Copertina

From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Wei, Liu, Hongkai, Deng, Zhiying, Teh, Yee Whye, Lee, Wee Sun
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Are We Evaluating the Edit Locality of LLM Model Editing Properly?
di: Liu, Wei, et al.
Pubblicazione: (2026)

Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents
di: Lee, Dongjun, et al.
Pubblicazione: (2025)

Can Vision-Language Models Solve the Shell Game?
di: Liu, Tiedong, et al.
Pubblicazione: (2026)

Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey
di: Liu, Qiyuan, et al.
Pubblicazione: (2025)

Verifier-Backed Hard Problem Generation for Mathematical Reasoning
di: Lai, Yuhang, et al.
Pubblicazione: (2026)

L3Ms -- Lagrange Large Language Models
di: Dhillon, Guneet S., et al.
Pubblicazione: (2024)

Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models
di: Rannen-Triki, Amal, et al.
Pubblicazione: (2024)

LinTree: Improving LLM Reasoning with Explicitly Structured Search Histories
di: Kang, Liwei, et al.
Pubblicazione: (2026)

Open-Source Image Editing Models Are Zero-Shot Vision Learners
di: Liu, Wei, et al.
Pubblicazione: (2026)

FB-RAG: Improving RAG with Forward and Backward Lookup
di: Chawla, Kushal, et al.
Pubblicazione: (2025)

From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding
di: Wang, Xiangfeng, et al.
Pubblicazione: (2025)

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
di: Zhang, Yi-Fan, et al.
Pubblicazione: (2025)

Online Adaptation of Language Models with a Memory of Amortized Contexts
di: Tack, Jihoon, et al.
Pubblicazione: (2024)

From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation
di: Li, Qingchuan, et al.
Pubblicazione: (2025)

Is Model Editing Built on Sand? Revealing Its Illusory Success and Fragile Foundation
di: Liu, Wei, et al.
Pubblicazione: (2025)

From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models
di: Shang, Yuying, et al.
Pubblicazione: (2024)

Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlation
di: Sgouritsa, Eleni, et al.
Pubblicazione: (2024)

Contextual Experience Replay for Self-Improvement of Language Agents
di: Liu, Yitao, et al.
Pubblicazione: (2025)

StochasTok: Improving Fine-Grained Subword Understanding in LLMs
di: Sims, Anya, et al.
Pubblicazione: (2025)

Seeing is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding
di: Guo, Pinxue, et al.
Pubblicazione: (2025)

Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts
di: Chen, Shengzhuang, et al.
Pubblicazione: (2024)

Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era
di: Oneata, Dan, et al.
Pubblicazione: (2025)

From Reasoning to Pixels: Benchmarking the Alignment Gap in Unified Multimodal Models
di: Yang, Cheng, et al.
Pubblicazione: (2026)

Adaptive Memory Replay for Continual Learning
di: Smith, James Seale, et al.
Pubblicazione: (2024)

Revisiting Multi-Modal LLM Evaluation
di: Lu, Jian, et al.
Pubblicazione: (2024)

Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward
di: Niu, Yuwei, et al.
Pubblicazione: (2025)

When Diffusion Breaks Constraints: Sequential Autoregressive Generation with RL and MCTS
di: Zhao, Zirui, et al.
Pubblicazione: (2025)

Uncovering Entity Identity Confusion in Multimodal Knowledge Editing
di: Wu, Shu, et al.
Pubblicazione: (2026)

LLM-Bootstrapped Targeted Finding Guidance for Factual MLLM-based Medical Report Generation
di: Yang, Cunyuan, et al.
Pubblicazione: (2026)

Uni3D-LLM: Unifying Point Cloud Perception, Generation and Editing with Large Language Models
di: Liu, Dingning, et al.
Pubblicazione: (2024)

FoR-SALE: Frame of Reference-guided Spatial Adjustment in LLM-based Diffusion Editing
di: Premsri, Tanawan, et al.
Pubblicazione: (2025)

From Personas to Talks: Revisiting the Impact of Personas on LLM-Synthesized Emotional Support Conversations
di: Wu, Shenghan, et al.
Pubblicazione: (2025)

SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization
di: Zheng, Zhi, et al.
Pubblicazione: (2025)

Forward-Backward Reasoning in Large Language Models for Mathematical Verification
di: Jiang, Weisen, et al.
Pubblicazione: (2023)

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

Bayesian Optimization for Controlled Image Editing via LLMs
di: Cai, Chengkun, et al.
Pubblicazione: (2025)

Sample-efficient LLM Optimization with Reset Replay
di: Liu, Zichuan, et al.
Pubblicazione: (2025)

Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning
di: Wei, Wenda, et al.
Pubblicazione: (2025)

Enhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspective
di: Wang, Bing, et al.
Pubblicazione: (2025)

ReLoop: "Seeing Twice and Thinking Backwards" via Closed-loop Training to Mitigate Hallucinations in Multimodal understanding
di: Yang, Jianjiang, et al.
Pubblicazione: (2025)