Artigos de Pesquisa em IA Diários

PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models

DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning

Rethinking the Generation of High-Quality CoT Data from the Perspective of LLM-Adaptive Question Difficulty Grading

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Causal-Copilot: An Autonomous Causal Analysis Agent

Unchecked and Overlooked: Addressing the Checkbox Blind Spot in Large Language Models with CheckboxQA

CRUST-Bench: A Comprehensive Benchmark for C-to-safe-Rust Transpilation

Decoupled Global-Local Alignment for Improving Compositional Understanding

RePOPE: Impact of Annotation Errors on the POPE Benchmark

I-Con: A Unifying Framework for Representation Learning

Tina: Tiny Reasoning Models via LoRA

Trillion 7B Technical Report

Progressive Language-guided Visual Learning for Multi-Task Visual Grounding

AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset

Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model

VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models

DreamO: A Unified Framework for Image Customization