Search Results for author:
Found 44 papers, 9 papers with code
Regularized Multi-LLMs Collaboration for Enhanced Score-based Causal Discovery
As the significance of understanding the cause-and-effect relationships among variables increases in the development of modern systems and algorithms, learning causality from observational data has become a preferred and efficient approach over conducting randomized control trials.
Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens
Our first approach is Batch-Scheduled Sampling, where, during training, we stochastically choose between the ground-truth token from the dataset and the model's own generated token as input to predict the next token.
AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents
On the other hand, there has been limited study on the misalignment between a web agent's observation/action representation and the pre-training data of the LLM it's based on.
Causality-Aware Transformer Networks for Robotic Navigation
We address these constraints by initially exploring the unique differences between Navigation tasks and other sequential data tasks through the lens of Causality, presenting a causal framework to elucidate the inadequacies of conventional sequential methods for Navigation.
EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data
Prior work in skill-based RL either requires expert supervision to define useful skills, which is hard to scale, or learns a skill-space from offline data with heuristics that limit the adaptability of the skills, making them difficult to transfer during downstream RL.
Learning the Target Network in Function Space
We focus on the task of learning the value function in the reinforcement learning (RL) setting.
Modeling Pedestrian Intrinsic Uncertainty for Multimodal Stochastic Trajectory Prediction via Energy Plan Denoising
In response, we propose the Energy Plan Denoising (EPD) model for stochastic trajectory prediction.
Multi-agent Traffic Prediction via Denoised Endpoint Distribution
The exploration of high-speed movement by robots or road traffic agents is crucial for autonomous driving and navigation.
Cognitive Bias in Decision-Making with LLMs
Large language models (LLMs) offer significant potential as tools to support an expanding range of decision-making tasks.
InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment
In this paper, we propose InstructGraph, a framework that empowers LLMs with the abilities of graph reasoning and generation by instruction tuning and preference alignment.
Attention-aware Social Graph Transformer Networks for Stochastic Trajectory Prediction
We propose Attention-aware Social Graph Transformer Networks for multi-modal trajectory prediction.
Precipitation Prediction Using an Ensemble of Lightweight Learners
Specifically, the framework consists of a precipitation predictor with multiple lightweight heads (learners) and a controller that combines the outputs from these heads.
Parrot-Trained Adversarial Examples: Pushing the Practicality of Black-Box Audio Attacks against Speaker Recognition Models
Motivated by recent advancements in voice conversion (VC), we propose to use the one short sentence knowledge to generate more synthetic speech samples that sound like the target speaker, called parrot speech.
MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation
Curated datasets for healthcare are often limited due to the need of human annotations from experts.
TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
Inspired by recent advancements in parameter-efficient fine-tuning in language domains, we explore efficient fine-tuning techniques -- e. g., Bottleneck Adapters, P-Tuning, and Low-Rank Adaptation (LoRA) -- in TAIL to adapt large pretrained models for new tasks with limited demonstration data.
A Novel Convolutional Neural Network Architecture with a Continuous Symmetry
This paper introduces a new Convolutional Neural Network (ConvNet) architecture inspired by a class of partial differential equations (PDEs) called quasi-linear hyperbolic systems.
Two-stream Multi-level Dynamic Point Transformer for Two-person Interaction Recognition
Subsequently, a frame features learning module and a two-stream multi-level feature aggregation module extract global and partial features from the sampled frames, effectively representing the local-region spatial information, appearance information, and motion information related to the interactions.
Budgeting Counterfactual for Offline RL
The main challenge of offline reinforcement learning, where data is limited, arises from a sequence of counterfactual reasoning dilemmas within the realm of potential actions: What if we were to choose a different course of action?
Reinforcement Learning Tutor Better Supported Lower Performers in a Math Task
Resource limitations make it hard to provide all students with one of the most effective educational interventions: personalized instruction.
Deep Reinforcement Learning
Explainable artificial intelligence
+2
Uncertainty-Aware Pedestrian Trajectory Prediction via Distributional Diffusion
Tremendous efforts have been put forth on predicting pedestrian trajectory with generative models to accommodate uncertainty and multi-modality in human behaviors.
Symbolic Discovery of Optimization Algorithms
On diffusion models, Lion outperforms Adam by achieving a better FID score and reducing the training compute by up to 2. 3x.
Perception-Aware Attack: Creating Adversarial Music via Reverse-Engineering Human Perception
In this work, we formulate the adversarial attack against music signals as a new perception-aware attack framework, which integrates human study into adversarial attack design.
Towards Adaptive Unknown Authentication for Universal Domain Adaptation by Classifier Paradox
In this paper, we propose a new UniDA method with adaptive Unknown Authentication by Classifier Paradox (UACP), considering that samples with paradoxical predictions are probably unknowns belonging to none of the source classes.
Offline Policy Optimization with Eligible Actions
Offline policy optimization could have a large impact on many real-world decision-making problems, as online learning may be infeasible in many applications.
Generalized Federated Learning via Sharpness Aware Minimization
Therefore, in this paper, we revisit the solutions to the distribution shift problem in FL with a focus on local learning generality.
Provably Sample-Efficient RL with Side Information about Latent Dynamics
We study reinforcement learning (RL) in settings where observations are high-dimensional, but where an RL agent has access to abstract knowledge about the structure of the state space, as is the case, for example, when a robot is tasked to go to a specific room in a building using observations from its own camera, while having access to the floor plan.
Tiny Object Tracking: A Large-scale Dataset and A Baseline
Tiny objects, frequently appearing in practical applications, have weak appearance and features, and receive increasing interests in meany vision tasks, such as object detection and segmentation.
IoTGAN: GAN Powered Camouflage Against Machine Learning Based IoT Device Identification
In this research, we propose a novel attack strategy named IoTGAN to manipulate an IoT device's traffic such that it can evade machine learning based IoT device identification.
LoMar: A Local Defense Against Poisoning Attack on Federated Learning
Federated learning (FL) provides a high efficient decentralized machine learning framework, where the training data remains distributed at remote clients in a network.
Context-Aware Online Client Selection for Hierarchical Federated Learning
In addition, client selection for HFL faces more challenges than conventional FL, e. g., the time-varying connection of client-ES pairs and the limited budget of the Network Operator (NO).
Avoiding Overfitting to the Importance Weights in Offline Policy Optimization
Offline policy optimization has a critical impact on many real-world decision-making problems, as online learning is costly and concerning in many applications.
Applying VertexShuffle Toward 360-Degree Video Super-Resolution on Focused-Icosahedral-Mesh
We further apply our proposed methods on super resolution model, which is the first to propose a spherical super-resolution model that directly operates on a mesh representation of spherical pixels of 360-degree data.
Provably Good Batch Off-Policy Reinforcement Learning Without Great Exploration
Doing batch RL in a way that yields a reliable new policy in large domains is challenging: a new decision policy may visit states and actions outside the support of the batch data, and function approximation and optimization with limited samples can further increase the potential of learning policies with overly optimistic estimates of their future performance.
Provably Good Batch Reinforcement Learning Without Great Exploration
Doing batch RL in a way that yields a reliable new policy in large domains is challenging: a new decision policy may visit states and actions outside the support of the batch data, and function approximation and optimization with limited samples can further increase the potential of learning policies with overly optimistic estimates of their future performance.
Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions
Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its validity.
SSAH: Semi-supervised Adversarial Deep Hashing with Self-paced Hard Sample Generation
In this paper, we propose a novel Semi-supervised Self-pace Adversarial Hashing method, named SSAH to solve the above problems in a unified framework.
All-Action Policy Gradient Methods: A Numerical Integration Approach
While often stated as an instance of the likelihood ratio trick [Rubinstein, 1989], the original policy gradient theorem [Sutton, 1999] involves an integral over the action space.
Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling
Surprisingly, we find that in finite horizon MDPs there is no strict variance reduction of per-decision importance sampling or stationary importance sampling, comparing with vanilla importance sampling.
Combining Parametric and Nonparametric Models for Off-Policy Evaluation
We consider a model-based approach to perform batch off-policy evaluation in reinforcement learning.
Off-Policy Policy Gradient with State Distribution Correction
We study the problem of off-policy policy optimization in Markov decision processes, and develop a novel off-policy policy gradient method.
Aurora Guard: Real-Time Face Anti-Spoofing via Light Reflection
In this paper, we propose a light reflection based face anti-spoofing method named Aurora Guard (AG), which is fast, simple yet effective that has already been deployed in real-world systems serving for millions of users.
Behaviour Policy Estimation in Off-Policy Policy Evaluation: Calibration Matters
In this work, we consider the problem of estimating a behaviour policy for use in Off-Policy Policy Evaluation (OPE) when the true behaviour policy is unknown.
Representation Balancing MDPs for Off-Policy Policy Evaluation
We study the problem of off-policy policy evaluation (OPPE) in RL.
When Simple Exploration is Sample Efficient: Identifying Sufficient Conditions for Random Exploration to Yield PAC RL Algorithms
Efficient exploration is one of the key challenges for reinforcement learning (RL) algorithms.
