Search Results for author:
Found 26 papers, 10 papers with code
Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
In this paper, we identify the main cause of PRM-induced reward hacking: the canonical summation-form credit assignment in reinforcement learning (RL), which defines the value as cumulative gamma-decayed future rewards, easily induces LLMs to hack steps with high rewards.
ElimPCL: Eliminating Noise Accumulation with Progressive Curriculum Labeling for Source-Free Domain Adaptation
Source-Free Domain Adaptation (SFDA) aims to train a target model without source data, and the key is to generate pseudo-labels using a pre-trained source model.
Offline Reinforcement Learning with Discrete Diffusion Skills
Skills have been introduced to offline reinforcement learning (RL) as temporal abstractions to tackle complex, long-horizon tasks, promoting consistent behavior and enabling meaningful exploration.
Establishing Reality-Virtuality Interconnections in Urban Digital Twins for Superior Intelligent Road Inspection
Road inspection is essential for ensuring road maintenance and traffic safety, as road defects gradually emerge and compromise road functionality.
LHPF: Look back the History and Plan for the Future in Autonomous Driving
However, these algorithms typically assess the current and historical plans independently, leading to discontinuities in driving intentions and an accumulation of errors with each step in a discontinuous plan.
Ada-K Routing: Boosting the Efficiency of MoE-based LLMs
In this paper, we propose a novel Ada-K routing strategy that dynamically adjusts the number of activated experts for each token, thereby improving the balance between computational efficiency and model performance.
Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining
Experimental results indicate that our largest agent, with 150 million parameters, achieves 78. 9% human-level performance on pretrained games using only 10% subsampled offline data, outperforming existing state-of-the-art large-scale offline RL baselines by 31. 6% on averange.
Multipath Identification and Mitigation with FDA-MIMO Radar
In smart city development, the automatic detection of structures and vehicles within urban or suburban areas via array radar (airborne or vehicle platforms) becomes crucial.
Toward Motion Robustness: A masked attention regularization framework in remote photoplethysmography
There has been growing interest in facial video-based remote photoplethysmography (rPPG) measurement recently, with a focus on assessing various vital signs such as heart rate and heart rate variability.
SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models
In this paper, we present and delve into the self-consistency capability of LVLMs, a crucial aspect that reflects the models' ability to both generate informative captions for specific objects and subsequently utilize these captions to accurately re-identify the objects in a closed-loop process.
RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences
Our experiments on robotic manipulation and locomotion tasks demonstrate that RIME significantly enhances the robustness of the state-of-the-art PbRL method.
On Smart Morphing Wing Aircraft Robust Adaptive Beamforming
To overcome this problem and ensure robust beamforming for FCA, deviations in array control parameters (ACPs) and array perturbations, the effect of mutual coupling in addition to looking-direction errors should be considered.
Rethinking Imitation-based Planner for Autonomous Driving
In recent years, imitation-based driving planners have reported considerable success.
Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modeling
To address this problem, we propose a novel attention-based hierarchically-structured latent model to learn the temporal variations of feature semantics.
Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders
This study explores the application of self-supervised learning (SSL) to the task of motion forecasting, an area that has not yet been extensively investigated despite the widespread success of SSL in computer vision and natural language processing.
Accurate and Efficient Event-based Semantic Segmentation Using Adaptive Spiking Encoder-Decoder Network
Moreover, we develop a dual-path Spiking Spatially-Adaptive Modulation module, which is specifically tailored to enhance the representation of sparse events and multi-modal inputs, thereby considerably improving network performance.
E-MLB: Multilevel Benchmark for Event-Based Camera Denoising
Event cameras, such as dynamic vision sensors (DVS), are biologically inspired vision sensors that have advanced over conventional cameras in high dynamic range, low latency and low power consumption, showing great application potential in many fields.
Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation
We observe that the performance of this feed-forward Hebbian learning for fully test-time adaptation can be significantly improved by incorporating a feedback neuro-modulation layer.
DKT: Diverse Knowledge Transfer Transformer for Class Incremental Learning
Deep neural networks suffer from catastrophic forgetting in class incremental learning, where the classification accuracy of old classes drastically deteriorates when the networks learn the knowledge of new classes.
Time Series Prediction by Multi-task GPR with Spatiotemporal Information Transformation
Making an accurate prediction of an unknown system only from a short-term time series is difficult due to the lack of sufficient information, especially in a multi-step-ahead manner.
Discrete Time Convolution for Fast Event-Based Stereo
Inspired by continuous dynamics of biological neuron models, we propose a novel encoding method for sparse events - continuous time convolution (CTC) - which learns to model the spatial feature of the data with intrinsic dynamics.
Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning
Few-shot class-incremental learning is to recognize the new classes given few samples and not forget the old classes.
class-incremental learning
Few-Shot Class-Incremental Learning
+2
GSECnet: Ground Segmentation of Point Clouds for Edge Computing
This paper proposes the GSECnet - Ground Segmentation network for Edge Computing, an efficient ground segmentation framework of point clouds specifically designed to be deployable on a low-power edge computing unit.
The Role of the Hercules Autonomous Vehicle During the COVID-19 Pandemic: An Autonomous Logistic Vehicle for Contactless Goods Transportation
Moreover, many countries have imposed tough lockdown measures to reduce the virus transmission (e. g., retail, catering) during the pandemic, which causes inconveniences for human daily life.
LogDet Rank Minimization with Application to Subspace Clustering
Most of the recent studies use the nuclear norm as a convex surrogate of the rank operator.
High-dimensional Mixed Graphical Models
While graphical models for continuous data (Gaussian graphical models) and discrete data (Ising models) have been extensively studied, there is little work on graphical models linking both continuous and discrete variables (mixed data), which are common in many scientific applications.
