Image de couverture de livre

CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yu, Hao, Zhao, Zhuokai, Yan, Shen, Korycki, Lukasz, Wang, Jianyu, He, Baosheng, Liu, Jiayi, Zhang, Lizhu, Fan, Xiangjun, Yu, Hanchao
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Synthetic Sandbox for Training Machine Learning Engineering Agents
par: Zhou, Yuhang, et autres
Publié: (2026)

OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification
par: Zhou, Yuhang, et autres
Publié: (2026)

S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning
par: Zeng, Hanqing, et autres
Publié: (2025)

TARo: Token-level Adaptive Routing for LLM Test-time Alignment
par: Rai, Arushi, et autres
Publié: (2026)

Agentic Recommender System with Hierarchical Belief-State Memory
par: Shen, Xiang, et autres
Publié: (2026)

Quantifying Generalization Complexity for Large Language Models
par: Qi, Zhenting, et autres
Publié: (2024)

Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning
par: Yang, Chenghao, et autres
Publié: (2025)

Reason to Contrast: A Cascaded Multimodal Retrieval Framework
par: Cui, Xuanming, et autres
Publié: (2025)

Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding
par: Zhou, Yuhang, et autres
Publié: (2025)

LLM-Driven Reasoning for Constraint-Aware Feature Selection in Industrial Systems
par: Zhou, Yuhang, et autres
Publié: (2026)

Representation Noising: A Defence Mechanism Against Harmful Finetuning
par: Rosati, Domenic, et autres
Publié: (2024)

GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification
par: Fostiropoulos, Iordanis, et autres
Publié: (2026)

Healthcare Copilot: Eliciting the Power of General LLMs for Medical Consultation
par: Ren, Zhiyao, et autres
Publié: (2024)

GEM: Empowering LLM for both Embedding Generation and Language Understanding
par: Zhang, Caojin, et autres
Publié: (2025)

Self-Policy Distillation via Capability-Selective Subspace Projection
par: Hao, Guangya, et autres
Publié: (2026)

UGen: Unified Autoregressive Multimodal Model with Progressive Vocabulary Learning
par: Tang, Hongxuan, et autres
Publié: (2025)

Token-Level LLM Collaboration via FusionRoute
par: Xiong, Nuoya, et autres
Publié: (2026)

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
par: Han, Jiaming, et autres
Publié: (2025)

RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization
par: Yu, Zhaoning, et autres
Publié: (2025)

Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data
par: Guo, Siqi, et autres
Publié: (2025)

The Hallucination Tax of Reinforcement Finetuning
par: Song, Linxin, et autres
Publié: (2025)

Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation
par: Li, Mingzhe, et autres
Publié: (2022)

Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models
par: Xu, Yexing, et autres
Publié: (2026)

Towards Better Understanding of Contrastive Sentence Representation Learning: A Unified Paradigm for Gradient
par: Li, Mingxin, et autres
Publié: (2024)

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
par: Ma, Yiyang, et autres
Publié: (2024)

General Transform: A Unified Framework for Adaptive Transform to Enhance Representations
par: Budiutama, Gekko, et autres
Publié: (2025)

Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters
par: Wang, Weizhi, et autres
Publié: (2024)

Analyzing Finetuning Representation Shift for Multimodal LLMs Steering
par: Khayatan, Pegah, et autres
Publié: (2025)

Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table Representations
par: Chen, Sibei, et autres
Publié: (2024)

LegalDuet: Learning Fine-grained Representations for Legal Judgment Prediction via a Dual-View Contrastive Learning
par: Xu, Buqiang, et autres
Publié: (2024)

SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs
par: Zhao, Sihang, et autres
Publié: (2026)

A Tutorial on the Pretrain-Finetune Paradigm for Natural Language Processing
par: Wang, Yu, et autres
Publié: (2024)

Linking Representations with Multimodal Contrastive Learning
par: Arora, Abhishek, et autres
Publié: (2023)

Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
par: Luo, Haozheng, et autres
Publié: (2026)

HalluClean: A Unified Framework to Combat Hallucinations in LLMs
par: Zhao, Yaxin, et autres
Publié: (2025)

KaLM: Knowledge-aligned Autoregressive Language Modeling via Dual-view Knowledge Graph Contrastive Learning
par: Yu, Peng, et autres
Publié: (2024)

Mitigating Large Language Model Hallucination with Faithful Finetuning
par: Hu, Minda, et autres
Publié: (2024)

ReFT: Representation Finetuning for Language Models
par: Wu, Zhengxuan, et autres
Publié: (2024)

Instruction Finetuning for Leaderboard Generation from Empirical AI Research
par: Kabongo, Salomon, et autres
Publié: (2024)

EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy Optimization
par: Han, Kevin, et autres
Publié: (2026)