Decoupling

Follow this topic Ask about this topic

Recent momentum

-79%

3 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

65 papers

Latest in Decoupling

Open your feed →

Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex Dialogue
Sep 3, 2026Yihang Li, Chenhui ChuFull-Duplex Dialogue Turn-Taking
Learning with Volterra Neural Networks: A System Theoretic Perspective
Sep 1, 2026Haoyu Yun, Hamid Krim, Yufang BaoNeural Tangent Kernel Neural Operators
Beyond Good Intentions: When Does the Framing of Multilingual and Low-Resource NLP Research Become a Caricature?
Aug 31, 2026Nedjma Ousidhoum, Noopur Zambare, Mohamed AbdallaLow-Resource Languages Multilingual
Revisiting Overestimation Bias Problem of Q-learning: Settling Large Discrete Action Space via Action Intersection
Aug 13, 2026Pu Li, Tao Tan, Hong Xie +2Q-Learning High-Dimensional Action Spaces
Beyond Visual Evidence: Revealing and Mitigating Relational Privacy Leakage in Document MLLMs
Aug 13, 2026Beining Xu, Hairui Wang, Jiaxin Wang +2Visual Document Retrieval Large Multimodal Models
Causal Structure is Inducible but Functionally Decoupled: The Routing/Readout Boundary of a Typed Mechanism Library
Aug 12, 2026Xining XunCausal Structure and Reasoning Mechanistic Interpretability
Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation
Aug 9, 2026Kaichen Zhang, Wei Huang, Keming Wu +2Multimodal Generation Streaming
Control-Diverse Reinforcement Fine-Tuning: Decoupling the Shared Control Bottleneck of RL Post-Training
Aug 8, 2026Binwen Tan, Jingchao Wang, Dengzhe Hou +6Reinforcement Fine-Tuning Cross-Task Interference
DeCo: Zero-Shot Industrial Anomaly Generation through Decoupling and Recoupling
Aug 8, 2026Shilei Zeng, Xurui Li, Yaohan Tang +1Unsupervised Detectors State-Of-The-Art Zero-Shot Performance
TOFD: Target-Oriented Feature Decoupling against Poisoning Attacks in Split Federated Learning
Aug 7, 2026Yuhan Xie, Jingrong Huang, Chen LyuModel-Agnostic Defense Adversarial Transferability
TA-RAG: Tone Awareness as a Design Imperative for Retrieval-Augmented Generation
Aug 7, 2026Yong-Bin Kang, Anthony McCoskerRetrieval-Augmented Generation Narrative Coherence
Decoupling Generation and Selection for Budget-Constrained Faithful Summarization
Aug 4, 2026Zeyu Wang, Guanghua Wang, Meng XuSummarization Long-Form Generation
Aligned in Form, Not in Meaning: The Comprehension - Containment Decoupling of LLM Safety in Low-Resource Bangla Derogatory Speech
Aug 3, 2026Shadab Bin Habib, A K M Ferdous Reza Habib, Subarno Neel +1Large Language Model Safety Large Language Model Alignment
Training Small LLMs as Spatial Multi-Agent Policies
Aug 2, 2026Yi Mao, Andrew PerraultMulti-Agent Reinforcement Learning Multi-Agent Large Language Model Systems
Mitigating Backdoors via Decoy Shortcuts and Knowledge Decoupling
Aug 1, 2026Zixuan Zhu, Rui Wang, Lihua Jing +1Backdoor Attacks Deep Neural Network
Juxtaposition of Shallow Reservoir-Triggered Seismicity and Deep Tectonic Locking in the Qiaojia-Dongchuan Seismic Gap
Jul 21, 2026Yuxin Zhou, Huai Zhang, S. Mostafa Mousavi +5Seismic Interpretation Continuum Dynamics
To Blend In, First Decouple: Rethinking Camouflage Image Generation via Context-Decoupled Representations
Jul 20, 2026Wenzhuang Wang, Yifan Zhao, Mingcan Ma +4Unified Generative Framework Decoupling
Decouple and Reason: Anatomically Guided Two-Stage Voxel-Level Grounding of Free-Text Findings in 3D Chest CT
Jul 14, 2026Kwang-Hyun Uhm, Inhwa Son, Sung-Jea KoComputed Tomography 3D Visual Grounding
The Equilibrium Is the Initialization: Lazy Identity Collapse in Physics-Structured Deep Equilibrium Reasoning
Jul 13, 2026Joyjeet SinghEquilibrium Equivalence
Constructed Reality, Contested Priors: Decoupling and the Architecture of Cognitive Relapse Under the Free Energy Principle
Jul 12, 2026MD Ibrahim Hossain RidoyPredictive Coding Free Energy Principle
Decoupling Code Complexity from Newcomer Participation: A Causal Study of AI Coding Agent Adoption in OSS
Jul 2, 2026Weiwei Xu, Xuanning Cui, Hengzhi Ye +1Coding Agents Open-Source
WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models
Jun 30, 2026Ting-Bing Xu, Jiacheng Sui, Zhe Gao +12World Models Open-World
Autoencoder Architectures for Athlete Performance Scoring from Wearable Telemetry
Jun 26, 2026Mateusz Kubita, Jan Zubalewicz, Krzysztof SiwekAutoencoder Sports Science
Not All Relations Rotate Alike: Transformation-Aware Decoupling for Viewpoint-Robust 3D Scene Graph Generation
Jun 25, 2026Jingjun Sun, Chaowei Wang, Zhirui Liu +43D Scene Graphs 3D Scenes
Scalability of Morality: A Particle-Based Numerical Study on the Decoupling of Law and Ethics in Large-Scale Populations
Jun 25, 2026Amir Arslan Haghrah, Amir Aslan HaghrahSocial Dynamics Moral Reasoning
Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors
Jun 24, 2026Alexander Hägele, Alejandro Hernández-Cano, Atli Kosson +1Model Weights Spectral Norm
Heterogeneous Knowledge Distillation via Geometry Decoupling and Momentum-Aware Gradient Regulation
Jun 23, 2026Wuming Yang, Xiang Zhang, Hongmin ZhaoHeterogeneous Knowledge Distillation Asymmetric Distillation
OrthoMotion:Disentangling Camera and Subject Motion via Geometry Semantics Orthogonal Attention
Jun 22, 2026Zijie MengCamera Control Optical Flow
Fed-CausalDiff: Decoupled Synchronization for Federated Do-Simulation and Policy Evaluation
Jun 21, 2026Pengfei Li, Mohammad KhalilDiffusion Policies Distributional Learning
Decoupling Search from Reasoning: A Vendor-Agnostic Grounding Architecture for LLM Agents
Jun 17, 2026Emmanuel Aboah Boateng, Kyle MacDonald, Amardeep Kumar +2Agentic Search Large Language Model Agents
Decoupling Semantics from Distortions: Multi-Scale Two-Stream Vision-Language Alignment for AI-Generated Image Quality Assessment
Jun 15, 2026Zijie MengVision-Language Alignment Contrastive Language-Image Pre-Training
AIR-VLA+: Decoupling Movement and Manipulation via Cascaded Dual-Action Decoders with Asymmetric MoE for Aerial Robots
Jun 11, 2026Jianli Sun, Bin Tian, Qiyao Zhang +6Aerial Manipulation Aerial Robots
Decoupling Thought from Speech: Knowledge-Grounded Counterfactual Reasoning for Resilient Multi-Agent Argumentation
Jun 9, 2026Jakub Masłowski, Jarosław A. ChudziakMulti-Agent Debate Counterfactual Reasoning
Scaling by Diversified Experience for Vision-Language-Action Models
Jun 8, 2026Leiyu Wang, Zhaofengnian Wang, Xueqi Li +3Diffusion-Based Vision-Language-Actions Vision-Language-Action
Decoupling Semantics and Logic: A Training-Free Coarse-to-Fine Pipeline for Video Retrieval-Augmented Generation
Jun 6, 2026Jiaxin Dai, Zehang Wei, Jiamin Yan +1Multimodal Retrieval Augmented Generation Agentic Video Generation
Dual-Route Top-K Retrieval with 1v1 VLM Reranking for the CoVR-R
May 31, 2026Yuyang Sun, Yongliang Wu, Xingyu Zhu +8Reranking Cross-Encoder Reranker
ZAPS-DA: Zero-Phase Action Policy Smoothing with Decoupled Actor for Continuous Control in Reinforcement Learning
May 28, 2026Faiq ShamassOff-Policy Reinforcement Learning Zero
DeCoDrift: Stabilizing Decoder Coupling in Closed-Loop Foundation Segmentation
May 25, 2026H. M. Shadman Tabib, Md. Shamsuzzoha Bayzid, M Sohel RahmanLarge Language Model Decoding Attention-Guided Transunet
Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints
May 20, 2026Alexi Canesse, Benoît Goupil, Jesse Read +1Multi-Agent Reinforcement Learning Bandwidth Extension
Efficient Gradient Methods for Distributed Saddle Problems
May 18, 2026Ruichen Luo, Anton Rodomanov, Sebastian U. StichDecoupling
Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
May 18, 2026Yihang Wu, Yihang Sun, Shaofeng Zhang +4Novel View Synthesis Multimodal Transformers
EchoSR: Efficient Context Harnessing for Lightweight Image Super-Resolution
May 17, 2026Hanli Zhao, Binhao Wang, Shihao Zhao +3Real-World Image Super-Resolution Multiscale
A Regret Perspective on Online Multiple Testing
May 13, 2026Qingyang Hao, Kongchang Zhou, Fang Kong +1False Discovery Rate Two-Sample Testing
VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority
May 12, 2026Chenhao Qiu, Yechao Zhang, Xin Luo +2Agentic Video Generation Video Question Answering
CAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and Aggregation
May 12, 2026Daohan Su, Hao Liu, Xunkai Li +6Multimodal Graph Graph Neural Networks
Factual recall in linear associative memories: sharp asymptotics and mechanistic insights
May 11, 2026Alessio Giorlandino, Sebastian Goldt, Antoine MaillardAssociative Memory Factual Recall
Cosine-Gated Adam-Decay: Drop-In Staleness-Aware Outer Optimization for Decoupled DiLoCo
May 9, 2026Vatsal Shah, Jiahao SunAdam Nesterov
Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval
May 8, 2026Mingyu Liu, Sihan Huang, Yijia Fan +4Composed Image Retrieval Image-Caption Pairs
Hierarchical Dual-Subspace Decoupling for Continual Learning in Vision-Language Models
May 8, 2026Mengxin Qin, Xiang Zhang, Kun Wei +2Efficient Continual Learning Pre-Trained Vision-Language Models
Decoupling Semantics and Fingerprints: A Universal Representation for AI-Generated Image Detection
May 8, 2026Zhiyuan Wang, Yanxiang Chen, Pengcheng Zhao +2Ai-Generated Image Detection Forgeries
Secure Seed-Based Multi-bit Watermarking for Diffusion Models from First Principles
May 7, 2026Enoal Gesny, Eva GiboulotMulti-Bit Watermarking Watermarking
Large Vision-Language Models Get Lost in Attention
May 7, 2026Gongli Xi, Ye Tian, Mengyu Yang +5Transformer Residual Streams Recent Vision-Language Models
SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies
May 6, 2026Siddhant Saxena, Nilesh Trivedi, Vinayaka JyothiSwe-Bench Verified Coding Agents
Rethinking Low-Light Image Enhancement: A Log-Domain Intensity--Chromaticity Decoupling Perspective
May 4, 2026Guangrui Bai, Yifan Mei, Yahui Deng +4Low-Light Image Enhancement Color
Decouple and Cache: KV Cache Construction for Streaming Video Understanding
May 3, 2026Zhanzhong Pang, Dibyadip Chatterjee, Fadime Sener +1Streaming Video Key-Value Cache
Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors
May 1, 2026Chaohao Yuan, Chenghao Xiao, Yu Rong +2Supervised Fine-Tuning Large Language Model Post-Training
Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation
Apr 29, 2026Théo Gigant, Bowen Peng, Jeffrey QuesnelleSubword Tokenization Decoupling
Task Switching Without Forgetting via Proximal Decoupling
Apr 20, 2026Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger +2Efficient Continual Learning Regularization Methods
CDSA-Net:Collaborative Decoupling of Vascular Structure and Background for High-Fidelity Coronary Digital Subtraction Angiography
Apr 19, 2026Si Li, Chen-Kai Hu, Zhenhuan Lyu +1Digital Subtraction Angiography Vascular Network
Orientation Matters: Learning Radiation Patterns of Multi-Rotor UAVs In-Flight to Enhance Communication Availability Modeling
Apr 3, 2026Martin Zoula, Daniel Bonilla Licea, Jan Faigl +2Unmanned Aerial Vehicles Single-Antenna Systems

Sep 3, 2026 · cs.CLJ/K move · Enter open · S save

Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex Dialogue

Yihang Li, Chenhui Chu

The Neural Finite State Machine (NFSM) framework offers a pragmatic path to full-duplex dialogue by serializing turn-taking control and response generation onto a single causal tape under the standard next-token prediction objective, thereby preserving semantic prowess at a low fine-tuning cost. However, its reliance on synthetic text data fundamentally limits turn-taking naturalness, as Large Language Models (LLMs) cannot faithfully simulate the fine-grained acoustic temporal dynamics of real human dialogues. In this work, we propose a decoupled data approach that learns turn-taking from real Human-Human (HH) spoken dialogues while shaping semantic behavior through configurable Human-Agent (HA) text dialogues. To operationalize this approach, we introduce a rule-based event-guided data transformation method that serializes HH spoken dialogues into FSM tapes by classifying turn-taking events and applying deterministic mapping rules, enabling scalable supervision without LLM-generated annotations. We further propose a Source-Aware Calibrated (SAC) Loss that jointly calibrates the long-tailed distribution of state transition tokens and channels each data source toward the capability it best supervises. Experiments show that our approach substantially improves turn-taking proficiency while recovering the foundation LLM's semantic capability. Our code and model are available at https://github.com/Liyht/def-fsm.

Full-Duplex Dialogue Turn-Taking Speech Language Models Decoupling Semantic Representation and Control

Open paper Ask about it PDF