Image de couverture de livre

AdaptFuse: Training-Free Sequential Preference Learning via Externalized Bayesian Inference

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lin, Fangzhou, Li, Peiran, Xing, Shuo, Yang, Siyuan, Ge, Qianwen, Yamada, Kazunori, Zhang, Ziming, Zhang, Haichong, Tu, Zhengzhong
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning
par: Lin, Fangzhou, et autres
Publié: (2026)

Position: Human-Centric AI Requires a Minimum Viable Level of Human Understanding
par: Lin, Fangzhou, et autres
Publié: (2026)

CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences
par: Lin, Fangzhou, et autres
Publié: (2026)

NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networks
par: Lin, Fangzhou, et autres
Publié: (2025)

A Strong View-Free Baseline Approach for Single-View Image Guided Point Cloud Completion
par: Lin, Fangzhou, et autres
Publié: (2025)

PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning
par: Jiang, Lingyu, et autres
Publié: (2026)

Traversal-as-Policy: Log-Distilled Gated Behavior Trees as Externalized, Verifiable Policies for Safe, Robust, and Efficient Agents
par: Li, Peiran, et autres
Publié: (2026)

Let the Abyss Stare Back Adaptive Falsification for Autonomous Scientific Discovery
par: Li, Peiran, et autres
Publié: (2026)

Hyperbolic Chamfer Distance for Point Cloud Completion and Beyond
par: Lin, Fangzhou, et autres
Publié: (2024)

TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting
par: Jiang, Lingyu, et autres
Publié: (2025)

BibAgent: An Agentic Framework for Traceable Miscitation Detection in Scientific Literature
par: Li, Peiran, et autres
Publié: (2026)

KANMixer: a minimal KAN-centered mixer for long-term time series forecasting
par: Jiang, Lingyu, et autres
Publié: (2025)

Loss Distillation via Gradient Matching for Point Cloud Completion with Weighted Chamfer Distance
par: Lin, Fangzhou, et autres
Publié: (2024)

Deep Loss Convexification for Learning Iterative Models
par: Zhang, Ziming, et autres
Publié: (2024)

Physics-Aware Video Instance Removal Benchmark
par: Li, Zirui, et autres
Publié: (2026)

Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization
par: Xing, Shuo, et autres
Publié: (2025)

A Language Anchor-Guided Method for Robust Noisy Domain Generalization
par: Dai, Zilin, et autres
Publié: (2025)

The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics
par: Gao, Xiangbo, et autres
Publié: (2026)

Demystifying the Visual Quality Paradox in Multimodal Large Language Models
par: Xing, Shuo, et autres
Publié: (2025)

SPADE: Spectroscopic Photoacoustic Denoising using an Analytical and Data-free Enhancement Framework
par: Lin, Fangzhou, et autres
Publié: (2024)

Towards Autonomous Robotic Kidney Ultrasound: Spatial-Efficient Volumetric Imaging via Template Guided Optimal Pivoting
par: Ma, Xihan, et autres
Publié: (2026)

DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning
par: Qian, Chengxuan, et autres
Publié: (2025)

Understanding Hyperbolic Metric Learning through Hard Negative Sampling
par: Yue, Yun, et autres
Publié: (2024)

Polyadic Grooming Patterns and Network in a Free‐Ranging Group of Japanese Macaques at Awajishima
par: Yu Kaigaishi, et autres
Publié: (2025)

WMF-AM: Probing LLM Working Memory via Depth-Parameterized Cumulative State Tracking
par: Hou, Dengzhe, et autres
Publié: (2026)

Same Brain, Different Prediction: How Preprocessing Choices Undermine EEG Decoding Reliability
par: Hou, Dengzhe, et autres
Publié: (2026)

Constitutive Components for Human-Like Autonomous Artificial Intelligence
par: Yamada, Kazunori D
Publié: (2025)

Learning Random Numbers to Realize Appendable Memory System for Artificial Intelligence to Acquire New Knowledge after Deployment
par: Yamada, Kazunori D
Publié: (2024)

Guiding the Last Centimeter: Novel Anatomy-Aware Probe Servoing for Standardized Imaging Plane Navigation in Robotic Lung Ultrasound
par: Ma, Xihan, et autres
Publié: (2024)

Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models
par: Shen, Minghe, et autres
Publié: (2025)

AlphaFuse: Learn ID Embeddings for Sequential Recommendation in Null Space of Language Embeddings
par: Hu, Guoqing, et autres
Publié: (2025)

SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems
par: Li, Peiran, et autres
Publié: (2025)

Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving
par: Wu, Fangzhou, et autres
Publié: (2025)

Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing
par: Qi, Leyi, et autres
Publié: (2026)

KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregation
par: Fang, Siyuan, et autres
Publié: (2024)

PQ-ball and its Real Scalar Analogue in an Expanding Universe
par: Nakayama, Kazunori, et autres
Publié: (2025)

On Sequential Bayesian Inference for Continual Learning
par: Kessler, Samuel, et autres
Publié: (2023)

Bayesian Optimization Sequential Surrogate (BOSS) Algorithm: Fast Bayesian Inference for a Broad Class of Bayesian Hierarchical Models
par: Li, Dayi, et autres
Publié: (2024)

T2T-VICL: Unlocking the Boundaries of Cross-Task Visual In-Context Learning via Implicit Text-Driven VLMs
par: Xia, Shao-Jun, et autres
Publié: (2025)

LLMs Can Get "Brain Rot": A Pilot Study on Twitter/X
par: Xing, Shuo, et autres
Publié: (2025)