Imagen de Portada

From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Du, Hang, Zhang, Jiayang, Nan, Guoshun, Deng, Wendi, Chen, Zhenyan, Zhang, Chenyang, Xiao, Wang, Huang, Shan, Pan, Yuqi, Qi, Tao, Leng, Sicong
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly
por: Du, Hang, et al.
Publicado: (2024)

Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly
por: Du, Hang, et al.
Publicado: (2024)

InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search
por: Hou, Bohan, et al.
Publicado: (2026)

RIMO: An Easy-to-Evaluate, Hard-to-Solve Olympiad Benchmark for Advanced Mathematical Reasoning
por: Chen, Ziye, et al.
Publicado: (2025)

Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions
por: Xu, Jingxin, et al.
Publicado: (2025)

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty
por: Ling, Zehui, et al.
Publicado: (2025)

Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution
por: Sinha, Ankita, et al.
Publicado: (2024)

Two Is Better Than One: Rotations Scale LoRAs
por: Guo, Hongcan, et al.
Publicado: (2025)

Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
por: Parashar, Shubham, et al.
Publicado: (2025)

From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision
por: Yu, Chuang, et al.
Publicado: (2024)

LDDR: Linear-DPP-Based Dynamic-Resolution Frame Sampling for Video MLLMs
por: Chen, Jingfeng, et al.
Publicado: (2026)

MOF‐Based Electrocatalysts for Water Electrolysis, Energy Storage, and Sensing: Progress and Insights
por: Tao Pan, et al.
Publicado: (2025)

Interleaved Tool-Call Reasoning for Protein Function Understanding
por: Fan, Chuanliu, et al.
Publicado: (2026)

Vector Retrieval with Similarity and Diversity: How Hard Is It?
por: Gao, Hang, et al.
Publicado: (2024)

WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation
por: Chow, Wei, et al.
Publicado: (2025)

Progressive Feedforward Collapse of ResNet Training
por: Wang, Sicong, et al.
Publicado: (2024)

Rethinking Easy-to-Hard: Limits of Curriculum Learning in Post-Training for Deductive Reasoning
por: Mordig, Maximilian, et al.
Publicado: (2026)

VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning
por: Yuan, Ruifeng, et al.
Publicado: (2025)

An Easy Approach to the Hard Problem Of Consciousness
por: Senkevich, Victor
Publicado: (2025)

Advancing Expert Specialization for Better MoE
por: Guo, Hongcan, et al.
Publicado: (2025)

Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning
por: Yin, Shaofeng, et al.
Publicado: (2026)

Research Progress of Ferroptosis in Cerebral Infarction
por: Yilan Fei, et al.
Publicado: (2026)

Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning
por: Luo, Qin-Wen, et al.
Publicado: (2026)

A Task-Centric Theory for Iterative Self-Improvement with Easy-to-Hard Curricula
por: Liu, Chenruo, et al.
Publicado: (2026)

Global Context Compression with Interleaved Vision-Text Transformation
por: Jiao, Dian, et al.
Publicado: (2026)

From Easy to Hard: Building a Shortcut for Differentially Private Image Synthesis
por: Li, Kecen, et al.
Publicado: (2025)

Harnessing the Power of Interleaving and Counterfactual Evaluation for Airbnb Search Ranking
por: Zhang, Qing, et al.
Publicado: (2025)

Emergent Misalignment is Easy, Narrow Misalignment is Hard
por: Soligo, Anna, et al.
Publicado: (2026)

FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning
por: Ge, Haonan, et al.
Publicado: (2025)

Query Recovery from Easy to Hard: Jigsaw Attack against SSE
por: Nie, Hao, et al.
Publicado: (2024)

Beyond Easy Wins: A Text Hardness-Aware Benchmark for LLM-generated Text Detection
por: Ayoobi, Navid, et al.
Publicado: (2025)

Easy, Rapid and High‐Throughput Production of Single and Multicompartment Liposomes by Vortex Emulsification
por: Zhen‐Hong Luo, et al.
Publicado: (2024)

EasyRobust: A Comprehensive and Easy-to-use Toolkit for Robust and Generalized Vision
por: Mao, Xiaofeng, et al.
Publicado: (2025)

Streaming Hallucination Detection in Long Chain-of-Thought Reasoning
por: Lu, Haolang, et al.
Publicado: (2026)

Bioinformatics tools for mytle rust strain level diagnostic
por: Luo, Zhenyan
Publicado: (2026)

Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment
por: Song, Zhixue, et al.
Publicado: (2026)

The Unreasonable Effectiveness of Easy Training Data for Hard Tasks
por: Hase, Peter, et al.
Publicado: (2024)

MetaLint: Easy-to-Hard Generalization for Code Linting
por: Naik, Atharva, et al.
Publicado: (2025)

VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-based Group Relative Policy Optimization
por: Cao, Xinye, et al.
Publicado: (2025)

AD-MIR: Bridging the Gap from Perception to Persuasion in Advertising Video Understanding via Structured Reasoning
por: Xu, Binxiao, et al.
Publicado: (2026)