AI研究論文每日精選

On Path to Multimodal Generalist: General-Level and General-Bench

Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities

ZeroSearch: Incentivize the Search Capability of LLMs without Searching

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

Beyond Recognition: Evaluating Visual Perspective Taking in Vision Language Models

PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer

R&B: Domain Regrouping and Data Mixture Balancing for Efficient Foundation Model Training

Benchmarking LLMs' Swarm intelligence

OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning

Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving

OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution

LLM-Independent Adaptive RAG: Let the Question Speak for Itself

OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation

OSUniverse: Benchmark for Multimodal GUI-navigation AI Agents

Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey

RAIL: Region-Aware Instructive Learning for Semi-Supervised Tooth Segmentation in CBCT

AutoLibra: Agent Metric Induction from Open-Ended Feedback

Uncertainty-Weighted Image-Event Multimodal Fusion for Video Anomaly Detection

Cognitio Emergens: Agency, Dimensions, and Dynamics in Human-AI Knowledge Co-Creation

COSMOS: Predictable and Cost-Effective Adaptation of LLMs