AI 연구 논문 데일리

WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation

Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play

RM-R1: Reward Modeling as Reasoning

R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning

FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models

Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL

SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations

Think on your Feet: Adaptive Thinking via Reinforcement Learning for Social Agents

Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning

SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing

Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers

Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities

Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction

A Survey on Inference Engines for Large Language Models: Perspectives on Optimization and Efficiency

TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action

MUSAR: Exploring Multi-Subject Customization from Single-Subject Dataset via Attention Routing

LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis