Search Results for author:
Found 44 papers, 24 papers with code
Counter-Contrastive Learning for Language GANs
Generative Adversarial Networks (GANs) have achieved great success in image synthesis, but have proven to be difficult to generate natural language.
Rethinking Generalizability and Discriminability of Self-Supervised Learning from Evolutionary Game Theory Perspective
Thus, to enhance the methodological generalization, we propose a novel self-supervised learning method that leverages advancements in reinforcement learning to jointly benefit from the general guidance of EGT and sequentially optimize the model to chase the consistent improvement of generalizability and discriminability for specific target domains during pre-training.
Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown
Reward models (RM) play a critical role in aligning generations of large language models (LLM) to human expectations.
Recent Advances in Attack and Defense Approaches of Large Language Models
Given the extensive research in the field of LLM security, we believe that summarizing the current state of affairs will help the research community better understand the present landscape and inform future developments.
Position: Foundation Agents as the Paradigm Shift for Decision Making
Decision making demands intricate interplay between perception, memory, and reasoning to discern optimal policies.
SPO: Multi-Dimensional Preference Sequential Alignment With Implicit Reward Modeling
Human preference alignment is critical in building powerful and reliable large language models (LLMs).
Urban Scene Diffusion through Semantic Occupancy Map
Generating unbounded 3D scenes is crucial for large-scale scene understanding and simulation.
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation
Autonomous driving simulation system plays a crucial role in enhancing self-driving data and simulating complex and rare traffic scenarios, ensuring navigation safety.
Safe Reinforcement Learning with Free-form Natural Language Constraints and Pre-Trained Language Models
Through the use of pre-trained LMs and the elimination of the need for a ground-truth cost, our method enhances safe policy learning under a diverse set of human-derived free-form natural language constraints.
Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges
Decision-making is a dynamic process requiring perception, memory, and reasoning to make choices and find optimal policies.
PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning
Designing better deep networks and better reinforcement learning (RL) algorithms are both important for deep RL.
TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient
We propose Topology-based multi-Agent Policy gradiEnt (TAPE) for both stochastic and deterministic MAPG methods.
BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning
Our algorithm, BadRL, strategically chooses state observations with high attack values to inject triggers during training and testing, thereby reducing the chances of detection.
Benchmarking Continual Learning from Cognitive Perspectives
To address these issues, we propose to integrate model cognitive capacities and evaluation metrics into a unified evaluation paradigm.
ProAgent: Building Proactive Cooperative Agents with Large Language Models
Building agents with adaptive behavior in cooperative tasks stands as a paramount goal in the realm of multi-agent systems.
Deep Reinforcement Learning with Task-Adaptive Retrieval via Hypernetwork
Deep reinforcement learning algorithms are usually impeded by sampling inefficiency, heavily depending on multiple interactions with the environment to acquire accurate decision-making capabilities.
NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields
We verify the effectiveness of our NeRF-LiDAR by training different 3D segmentation models on the generated LiDAR point clouds.
S-NeRF: Neural Radiance Fields for Street Views
Specifically, we improve the scene parameterization function and the camera poses for learning better neural representations from street views.
Improved Training of Mixture-of-Experts Language GANs
In this work, we (1) first empirically show that the mixture-of-experts approach is able to enhance the representation capacity of the generator for language GANs and (2) harness the Feature Statistics Alignment (FSA) paradigm to render fine-grained learning signals to advance the generator training.
PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination
We conduct experiments on the Overcooked environment, and evaluate the zero-shot human-AI coordination performance of our method with both behavior-cloned human proxies and real humans.
Transformer in Transformer as Backbone for Deep Reinforcement Learning
Recent methods combine the Transformer with these modules for better performance.
Delving into Transformer for Incremental Semantic Segmentation
In contrast, a Transformer based method has a natural advantage in curbing catastrophic forgetting due to its ability to model both long-term and short-term tasks.
Softmax-free Linear Transformers
With linear complexity, much longer token sequences are permitted by SOFT, resulting in superior trade-off between accuracy and complexity.
RACA: Relation-Aware Credit Assignment for Ad-Hoc Cooperation in Multi-Agent Deep Reinforcement Learning
Specifically, these methods do not explicitly utilize the relationship between agents and cannot adapt to different sizes of inputs.
DecisionHoldem: Safe Depth-Limited Solving With Diverse Opponents for Imperfect-Information Games
It is more common in life than perfect-information game.
Coordinated Proximal Policy Optimization
We present Coordinated Proximal Policy Optimization (CoPPO), an algorithm that extends the original Proximal Policy Optimization (PPO) to the multi-agent setting.
SOFT: Softmax-free Transformer with Linear Complexity
Crucially, with a linear complexity, much longer token sequences are permitted in SOFT, resulting in superior trade-off between accuracy and complexity.
Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning
More specifically, we evaluate the effect of an imaginary transition by calculating the change of the loss computed on the real samples when we use the transition to train the action-value and policy functions.
Model-based Reinforcement Learning
reinforcement-learning
+2
Improving Sequence Generative Adversarial Networks with Feature Statistics Alignment
Generative Adversarial Networks (GAN) are facing great challenges in synthesizing sequences of discrete elements, such as mode dropping and unstable training.
Planning with Exploration: Addressing Dynamics Bottleneck in Model-based Reinforcement Learning
We give an upper bound of the trajectory reward estimation error and point out that increasing the agent's exploration ability is the key to reduce trajectory reward estimation error, thereby alleviating dynamics bottleneck dilemma.
MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection
In this paper, we propose to incorporate domain knowledge in clinical practice into the model design of universal lesion detectors.
Ranked #8 on
Medical Object Detection
on DeepLesion
Point Cloud Super Resolution with Adversarial Residual Graph Networks
The key idea of the proposed network is to exploit the local similarity of point cloud and the analogy between LR input and HR output.
Ranked #2 on
Point Cloud Super Resolution
on SHREC15
Graphics Image and Video Processing
SparseMask: Differentiable Connectivity Learning for Dense Image Prediction
In this paper, we aim at automatically searching an efficient network architecture for dense image prediction.
FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
Modern approaches for semantic segmentation usually employ dilated convolutions in the backbone to extract high-resolution feature maps, which brings heavy computation complexity and memory footprint.
Ranked #40 on
Semantic Segmentation
on PASCAL Context
Transductive Zero-Shot Learning with Visual Structure Constraint
Based on the observation that visual features of test instances can be separated into different clusters, we propose a new visual structure constraint on class centers for transductive ZSL, to improve the generality of the projection function (i. e. alleviate the above domain shift problem).
Discriminative Learning of Latent Features for Zero-Shot Recognition
In this work, we retrospect existing methods and demonstrate the necessity to learn discriminative representations for both visual and semantic instances of ZSL.
Fast End-to-End Trainable Guided Filter
To address the problem, we present a novel building block for FCNs, namely guided filtering layer, which is designed for efficiently generating a high-resolution output given the corresponding low-resolution one and a high-resolution guidance map.
Mixed Supervised Object Detection with Robust Objectness Transfer
Different from previous MSD methods that directly transfer the pre-trained object detectors from existing categories to new categories, we propose a more reasonable and robust objectness transfer approach for MSD.
MSC: A Dataset for Macro-Management in StarCraft II
We also split MSC into training, validation and test set for the convenience of evaluation and comparison.
A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping
Image cropping aims at improving the aesthetic quality of images by adjusting their composition.
GP-GAN: Towards Realistic High-Resolution Image Blending
Concretely, we propose Gaussian-Poisson Equation to formulate the high-resolution image blending problem, which is a joint optimization constrained by the gradient and color information.
Conditional Image Generation
Generative Adversarial Network
+1
Beyond Tree Structure Models: A New Occlusion Aware Graphical Model for Human Pose Estimation
Occlusion is a main challenge for human pose estimation, which is largely ignored in popular tree structure models.
GRSA: Generalized Range Swap Algorithm for the Efficient Optimization of MRFs
al propose the range move algorithms, which are one of the most successful solvers to this problem.
Deformable Object Matching via Deformation Decomposition based 2D Label MRF
The MRF energy function is derived from the deformation decomposition model.
