large-Scale Foundation Models for Prognostics and Health Management: A Survey and Roadmaps
Prognostics and health management (PHM) technology plays a critical role in industrial production and equipment maintenance by identifying and predicting possible equipment failures and damages, thereby allowing necessary maintenance measures to be taken to enhance equipment service life and reliability while reducing production costs and downtime.
PTC-Net: Point-Wise Transformer with Sparse Convolution Network for Place Recognition
To address this issue, we propose a novel Point-wise Transformer with sparse Convolution (PTC).
Towards More Robust and Accurate Sequential Recommendation with Cascade-guided Adversarial Training
Two properties unique to the nature of sequential recommendation models may impair their robustness - the cascade effects induced during training and the model's tendency to rely too heavily on temporal information.
Frame Flexible Network
To fix this issue, we propose a general framework, named Frame Flexible Network (FFN), which not only enables the model to be evaluated at different frames to adjust its computation, but also reduces the memory costs of storing multiple models significantly.
ABC: Attention with Bilinear Correlation for Infrared Small Target Detection
Infrared small target detection (ISTD) has a wide range of applications in early warning, rescue, and guidance.
Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution
Second, existing pruning methods generally operate upon a pre-trained network for the sparse structure determination, hard to get rid of dense model training in the traditional SR paradigm.
HIVE: Harnessing Human Feedback for Instructional Visual Editing
Incorporating human feedback has been shown to be crucial to align text generated by large language models to human preferences.
On the Unlikelihood of D-Separation
We then provide an analytic average case analysis of the PC Algorithm for causal discovery, as well as a variant of the SGS Algorithm we call UniformSGS.
Image as Set of Points
Context clusters (CoCs) view an image as a set of unorganized points and extract features via simplified clustering algorithm.
Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems
Prior works mainly focus on adopting advanced RL techniques to train the ToD agents, while the design of the reward function is not well studied.
Improved Online Conformal Prediction via Strongly Adaptive Online Learning
We prove that our methods achieve near-optimal strongly adaptive regret for all interval lengths simultaneously, and approximately valid coverage.
Lower Bounds for Learning in Revealing POMDPs
However, the fundamental limits for learning in revealing POMDPs are much less understood, with existing lower bounds being rather preliminary and having substantial gaps from the current best upper bounds.
Local Contrast and Global Contextual Information Make Infrared Small Object Salient Again
On the other hand, FFC can gain image-level receptive fields and extract global information while preventing small objects from being overwhelmed. Experiments on several public datasets demonstrate that our method significantly outperforms the state-of-the-art ISOS models, and can provide useful guidelines for designing better ISOS deep models.
Salesforce CausalAI Library: A Fast and Scalable Framework for Causal Analysis of Time Series and Tabular Data
Finally, we provide a user interface (UI) that allows users to perform causal analysis on data without coding.
Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning
The state of neural network pruning has been noticed to be unclear and even confusing for a while, largely due to "a lack of standardized benchmarks and metrics" [3].
A Close Look at Spatial Modeling: From Attention to Convolution
Vision Transformers have shown great promise recently for many vision tasks due to the insightful architecture design and attention mechanism.
Real-Time Neural Light Field on Mobile Devices
Nevertheless, to reach a similar rendering quality as NeRF, the network in NeLF is designed with intensive computation, which is not mobile-friendly.
Look More but Care Less in Video Recognition
To tackle this problem, we propose Ample and Focal Network (AFNet), which is composed of two branches to utilize more frames but with less computation.
Parameter-Efficient Masking Networks
We validate the potential of PEMN learning masks on random weights with limited unique values and test its effectiveness for a new compression paradigm based on different network architectures.
Generating Negative Samples for Sequential Recommendation
Due to the dynamics of users' interests and model updates during training, considering randomly sampled items from a user's non-interacted item set as negatives can be uninformative.
Trainability Preserving Neural Pruning
Moreover, results on ImageNet-1K with ResNets suggest that TPP consistently performs more favorably against other top-performing structured pruning approaches.
Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain
This paper proposes a privacy-preserving face recognition method using differential privacy in the frequency domain.
Policy Optimization for Markov Games: Unified Framework and Faster Convergence
Next, we show that this framework instantiated with the Optimistic Follow-The-Regularized-Leader (OFTRL) algorithm at each state (and smooth value updates) can find an $\mathcal{\widetilde{O}}(T^{-5/6})$ approximate NE in $T$ iterations, and a similar algorithm with slightly modified value update rule achieves a faster $\mathcal{\widetilde{O}}(T^{-1})$ convergence rate.
STN: Scalable Tensorizing Networks via Structure-Aware Training and Adaptive Compression
Deep neural networks (DNNs) have delivered a remarkable performance in many tasks of computer vision.
R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis
On the other hand, Neural Light Field (NeLF) presents a more straightforward representation over NeRF in novel view synthesis -- the rendering of a pixel amounts to one single forward pass without ray-marching.
CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
To democratize this, we train and release a family of large language models up to 16. 1B parameters, called CODEGEN, on natural language and programming language data, and open source the training library JAXFORMER.
Ranked #1 on
Program Synthesis
on HumanEval
Converse: A Tree-Based Modular Task-Oriented Dialogue System
At the core of the struggle is the need to script every single turn of interactions between the bot and the human user.
Dual Lottery Ticket Hypothesis
In this work, we regard the winning ticket from LTH as the subnetwork which is in trainable condition and its performance as our benchmark, then go from a complementary direction to articulate the Dual Lottery Ticket Hypothesis (DLTH): Randomly selected subnetworks from a randomly initialized dense network can be transformed into a trainable condition and achieve admirable performance compared with LTH -- random tickets in a given lottery pool can be transformed into winning tickets.
Efficient and Differentiable Conformal Prediction with General Function Classes
Experiments show that our algorithm is able to learn valid prediction sets and improve the efficiency significantly over existing approaches in several applications such as prediction intervals with improved length, minimum-volume prediction sets for multi-output regression, and label prediction sets for image classification.
Semi-supervised Domain Adaptive Structure Learning
Semi-supervised domain adaptation (SSDA) is quite a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains.
Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation
For slow learning of graph similarity, this paper proposes a novel early-fusion approach by designing a co-attention-based feature fusion network on multilevel GNN features.
Aligned Structured Sparsity Learning for Efficient Image Super-Resolution
To address the above issues, we propose aligned structured sparsity learning (ASSL), which introduces a weight normalization layer and applies $L_2$ regularization to the scale parameters for sparsity.
Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
We first show that this chaotic behavior exists even along the training optimization trajectory of a single model, and propose a simple model averaging protocol that both significantly boosts domain generalization and diminishes the impact of stochasticity by improving the rank correlation between the in-domain validation accuracy and out-domain test accuracy, which is crucial for reliable early stopping.
Ranked #3 on
Domain Generalization
on TerraIncognita
Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE
Wasserstein autoencoder (WAE) shows that matching two distributions is equivalent to minimizing a simple autoencoder (AE) loss under the constraint that the latent space of this AE matches a pre-specified prior distribution.
Learning Rich Nearest Neighbor Representations from Self-supervised Ensembles
Pretraining convolutional neural networks via self-supervision, and applying them in transfer learning, is an incredibly fast-growing field that is rapidly and iteratively improving performance across practically all image domains.
Continuous Conditional Random Field Convolution for Point Cloud Segmentation
Furthermore, we build an encoder-decoder network based on the proposed continuous CRF graph convolution (CRFConv), in which the CRFConv embedded in the decoding layers can restore the details of high-level features that were lost in the encoding stage to enhance the location ability of the network, thereby benefiting segmentation.
Understanding the Success of Knowledge Distillation -- A Data Augmentation Perspective
We achieve new state-of-the-art accuracy by using the original KD loss armed with stronger augmentation schemes, compared to existing state-of-the-art methods that employ more advanced distillation losses.
Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning
Specifically, for the layers connected by the same residual, we select the filters of the same indices as unimportant filters.
Structured Pruning Meets Orthogonality
In this paper, we present \emph{orthogonality preserving pruning} (OPP), a regularization-based structured pruning method that maintains the dynamical isometry during pruning.
Rethinking Again the Value of Network Pruning -- A Dynamical Isometry Perspective
Several recent works questioned the value of inheriting weight in structured neural network pruning because they empirically found training from scratch can match or even outperform finetuning a pruned model.
Merlion: A Machine Learning Library for Time Series
We introduce Merlion, an open-source machine learning library for time series.
Multi-Tensor Network Representation for High-Order Tensor Completion
In particular, each component can be represented as multilinear connections over several latent factors and naturally mapped to a specific tensor network (TN) topology.
WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU
We present WarpDrive, a flexible, lightweight, and easy-to-use open-source RL framework that implements end-to-end deep multi-agent RL on a single GPU (Graphics Processing Unit), built on PyCUDA and PyTorch.
Rethinking Adam: A Twofold Exponential Moving Average Approach
The intuition is that gradient with momentum contains more accurate directional information and therefore its second moment estimation is a more favorable option for learning rate scaling than that of the raw gradient.
Understanding the Under-Coverage Bias in Uncertainty Estimation
Estimating the data uncertainty in regression tasks is often done by learning a quantile function or a prediction interval of the true label conditioned on the input.
Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning
This offline result is the first that matches the sample complexity lower bound in this setting, and resolves a recent open question in offline RL.
Evaluating State-of-the-Art Classification Models Against Bayes Optimality
Moreover, we show that by varying the temperature of the learned flow models, we can generate synthetic datasets that closely resemble standard benchmark datasets, but with almost any desired Bayes error.
Dynamical Isometry: The Missing Ingredient for Neural Network Pruning
This paper is meant to explain it through the lens of dynamical isometry [42].
Recent Advances on Neural Network Pruning at Initialization
Neural network pruning typically removes connections or neurons from a pretrained converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to prune a randomly initialized network.
Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games
Real world applications such as economics and policy making often involve solving multi-agent games with two unique features: (1) The agents are inherently asymmetric and partitioned into leaders and followers; (2) The agents have different reward functions, thus the game is general-sum.
Local Calibration: Metrics and Recalibration
In this work, we propose the local calibration error (LCE) to span the gap between average and individual reliability.
Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
Modern machine learning models with high accuracy are often miscalibrated -- the predicted top probability does not reflect the actual accuracy, and tends to be over-confident.
Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss
Despite the stateof-the-art performance achieved by Convolutional Neural Networks (CNNs) for automatic segmentation of OARs, existing methods do not provide uncertainty estimation of the segmentation results for treatment planning, and their accuracy is still limited by several factors, including the low contrast of soft tissues in CT, highly imbalanced sizes of OARs and large inter-slice spacing.
Use or Misuse of NMR to Test Molecular Mobility during Chemical Reaction
With raw NMR spectra available in a public depository, we confirm boosted mobility during the click chemical reaction (Science 2020, 369, 537) regardless of the order of magnetic field gradient (linearly-increasing, linearly-decreasing, random sequence).
Soft Condensed Matter
Momentum Contrastive Autoencoder
Quantitatively, we show that our algorithm achieves a new state-of-the-art FID of 54. 36 on CIFAR-10, and performs competitively with existing models on CelebA in terms of FID score.
Improved Uncertainty Post-Calibration via Rank Preserving Transforms
In this paper, we propose Neural Rank Preserving Transforms (NRPT), a new post-calibration method that adjusts the output probabilities of a trained classifier using a calibrator of higher capacity, while maintaining its prediction accuracy.
Context Reasoning Attention Network for Image Super-Resolution
However, the basic convolutional layer in CNNs is designed to extract local patterns, lacking the ability to model global context.
Neural Bayes: A Generic Parameterization Method for Unsupervised Learning
Disjoint Manifold Separation: Neural Bayes allows us to formulate an objective which can optimally label samples from disjoint manifolds present in the support of a continuous distribution.
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
The early phase of training a deep neural network has a dramatic effect on the local curvature of the loss function.
Szegő kernel asymptotics on some non-compact complete CR manifolds
We establish Szeg\H{o} kernel asymptotic expansions on non-compact strictly pseudoconvex complete CR manifolds with transversal CR $\mathbb{R}$-action under certain natural geometric conditions.
Complex Variables Differential Geometry
Neural Pruning via Growing Regularization
Regularization has long been utilized to learn sparsity in deep neural network pruning.
An Event Correlation Filtering Method for Fake News Detection
To improve the detection performance of fake news, we take advantage of the event correlations of news and propose an event correlation filtering method (ECFM) for fake news detection, mainly consisting of the news characterizer, the pseudo label annotator, the event credibility updater, and the news entropy selector.
Multi-head Knowledge Distillation for Model Compression
We add loss terms for training the student that measure the dissimilarity between student and teacher outputs of the auxiliary classifiers.
What Makes a "Good" Data Augmentation in Knowledge Distillation -- A Statistical Perspective
What makes a "good" DA in KD?
Unsupervised Paraphrasing with Pretrained Language Models
To enforce a surface form dissimilar from the input, whenever the language model emits a token contained in the source sequence, DB prevents the model from outputting the subsequent source token for the next generation step.
How Important is the Train-Validation Split in Meta-Learning?
A common practice in meta-learning is to perform a train-validation split (\emph{train-val method}) where the prior adapts to the task on one split of the data, and the resulting predictor is evaluated on another split.
Towards Understanding Hierarchical Learning: Benefits of Neural Representations
When the trainable network is the quadratic Taylor model of a wide two-layer network, we show that neural representation can achieve improved sample complexities compared with the raw input: For learning a low-rank degree-$p$ polynomial ($p \geq 4$) in $d$ dimension, neural representation requires only $\tilde{O}(d^{\lceil p/2 \rceil})$ samples, while the best-known sample complexity upper bound for the raw input is $\tilde{O}(d^{p-1})$.
Collaborative Distillation for Ultra-Resolution Universal Style Transfer
In this work, we present a new knowledge distillation method (named Collaborative Distillation) for encoder-decoder based neural style transfer to reduce the convolutional filters.
MNN: A Universal and Efficient Inference Engine
Deploying deep learning models on mobile devices draws more and more attention recently.
Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning
Disjoint Manifold Labeling: Neural Bayes allows us to formulate an objective which can optimally label samples from disjoint manifolds present in the support of a continuous distribution.
Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width
We propose \emph{Taylorized training} as an initiative towards better understanding neural network training at finite width.
Contradictory Structure Learning for Semi-supervised Domain Adaptation
Current adversarial adaptation methods attempt to align the cross-domain features, whereas two challenges remain unsolved: 1) the conditional distribution mismatch and 2) the bias of the decision boundary towards the source domain.
MKD: a Multi-Task Knowledge Distillation Approach for Pretrained Language Models
Our approach is model agnostic and can be easily applied on different future teacher model architectures.
Global Capacity Measures for Deep ReLU Networks via Path Sampling
Classical results on the statistical complexity of linear models have commonly identified the norm of the weights $\|w\|$ as a fundamental capacity measure.
Miss Detection vs. False Alarm: Adversarial Learning for Small Object Segmentation in Infrared Images
Second, the adversarial training of the two models naturally produces a delicate balance of MD and FA, and low rates for both MD and FA could be achieved at Nash equilibrium.
DIME: AN INFORMATION-THEORETIC DIFFICULTY MEASURE FOR AI DATASETS
Empirically, we estimate this lower bound using a neural network to compute DIME.
On the Generalization Gap in Reparameterizable Reinforcement Learning
For this problem class, estimating the expected return is efficient and the trajectory can be computed deterministically given peripheral random variables, which enables us to study reparametrizable RL using supervised learning and transfer learning theory.
Triplet Distillation for Deep Face Recognition
Convolutional neural networks (CNNs) have achieved a great success in face recognition, which unfortunately comes at the cost of massive computation and storage consumption.
Multi-Task Learning for Semantic Parsing with Cross-Domain Sketch
Semantic parsing which maps a natural language sentence into a formal machine-readable representation of its meaning, is highly constrained by the limited annotated training data.
Structured Pruning for Efficient ConvNets via Incremental Regularization
Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance loss.
Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method
Despite enjoying extensive applications in video analysis, three-dimensional convolutional neural networks (3D CNNs)are restricted by their massive computation and storage consumption.
Shubnikov-de Haas and de Haas-van Alphen oscillations in topological semimetal CaAl4
An electron-type quasi-2D Fermi surface is found by the angle-dependent Shubnikov-de Haas oscillations, de Haas-van Alphen oscillations and the first-principles calculations.
Materials Science Mesoscale and Nanoscale Physics
Identifying Generalization Properties in Neural Networks
In particular, we prove that model generalization ability is related to the Hessian, the higher-order "smoothness" terms characterized by the Lipschitz constant of the Hessian, and the scales of the parameters.
Structured Pruning for Efficient ConvNets via Incremental Regularization
Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance degrade.
Adaptive Dropout with Rademacher Complexity Regularization
We propose a novel framework to adaptively adjust the dropout rates for the deep neural network based on a Rademacher complexity bound.
Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
Unlike existing deterministic pruning approaches, where unimportant weights are permanently eliminated, SPP introduces a pruning probability for each weight, and pruning is guided by sampling from the pruning probabilities.
Exploiting Color Name Space for Salient Object Detection
In this paper, we will investigate the contribution of color names for the task of salient object detection.
Synthesizing Training Images for Boosting Human 3D Pose Estimation
Human 3D pose estimation from a single image is a challenging task with numerous applications.
A Batchwise Monotone Algorithm for Dictionary Learning
Unlike the state-of-the-art dictionary learning algorithms which impose sparsity constraints on a sample-by-sample basis, we instead treat the samples as a batch, and impose the sparsity constraint on the whole.
