Artigos de Pesquisa em IA Diários

HackerRank-ASTRA: Evaluating Correctness & Consistency of Large Language Models on cross-domain multi-file project problems

LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer

Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation

TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets

Boosting Multimodal Reasoning with MCTS-Automated Structured Thinking

Large Language Model Guided Self-Debugging Code Generation

Demystifying Long Chain-of-Thought Reasoning in LLMs

On Teacher Hacking in Language Model Distillation

A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

LIMO: Less is More for Reasoning

Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning

Activation-Informed Merging of Large Language Models

Jailbreaking with Universal Multi-Prompts