Cover Image

From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Luo, Ruilin, Shi, Chufan, Zhang, Yizhen, Yang, Cheng, Jiang, Songtao, Guan, Tongkun, Chen, Ruizhe, Chu, Ruihang, Wang, Peng, Yang, Mingkun, Yang, Yujiu, Lin, Junyang, Yang, Zhibo
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning
by: Ding, Yang, et al.
Published: (2025)

Unlocking Multimodal Mathematical Reasoning via Process Reward Model
by: Luo, Ruilin, et al.
Published: (2025)

CodePercept: Code-Grounded Visual STEM Perception for MLLMs
by: Guan, Tongkun, et al.
Published: (2026)

Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos
by: Jiang, Songtao, et al.
Published: (2026)

Generative Universal Verifier as Multimodal Meta-Reasoner
by: Zhang, Xinchen, et al.
Published: (2025)

LiFi: Lightweight Controlled Text Generation with Fine-Grained Control Codes
by: Shi, Chufan, et al.
Published: (2024)

LLM2: Let Large Language Models Harness System 2 Reasoning
by: Yang, Cheng, et al.
Published: (2024)

ContextVis: Envision Contextual Learning and Interaction with Generative Models
by: Shui, Bo, et al.
Published: (2024)

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
by: Lin, Zicheng, et al.
Published: (2024)

CriticBench: Benchmarking LLMs for Critique-Correct Reasoning
by: Lin, Zicheng, et al.
Published: (2024)

See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning
by: Zhang, Shuoshuo, et al.
Published: (2025)

Mitigating the Reasoning Tax in Vision-Language Fine-Tuning with Input-Adaptive Depth Aggregation
by: Ren, Yiming, et al.
Published: (2026)

From Sparse Decisions to Dense Reasoning: A Multi-attribute Trajectory Paradigm for Multimodal Moderation
by: Gu, Tianle, et al.
Published: (2026)

PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQL
by: Luo, Ruilin, et al.
Published: (2024)

Progressive Knowledge Graph Completion
by: Li, Jiayi, et al.
Published: (2024)

Personalized Diffusion Model Reshapes Cold-Start Bundle Recommendation
by: Bui, Tuan-Nghia, et al.
Published: (2025)

Teaching Your Models to Understand Code via Focal Preference Alignment
by: Wu, Jie, et al.
Published: (2025)

Panoramic Multimodal Semantic Occupancy Prediction for Quadruped Robots
by: Zhao, Guoqiang, et al.
Published: (2026)

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
by: Ren, Yiming, et al.
Published: (2026)

CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making
by: Jiang, Songtao, et al.
Published: (2025)

IDProxy: Cold-Start CTR Prediction for Ads and Recommendation at Xiaohongshu with Multimodal LLMs
by: Zhang, Yubin, et al.
Published: (2026)

Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors
by: Guan, Tongkun, et al.
Published: (2023)

Video-Zero: Self-Evolution Video Understanding
by: Zhang, Ruixu, et al.
Published: (2026)

O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing
by: Chen, Yuqing, et al.
Published: (2025)

Velocity-Space 3D Asset Editing
by: Liu, Hao, et al.
Published: (2026)

PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer
by: Guan, Tongkun, et al.
Published: (2024)

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
by: Wei, Lai, et al.
Published: (2025)

A Thorough Examination of Decoding Methods in the Era of LLMs
by: Shi, Chufan, et al.
Published: (2024)

Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability
by: Zhu, Zhiyu, et al.
Published: (2025)

PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning
by: Zhang, Yizhen, et al.
Published: (2025)

Nav-$R^2$ Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation
by: Xiang, Wentao, et al.
Published: (2025)

CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy
by: Yang, Zhibo, et al.
Published: (2024)

Graph Neural Patching for Cold-Start Recommendations
by: Chen, Hao, et al.
Published: (2024)

Deep Evolutional Instant Interest Network for CTR Prediction in Trigger-Induced Recommendation
by: Xiao, Zhibo, et al.
Published: (2024)

Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning
by: Chen, Shuang, et al.
Published: (2025)

Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
by: Chen, Kun, et al.
Published: (2025)

MARC: Multimodal and Multi-Task Agentic Retrieval-Augmented Generation for Cold-Start Recommender System
by: Cho, Seung Hwan, et al.
Published: (2025)

ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models
by: Yang, Cheng, et al.
Published: (2026)

Design of High‐Sensitivity Cold‐Start Circuit for Wireless Energy Harvesting With Low Start‐Up Voltage
by: Feng Shi, et al.
Published: (2024)

Pano360: Perspective to Panoramic Vision with Geometric Consistency
by: Zhu, Zhengdong, et al.
Published: (2026)