Artigos de Pesquisa em IA Diários

Are Your LLMs Capable of Stable Reasoning?

OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain

Multi-Dimensional Insights: Benchmarking Real-World Personalization in Large Multimodal Models

Compressed Chain of Thought: Efficient Reasoning Through Dense Representations

VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation

Emergence of Abstractions: Concept Encoding and Decoding Mechanism for In-Context Learning in Transformers

Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration

Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents

Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion

SUGAR: Subject-Driven Video Customization in a Zero-Shot Manner

Seeker: Towards Exception Safety Code Generation with Intermediate Language Agents Framework

When to Speak, When to Abstain: Contrastive Decoding with Abstention

MIVE: New Design and Benchmark for Multi-Instance Video Editing