arXiv subjects

Ke Mu

Publications and source records attributed to Ke Mu.

4 recordsLinked to original sources

arXiv2026

PTC-Decoder: Towards Intelligent SLMs on Offline Resource-Constrained Edge Devices

Deploying small language models (SLMs) on offline, resource-constrained edge devices such as remote sensing satellites presents a fundamental challenge: their limited reasoning capacity hinders reliable execution of multi-step agent tasks requiring complex tool orchestration. Existing plan-solve paradigms rely on prompt-based enforcement, which our experiments show SLMs almost entirely disregard: weak models fail to invoke the plan. We propose PTC-Decoder (Plan-Tool Constrained Decoder), a training-free, plug-and-play decoder framework that combines (1) a Plan-to-Act paradigm, which elevates planning to an atomic tool and forces its invocation at the first inference step, and (2) TC-Decoder, a deterministic finite automaton that imposes token-level hard constraints on tool names while preserving freedom over parameter generation, thereby retaining SLM reasoning capability. Evaluated on 200 real remote-sensing satellite tasks across 7 SLMs, PTC-Decoder yields a statistically significant mean overall score gain of +1.21 (p<0.01), 95% CI [+1.13, +1.29]), with consistent improvements across models and other datasets. An ablation study that removes TC-Decoder causes substantial performance degradation across all quality metrics without reducing computational cost, confirming TC-Decoder as the primary driver. PTC-Decoder thus offers a lightweight yet effective solution for improving step-level reliability, with final-answer accuracy remaining an open challenge. In essence, we enforce plan adherence by constraining the permissible output vocabulary during inference, without requiring retraining.

cs.AI↗

arXiv2025

VarGes: Improving Variation in Co-Speech 3D Gesture Generation via StyleCLIPS

Generating expressive and diverse human gestures from audio is crucial in fields like human-computer interaction, virtual reality, and animation. Though existing methods have achieved remarkable performance, they often exhibit limitations due to constrained dataset diversity and the restricted amount of information derived from audio inputs. To address these challenges, we present VarGes, a novel variation-driven framework designed to enhance co-speech gesture generation by integrating visual stylistic cues while maintaining naturalness. Our approach begins with the Variation-Enhanced Feature Extraction (VEFE) module, which seamlessly incorporates \textcolor{blue}{style-reference} video data into a 3D human pose estimation network to extract StyleCLIPS, thereby enriching the input with stylistic information. Subsequently, we employ the Variation-Compensation Style Encoder (VCSE), a transformer-style encoder equipped with an additive attention mechanism pooling layer, to robustly encode diverse StyleCLIPS representations and effectively manage stylistic variations. Finally, the Variation-Driven Gesture Predictor (VDGP) module fuses MFCC audio features with StyleCLIPS encodings via cross-attention, injecting this fused data into a cross-conditional autoregressive model to modulate 3D human gesture generation based on audio input and stylistic clues. The efficacy of our approach is validated on benchmark datasets, where it outperforms existing methods in terms of gesture diversity and naturalness. The code and video results will be made publicly available upon acceptance:https://github.com/mookerr/VarGES/ .

cs.CV↗

arXiv2022

DPCN: Towards Deadline-aware Payment Channel Networks

Payment channel is a class of techniques designed to solve the scalability problem of blockchain. By establishing channels off the blockchain to form payment channel networks (PCNs), users can make instant payments without interacting with the blockchain, avoiding the problems of long transaction consensus delays and high transaction fees. Recently, the optimization of PCNs has mainly focused on improving the network throughput via multi-path routing. However, the transaction's atomicity comes at a non-trivial cost for transaction completion latency that affects user experience in deadline-sensitive applications of PCNs. In this paper, we propose a new and systematic framework DPCN to consider the deadlines of transactions for payment channel networks while improving the success ratio of transactions. DPCN is enabled via a synergy of three components: (1) deadline-based dynamic transaction split mechanism that splits the transaction according to current network status and the transaction's deadline; (2) deadline-aware transaction scheduling that prioritizes near-deadline transactions; (3) deadline-aware transaction congestion avoidance algorithm, which uses a path window to balance transactions with different deadlines. Our extensive experiments show that compared with existing methods, DPCN can well meet the needs of transactions with different deadlines and ensure a higher success ratio for transactions in the payment channel networks.

cs.NI↗

arXiv2021

RingFed: Reducing Communication Costs in Federated Learning on Non-IID Data

Federated learning is a widely used distributed deep learning framework that protects the privacy of each client by exchanging model parameters rather than raw data. However, federated learning suffers from high communication costs, as a considerable number of model parameters need to be transmitted many times during the training process, making the approach inefficient, especially when the communication network bandwidth is limited. This article proposes RingFed, a novel framework to reduce communication overhead during the training process of federated learning. Rather than transmitting parameters between the center server and each client, as in original federated learning, in the proposed RingFed, the updated parameters are transmitted between each client in turn, and only the final result is transmitted to the central server, thereby reducing the communication overhead substantially. After several local updates, clients first send their parameters to another proximal client, not to the center server directly, to preaggregate. Experiments on two different public datasets show that RingFed has fast convergence, high model accuracy, and low communication cost.

cs.LG↗