Artigos de Pesquisa em IA Diários

Kuwain 1.5B: An Arabic SLM via Language Injection

TTRL: Test-Time Reinforcement Learning

The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks

Describe Anything: Detailed Localized Image and Video Captioning

Learning Adaptive Parallel Reasoning with Language Models

LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale

BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation

IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs

LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities

Efficient Pretraining Length Scaling

WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

Personalized Text-to-Image Generation with Auto-Regressive Models

CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning

From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning

Vidi: Large Multimodal Models for Video Understanding and Editing

RealisDance-DiT: Simple yet Strong Baseline towards Controllable Character Animation in the Wild

Progent: Programmable Privilege Control for LLM Agents

MR. Video: "MapReduce" is the Principle for Long Video Understanding

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting

IPBench: Benchmarking the Knowledge of Large Language Models in Intellectual Property

DiffVox: A Differentiable Model for Capturing and Analysing Professional Effects Distributions