Copertina

Distribution-Aligned Decoding for Efficient LLM Task Adaptation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hu, Senkang, Han, Xudong, Jiang, Jinqi, Tao, Yihang, Fang, Zihan, Dai, Yong, Kwong, Sam Tak Wu, Fang, Yuguang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers
di: Hu, Senkang, et al.
Pubblicazione: (2026)

Task-Aware Parameter-Efficient Fine-Tuning of Large Pre-Trained Models at the Edge
di: Hu, Senkang, et al.
Pubblicazione: (2025)

DSP-Reg: Domain-Sensitive Parameter Regularization for Robust Domain Generalization
di: Han, Xudong, et al.
Pubblicazione: (2026)

Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward
di: Hu, Senkang, et al.
Pubblicazione: (2026)

CP-Guard+: A New Paradigm for Malicious Agent Detection and Defense in Collaborative Perception
di: Hu, Senkang, et al.
Pubblicazione: (2025)

V2XCrafter: Learning to Generate Driving Scene Across Agents
di: Tao, Yihang, et al.
Pubblicazione: (2026)

Directed-CP: Directed Collaborative Perception for Connected and Autonomous Vehicles via Proactive Attention
di: Tao, Yihang, et al.
Pubblicazione: (2024)

CP-uniGuard: A Unified, Probability-Agnostic, and Adaptive Framework for Malicious Agent Detection and Defense in Multi-Agent Embodied Perception Systems
di: Hu, Senkang, et al.
Pubblicazione: (2025)

AgentsCoMerge: Large Language Model Empowered Collaborative Decision Making for Ramp Merging
di: Hu, Senkang, et al.
Pubblicazione: (2024)

CP-Guard: Malicious Agent Detection and Defense in Collaborative Bird's Eye View Perception
di: Hu, Senkang, et al.
Pubblicazione: (2024)

Unified Context Evolution for LLM Agents
di: Zhu, Zixuan, et al.
Pubblicazione: (2026)

Towards Full-scene Domain Generalization in Multi-agent Collaborative Bird's Eye View Segmentation for Connected and Autonomous Driving
di: Hu, Senkang, et al.
Pubblicazione: (2023)

Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception
di: Tao, Yihang, et al.
Pubblicazione: (2026)

Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoring
di: Fang, Zihan, et al.
Pubblicazione: (2025)

GCP: Guarded Collaborative Perception with Spatial-Temporal Aware Malicious Agent Detection
di: Tao, Yihang, et al.
Pubblicazione: (2025)

Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations
di: Fang, Zhengru, et al.
Pubblicazione: (2026)

HFedMoE: Resource-aware Heterogeneous Federated Learning with Mixture-of-Experts
di: Fang, Zihan, et al.
Pubblicazione: (2026)

Task-Oriented Semantic Compression for Localization at the Network Edge
di: Fang, Zhengru, et al.
Pubblicazione: (2025)

AgentsCoDriver: Large Language Model Empowered Collaborative Driving with Lifelong Learning
di: Hu, Senkang, et al.
Pubblicazione: (2024)

Skill-Conditioned Gated Self-Distillation for LLM Reasoning
di: Huang, Jiazhen, et al.
Pubblicazione: (2026)

Inference-Time Budget Control for LLM Search Agents
di: Fang, Zhengru, et al.
Pubblicazione: (2026)

UAV-enabled Computing Power Networks: Task Completion Probability Analysis
di: Deng, Yiqin, et al.
Pubblicazione: (2025)

Prioritized Information Bottleneck Theoretic Framework with Distributed Online Learning for Edge Video Analytics
di: Fang, Zhengru, et al.
Pubblicazione: (2024)

Collaborative Perception for Connected and Autonomous Driving: Challenges, Possible Solutions and Opportunities
di: Hu, Senkang, et al.
Pubblicazione: (2024)

CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning
di: Liu, Peiyuan, et al.
Pubblicazione: (2024)

IC3M: In-Car Multimodal Multi-object Monitoring for Abnormal Status of Both Driver and Passengers
di: Fang, Zihan, et al.
Pubblicazione: (2024)

TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation
di: Miao, Daiye, et al.
Pubblicazione: (2025)

PIB: Prioritized Information Bottleneck Framework for Collaborative Edge Video Analytics
di: Fang, Zhengru, et al.
Pubblicazione: (2024)

Sense4FL: Vehicular Crowdsensing Enhanced Federated Learning for Object Detection in Autonomous Driving
di: Ma, Yanan, et al.
Pubblicazione: (2025)

EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation
di: Li, Ting-Wei, et al.
Pubblicazione: (2026)

Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks
di: Lu, Bo-Ru, et al.
Pubblicazione: (2024)

Automatic Task Detection and Heterogeneous LLM Speculative Decoding
di: Ge, Danying, et al.
Pubblicazione: (2025)

DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval
di: Sun, Maojun, et al.
Pubblicazione: (2026)

Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding
di: Guan, Yue, et al.
Pubblicazione: (2025)

FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views
di: Tao, Yihang, et al.
Pubblicazione: (2026)

Adaptive Communications in Collaborative Perception with Domain Alignment for Autonomous Driving
di: Hu, Senkang, et al.
Pubblicazione: (2023)

Channel-Aware Throughput Maximization for Cooperative Data Fusion in CAV
di: An, Haonan, et al.
Pubblicazione: (2024)

Mask What Matters: Mitigating Object Hallucinations in Multimodal Large Language Models with Object-Aligned Visual Contrastive Decoding
di: Chen, Boqi, et al.
Pubblicazione: (2026)

Aligning the True Semantics: Constrained Decoupling and Distribution Sampling for Cross-Modal Alignment
di: Ma, Xiang, et al.
Pubblicazione: (2026)

TokAlign: Efficient Vocabulary Adaptation via Token Alignment
di: Li, Chong, et al.
Pubblicazione: (2025)