Artigos de Pesquisa em IA Diários

PUMA: Empowering Unified MLLM with Multi-granular Visual Generation

AutoTrain: No-code training for state-of-the-art models

Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant

SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation

SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree

Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages

Zero-shot Model-based Reinforcement Learning using Large Language Models

Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training

Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs

RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style

DM-Codec: Distilling Multimodal Representations for Speech Tokenization

How Many Van Goghs Does It Take to Van Gogh? Finding the Imitation Threshold

CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy

Router-Tuning: A Simple and Effective Approach for Enabling Dynamic-Depth in Transformers

Baichuan Alignment Technical Report

Alchemy: Amplifying Theorem-Proving Capability through Symbolic Mutation

Pre-training Distillation for Large Language Models: A Design Space Exploration

Selecting Influential Samples for Long Context Alignment via Homologous Models' Guidance and Contextual Awareness Measurement

Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos

Meta-Chunking: Learning Efficient Text Segmentation via Logical Perception

FrugalNeRF: Fast Convergence for Few-shot Novel View Synthesis without Learned Priors

CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution

In-context learning and Occam's razor