Search Results for author:
Found 32 papers, 12 papers with code
Beyond Pixels: Text Enhances Generalization in Real-World Image Restoration
Generalization has long been a central challenge in real-world image restoration.
SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation
Smartphone agents are increasingly important for helping users control devices efficiently, with (Multimodal) Large Language Model (MLLM)-based approaches emerging as key contenders.
Multimodal Situational Safety
To evaluate this capability, we develop the Multimodal Situational Safety benchmark (MSSBench) to assess the situational safety performance of current MLLMs.
RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models
RestoreAgent autonomously assesses the type and extent of degradation in input images and performs restoration through (1) determining the appropriate restoration tasks, (2) optimizing the task sequence, (3) selecting the most suitable models, and (4) executing the restoration.
Enhancing Neural Subset Selection: Integrating Background Information into Set Representations
Learning neural subset selection tasks, such as compound selection in AI-aided drug discovery, have become increasingly pivotal across diverse applications.
Muffin or Chihuahua? Challenging Multimodal Large Language Models with Multipanel VQA
Our evaluation shows that questions in the MultipanelVQA benchmark pose significant challenges to the state-of-the-art Multimodal Large Language Models (MLLMs) tested, even though humans can attain approximately 99% accuracy on these questions.
Enhancing Evolving Domain Generalization through Dynamic Latent Representations
However, in non-stationary tasks where new domains evolve in an underlying continuous structure, such as time, merely extracting the invariant features is insufficient for generalization to the evolving new domains.
Positional Information Matters for Invariant In-Context Learning: A Case Study of Simple Function Classes
Surprisingly, DeepSet outperforms transformers across a variety of distribution shifts, implying that preserving permutation invariance symmetry to input demonstrations is crucial for OOD ICL.
Does Invariant Graph Learning via Environment Augmentation Learn Invariance?
Invariant graph representation learning aims to learn the invariance among data from different environments for out-of-distribution generalization on graphs.
ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models
For problems where the goal is to infer conclusions beyond image content, which we noted as visual commonsense inference (VCI), VLMs face difficulties, while LLMs, given sufficient visual evidence, can use commonsense to infer the answer well.
Understanding and Improving Feature Learning for Out-of-Distribution Generalization
Moreover, when fed the ERM learned features to the OOD objectives, the invariant feature learning quality significantly affects the final OOD performance, as OOD objectives rarely learn new features.
ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation
Such object navigation tasks usually require large-scale training in visual environments with labeled objects, which generalizes poorly to novel objects in unknown environments.
Navigation as Attackers Wish? Towards Building Robust Embodied Agents under Federated Learning
However, since the local data is inaccessible to the server under federated learning, attackers may easily poison the training data of the local client to build a backdoor in the agent without notice.
JARVIS: A Neuro-Symbolic Commonsense Reasoning Framework for Conversational Embodied Agents
Building a conversational embodied agent to execute real-life tasks has been a long-standing yet quite challenging research goal, as it requires effective human-agent communication, multi-modal understanding, long-range sequential decision making, etc.
Efficient Private SCO for Heavy-Tailed Data via Averaged Clipping
We consider stochastic convex optimization for heavy-tailed data with the guarantee of being differentially private (DP).
Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack
The AutoAttack (AA) has been the most reliable method to evaluate adversarial robustness when considerable computational resources are available.
Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization
Recently, there has been a growing surge of interest in enabling machine learning systems to generalize well to Out-of-Distribution (OOD) data.
An Adaptive Incremental Gradient Method With Support for Non-Euclidean Norms
Stochastic variance reduced methods have shown strong performance in solving finite-sum problems.
FedVLN: Privacy-preserving Federated Vision-and-Language Navigation
Data privacy is a central problem for embodied agents that can perceive the environment, communicate with humans, and act in the real world.
Accelerating Perturbed Stochastic Iterates in Asynchronous Lock-Free Optimization
We show that stochastic acceleration can be achieved under the perturbed iterate framework (Mania et al., 2017) in asynchronous lock-free optimization, which leads to the optimal incremental gradient complexity for finite-sum objectives.
Local Reweighting for Adversarial Training
However, when tested on attacks different from the given attack simulated in training, the robustness may drop significantly (e. g., even worse than no reweighting).
Practical Schemes for Finding Near-Stationary Points of Convex Finite-Sums
In convex optimization, the problem of finding near-stationary points has not been adequately studied yet, unlike other optimality measures such as the function value.
Boosting First-Order Methods by Shifting Objective: New Schemes with Faster Worst-Case Rates
Specifically, instead of tackling the original objective directly, we construct a shifted objective function that has the same minimizer as the original objective and encodes both the smoothness and strong convexity of the original objective in an interpolation condition.
Convolutional Embedding for Edit Distance
Edit-distance-based string similarity search has many applications such as spell correction, data de-duplication, and sequence alignment.
Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning
In particular, at the high compression ratio end, HSQ provides a low per-iteration communication cost of $O(\log d)$, which is favorable for federated learning.
Amortized Nesterov's Momentum: Robust and Lightweight Momentum for Deep Learning
Stochastic Gradient Descent (SGD) with Nesterov's momentum is a widely used optimizer in deep learning, which is observed to have excellent generalization performance.
Norm-Range Partition: A Universal Catalyst for LSH based Maximum Inner Product Search (MIPS)
Recently, locality sensitive hashing (LSH) was shown to be effective for MIPS and several algorithms including $L_2$-ALSH, Sign-ALSH and Simple-LSH have been proposed.
ASVRG: Accelerated Proximal SVRG
This paper proposes an accelerated proximal stochastic variance reduced gradient (ASVRG) method, in which we design a simple and effective momentum acceleration trick.
A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates
Recent years have witnessed exciting progress in the study of stochastic variance reduced gradient methods (e. g., SVRG, SAGA), their accelerated variants (e. g, Katyusha) and their extensions in many different settings (e. g., online, sparse, asynchronous, distributed).
Direct Acceleration of SAGA using Sampled Negative Momentum
Variance reduction is a simple and effective technique that accelerates convex (or non-convex) stochastic optimization.
VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning
In this paper, we propose a simple variant of the original SVRG, called variance reduced stochastic gradient descent (VR-SGD).
Guaranteed Sufficient Decrease for Stochastic Variance Reduced Gradient Optimization
In order to make sufficient decrease for stochastic optimization, we design a new sufficient decrease criterion, which yields sufficient decrease versions of stochastic variance reduction algorithms such as SVRG-SD and SAGA-SD as a byproduct.
