Image de couverture de livre

MMGeoLM: Hard Negative Contrastive Learning for Fine-Grained Geometric Understanding in Large Multimodal Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Kai, Bai, Yushi, Yang, Zhen, Zhang, Jiajie, Qi, Ji, Hou, Lei, Li, Juanzi
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MM-MATH: Advancing Multimodal Math Evaluation with Process Evaluation and Fine-grained Classification
par: Sun, Kai, et autres
Publié: (2024)

LongAlign: A Recipe for Long Context Alignment of Large Language Models
par: Bai, Yushi, et autres
Publié: (2024)

Pre-training Distillation for Large Language Models: A Design Space Exploration
par: Peng, Hao, et autres
Publié: (2024)

DICE: Detecting In-distribution Contamination in LLM's Fine-tuning Phase for Math Reasoning
par: Tu, Shangqing, et autres
Publié: (2024)

WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models
par: Tu, Shangqing, et autres
Publié: (2023)

Enhancing Conceptual Understanding in Multimodal Contrastive Learning through Hard Negative Samples
par: Rösch, Philipp J., et autres
Publié: (2024)

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
par: Chen, Jianhui, et autres
Publié: (2024)

VidCoM: Fast Video Comprehension through Large Language Models with Multimodal Tools
par: Qi, Ji, et autres
Publié: (2023)

An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes
par: Qi, Ji, et autres
Publié: (2025)

Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models
par: Lin, Nianyi, et autres
Publié: (2025)

DeepPrune: Parallel Scaling without Inter-trace Redundancy
par: Tu, Shangqing, et autres
Publié: (2025)

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
par: Zhang, Jiajie, et autres
Publié: (2024)

Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards
par: Zhang, Jiajie, et autres
Publié: (2026)

SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression
par: Wen, Haoming, et autres
Publié: (2025)

LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
par: Bai, Yushi, et autres
Publié: (2024)

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
par: Bai, Yushi, et autres
Publié: (2023)

AdaptThink: Reasoning Models Can Learn When to Think
par: Zhang, Jiajie, et autres
Publié: (2025)

LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks
par: Bai, Yushi, et autres
Publié: (2024)

KB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge Bases
par: Zhang, Jiajie, et autres
Publié: (2024)

SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models
par: Wu, Yuhao, et autres
Publié: (2025)

CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning
par: Qi, Ji, et autres
Publié: (2024)

ADELIE: Aligning Large Language Models on Information Extraction
par: Qi, Yunjia, et autres
Publié: (2024)

Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning
par: Bai, Tianyi, et autres
Publié: (2025)

HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities
par: Dönmez, Esra, et autres
Publié: (2026)

LongReward: Improving Long-context Large Language Models with AI Feedback
par: Zhang, Jiajie, et autres
Publié: (2024)

Enhancing Contrastive Learning for Geolocalization by Discovering Hard Negatives on Semivariograms
par: Chen, Boyi, et autres
Publié: (2025)

Locality-Sensitive Hashing for Efficient Hard Negative Sampling in Contrastive Learning
par: Deuser, Fabian, et autres
Publié: (2025)

WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection
par: He, Guanzhong, et autres
Publié: (2025)

ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation
par: Lee, Zhicheng, et autres
Publié: (2025)

LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning
par: Wu, Yuhao, et autres
Publié: (2025)

Understanding Hyperbolic Metric Learning through Hard Negative Sampling
par: Yue, Yun, et autres
Publié: (2024)

Constraint Back-translation Improves Complex Instruction Following of Large Language Models
par: Qi, Yunjia, et autres
Publié: (2024)

Rehabilitation Exercise Quality Assessment through Supervised Contrastive Learning with Hard and Soft Negatives
par: Karlov, Mark, et autres
Publié: (2024)

HNCSE: Advancing Sentence Embeddings via Hybrid Contrastive Learning with Hard Negatives
par: Liu, Wenxiao, et autres
Publié: (2024)

Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization
par: Deng, Haolin, et autres
Publié: (2026)

Adaptive Global and Fine-Grained Perceptual Fusion for MLLM Embeddings Compatible with Hard Negative Amplification
par: Hu, Lexiang, et autres
Publié: (2026)

RA-SSU: Towards Fine-Grained Audio-Visual Learning with Region-Aware Sound Source Understanding
par: Sun, Muyi, et autres
Publié: (2026)

Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding
par: Zhang, Le, et autres
Publié: (2023)

MAVEN-Fact: A Large-scale Event Factuality Detection Dataset
par: Li, Chunyang, et autres
Publié: (2024)

VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
par: Peng, Hao, et autres
Publié: (2025)