Cover Image

Beyond Static Cropping: Layer-Adaptive Visual Localization and Decoding Enhancement

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Zipeng, Hu, Zhanghao, Zhu, Qinglin, Hong, Yuxi, Liu, Yijun, Su, Jingyong, He, Yulan, Gui, Lin
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Perplexity: Let the Reader Select Retrieval Summaries via Spectrum Projection Score
by: Hu, Zhanghao, et al.
Published: (2025)

Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering
by: Hu, Zhanghao, et al.
Published: (2025)

Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
by: Hu, Zhanghao, et al.
Published: (2026)

Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention
by: Qi, Siya, et al.
Published: (2026)

Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning
by: Yan, Hanqi, et al.
Published: (2024)

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration
by: Zhu, Qinglin, et al.
Published: (2025)

PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games
by: Zhu, Qinglin, et al.
Published: (2024)

SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding
by: Zhao, Runcong, et al.
Published: (2025)

Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States
by: Zhu, Qinglin, et al.
Published: (2025)

Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding
by: Zhu, Lixing, et al.
Published: (2023)

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism
by: Wei, Zhepei, et al.
Published: (2025)

Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives
by: Zhao, Runcong, et al.
Published: (2024)

Multi-Layer Ranking with Large Language Models for News Source Recommendation
by: Zhang, Wenjia, et al.
Published: (2024)

Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding
by: Xiang, Yanzheng, et al.
Published: (2026)

Sparse Activation Editing for Reliable Instruction Following in Narratives
by: Zhao, Runcong, et al.
Published: (2025)

CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation
by: Shen, Zhenyi, et al.
Published: (2025)

Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond
by: Wang, Xinyu, et al.
Published: (2024)

EEE-QA: Exploring Effective and Efficient Question-Answer Representations
by: Hu, Zhanghao, et al.
Published: (2024)

PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA
by: Wang, Xinyu, et al.
Published: (2024)

Addressing Order Sensitivity of In-Context Demonstration Examples in Causal Language Models
by: Xiang, Yanzheng, et al.
Published: (2024)

A Survey of Automatic Hallucination Evaluation on Natural Language Generation
by: Qi, Siya, et al.
Published: (2024)

Hatevolution: What Static Benchmarks Don't Tell Us
by: Di Bonaventura, Chiara, et al.
Published: (2025)

Weak Reward Model Transforms Generative Models into Robust Causal Event Extraction Systems
by: da Silva, Italo Luis, et al.
Published: (2024)

Improving Open-Ended Text Generation via Adaptive Decoding
by: Zhu, Wenhong, et al.
Published: (2024)

PEARL: Parallel Speculative Decoding with Adaptive Draft Length
by: Liu, Tianyu, et al.
Published: (2024)

The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis
by: Zhou, Yuxiang, et al.
Published: (2023)

GraphMind: Interactive Novelty Assessment System for Accelerating Scientific Discovery
by: da Silva, Italo Luis, et al.
Published: (2025)

Explainable Recommender with Geometric Information Bottleneck
by: Yan, Hanqi, et al.
Published: (2023)

Pull Requests as a Training Signal for Repo-Level Code Editing
by: Zhu, Qinglin, et al.
Published: (2026)

SDSAT: Accelerating LLM Inference through Speculative Decoding with Semantic Adaptive Tokens
by: Liu, Chengbo, et al.
Published: (2024)

SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding
by: Lin, Yijun, et al.
Published: (2026)

Multilingual Contrastive Decoding via Language-Agnostic Layers Skipping
by: Zhu, Wenhao, et al.
Published: (2024)

Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models
by: Chen, Kecheng, et al.
Published: (2025)

DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization
by: Deng, Mengyi, et al.
Published: (2026)

Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training
by: Chen, Hang, et al.
Published: (2026)

Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time Scaling
by: Ji, Shiyu, et al.
Published: (2025)

Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time
by: Li, Jiazheng, et al.
Published: (2025)

SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space
by: Shen, Zhenyi, et al.
Published: (2025)

TAG-INSTRUCT: Controlled Instruction Complexity Enhancement through Structure-based Augmentation
by: Zhu, He, et al.
Published: (2025)

Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs
by: Sen, Jaydip, et al.
Published: (2025)