Copertina

From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Xiaofeng, Quan, Yihao, Shen, Chen, Yuan, Xiaosong, Yan, Shaotian, Xie, Liang, Wang, Wenxiao, Gu, Chaochen, Tang, Hao, Ye, Jieping
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs
di: Zhang, Xiaofeng, et al.
Pubblicazione: (2024)

Instance-adaptive Zero-shot Chain-of-Thought Prompting
di: Yuan, Xiaosong, et al.
Pubblicazione: (2024)

Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models
di: Yan, Shaotian, et al.
Pubblicazione: (2025)

Concise and Organized Perception Facilitates Reasoning in Large Language Models
di: Liu, Junjie, et al.
Pubblicazione: (2023)

SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning
di: Xin, Yue, et al.
Pubblicazione: (2025)

Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach
di: Fan, Sinan, et al.
Pubblicazione: (2025)

Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation
di: Liu, Kaiyuan, et al.
Pubblicazione: (2025)

Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation
di: Wang, Bing, et al.
Pubblicazione: (2026)

ART: Attention Replacement Technique to Improve Factuality in LLMs
di: Luo, Ziqin, et al.
Pubblicazione: (2026)

On the Step Length Confounding in LLM Reasoning Data Selection
di: Wang, Bing, et al.
Pubblicazione: (2026)

Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
di: Wang, Bing, et al.
Pubblicazione: (2026)

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning
di: Huang, Chenxi, et al.
Pubblicazione: (2025)

Hallucination Begins Where Saliency Drops
di: Zhang, Xiaofeng, et al.
Pubblicazione: (2026)

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models
di: Liu, Kaiyuan, et al.
Pubblicazione: (2025)

Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs
di: Pan, Zhiyu, et al.
Pubblicazione: (2026)

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
di: Yan, Shaotian, et al.
Pubblicazione: (2026)

Controlling Thinking Speed in Reasoning Models
di: Lin, Zhengkai, et al.
Pubblicazione: (2025)

Enhancing Multimodal Large Language Models Complex Reason via Similarity Computation
di: Zhang, Xiaofeng, et al.
Pubblicazione: (2024)

Enlighten-Your-Voice: When Multimodal Meets Zero-shot Low-light Image Enhancement
di: Zhang, Xiaofeng, et al.
Pubblicazione: (2023)

From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
di: Chen, Wei, et al.
Pubblicazione: (2024)

Learning to Reason Across Parallel Samples for LLM Reasoning
di: Qi, Jianing, et al.
Pubblicazione: (2025)

SciPIP: An LLM-based Scientific Paper Idea Proposer
di: Wang, Wenxiao, et al.
Pubblicazione: (2024)

Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
di: Lin, Zhengkai, et al.
Pubblicazione: (2024)

Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
di: Xiao, Yuxin, et al.
Pubblicazione: (2024)

CIMR: Contextualized Iterative Multimodal Reasoning for Robust Instruction Following in LVLMs
di: Yuan, Yangshu, et al.
Pubblicazione: (2025)

Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering
di: Li, Qiming, et al.
Pubblicazione: (2025)

Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs
di: Ghosh, Sreyan, et al.
Pubblicazione: (2024)

Robust Anti-Backdoor Instruction Tuning in LVLMs
di: Xun, Yuan, et al.
Pubblicazione: (2025)

Improving Visual Reasoning with Iterative Evidence Refinement
di: Shi, Zeru, et al.
Pubblicazione: (2026)

Towards Quantum Accelerated Large-scale Topology Optimization
di: Ye, Zisheng, et al.
Pubblicazione: (2025)

PTZ-Calib: Robust Pan-Tilt-Zoom Camera Calibration
di: Guo, Jinhui, et al.
Pubblicazione: (2025)

Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs
di: Tong, Jintao, et al.
Pubblicazione: (2025)

General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks
di: Liu, Junlin, et al.
Pubblicazione: (2026)

SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMs
di: Ye, Guanting, et al.
Pubblicazione: (2026)

Context-Aware Multi-Turn Visual-Textual Reasoning in LVLMs via Dynamic Memory and Adaptive Visual Guidance
di: Shen, Weijie, et al.
Pubblicazione: (2025)

Multimodal Data Storage and Retrieval for Embodied AI: A Survey
di: Lu, Yihao, et al.
Pubblicazione: (2025)

Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context
di: Zheng, Ge, et al.
Pubblicazione: (2025)

CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation
di: Leng, Jixuan, et al.
Pubblicazione: (2025)

Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence
di: He, Jinghan, et al.
Pubblicazione: (2024)

Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMs
di: Wang, Chaoyang, et al.
Pubblicazione: (2025)