Search Results for author:
Found 25 papers, 8 papers with code
Adaptive Federated LoRA in Heterogeneous Wireless Networks with Independent Sampling
In this paper, we propose an adaptive federated LoRA strategy with independent client sampling to minimize the convergence wall-clock time of federated fine-tuning under both computation and communication heterogeneity.
Linear Simple Cycle Reservoirs at the edge of stability perform Fourier decomposition of the input driving signals
This paper explores the representational structure of linear Simple Cycle Reservoirs (SCR) operating at the edge of stability.
SELU: Self-Learning Embodied MLLMs in Unknown Environments
Recently, multimodal large language models (MLLMs) have demonstrated strong visual understanding and decision-making capabilities, enabling the exploration of autonomously improving MLLMs in unknown environments.
Universality of Real Minimal Complexity Reservoir
For linear reservoirs, given the reservoir size, the reservoir construction has only one degree of freedom -- the reservoir cycle weight.
Egocentric Vision Language Planning
LMMs excel in planning long-horizon tasks over symbolic abstractions but struggle with grounding in the physical world, often failing to accurately identify object positions in images.
TransFeat-TPP: An Interpretable Deep Covariate Temporal Point Processes
The classical temporal point process (TPP) constructs an intensity function by taking the occurrence times into account.
FedEx: Expediting Federated Learning over Heterogeneous Mobile Devices by Overlapping and Participant Selection
Experimental results show that compared with its peer designs, FedEx demonstrates substantial reductions in FL training latency over heterogeneous mobile devices with limited memory cost.
Cradle: Empowering Foundation Agents Towards General Computer Control
To handle this issue, we propose the General Computer Control (GCC) setting to restrict foundation agents to interact with software through the most unified and standardized interface, i. e., using screenshots as input and keyboard and mouse actions as output.
Outlier-Aware Training for Low-Bit Quantization of Structural Re-Parameterized Networks
Lightweight design of Convolutional Neural Networks (CNNs) requires co-design efforts in the model architectures and compression techniques.
EvDiG: Event-guided Direct and Global Components Separation
In this paper we leverage the event camera to facilitate the separation of direct and global components enabling video-rate separation of high quality.
Mitigating Label Bias in Machine Learning: Fairness through Confident Learning
In this paper, we demonstrate that despite only having access to the biased labels, it is possible to eliminate bias by filtering the fairest instances within the framework of confident learning.
EventAid: Benchmarking Event-aided Image/Video Enhancement Algorithms with Real-captured Hybrid Dataset
Event cameras are emerging imaging technology that offers advantages over conventional frame-based imaging sensors in dynamic range and sensing speed.
Hundred-Kilobyte Lookup Tables for Efficient Single-Image Super-Resolution
Conventional super-resolution (SR) schemes make heavy use of convolutional neural networks (CNNs), which involve intensive multiply-accumulate (MAC) operations, and require specialized hardware such as graphics processing units.
Improving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducer
Deep biasing for the Transducer can improve the recognition performance of rare words or contextual entities, which is essential in practical applications, especially for streaming Automatic Speech Recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Simple Cycle Reservoirs are Universal
Reservoir computation models form a subclass of recurrent neural networks with fixed non-trainable input and dynamic coupling weights.
Text-only Domain Adaptation using Unified Speech-Text Representation in Transducer
Domain adaptation using text-only corpus is challenging in end-to-end(E2E) speech recognition.
DyBit: Dynamic Bit-Precision Numbers for Efficient Quantized Neural Network Inference
To accelerate the inference of deep neural networks (DNNs), quantization with low-bitwidth numbers is actively researched.
Cross-domain Random Pre-training with Prototypes for Reinforcement Learning
CRPTpro significantly outperforms the next best Proto-RL(C) on 11/12 cross-domain downstream tasks with only 54\% wall-clock pre-training time, exhibiting state-of-the-art pre-training performance with greatly improved pre-training efficiency.
Coherent Event Guided Low-Light Video Enhancement
With frame-based cameras, capturing fast-moving scenes without suffering from blur often comes at the cost of low SNR and low contrast.
Neighborhood Convolutional Network: A New Paradigm of Graph Neural Networks for Node Classification
The decoupled Graph Convolutional Network (GCN), a recent development of GCN that decouples the neighborhood aggregation and feature transformation in each convolutional layer, has shown promising performance for graph representation learning.
Spatio-Temporal Contrastive Learning Enhanced GNNs for Session-based Recommendation
The idea is to supplement the GNN-based main supervised recommendation task with the temporal representation via an auxiliary cross-view contrastive learning mechanism.
Propagation with Adaptive Mask then Training for Node Classification on Attributed Networks
However, they follow the traditional structure-aware propagation strategy of GCNs, making it hard to capture the attribute correlation of nodes and sensitive to the structure noise described by edges whose two endpoints belong to different categories.
Recur, Attend or Convolve? On Whether Temporal Modeling Matters for Cross-Domain Robustness in Action Recognition
Most action recognition models today are highly parameterized, and evaluated on datasets with appearance-wise distinct classes.
Uncovering the Local Hidden Community Structure in Social Networks
We theoretically show that our method can avoid some situations that a broken community and the local community are regarded as one community in the subgraph, leading to the inaccuracy on detection which can be caused by global hidden community detection methods.
Making Adversarial Examples More Transferable and Indistinguishable
Fast gradient sign attack series are popular methods that are used to generate adversarial examples.
