Artigos de Pesquisa em IA Diários

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes

MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space

Could Thinking Multilingually Empower LLM Reasoning?

AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis

Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations

It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization

Generative AI Act II: Test Time Scaling Drives Cognition Engineering

CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives

HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation

Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images

Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models

Cost-of-Pass: An Economic Framework for Evaluating Language Models

Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization

Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results

Filter2Noise: Interpretable Self-Supervised Single-Image Denoising for Low-Dose CT with Attention-Guided Bilateral Filtering