AI 연구 논문 데일리

DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping

DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking

SoS1: O1 and R1-Like Reasoning LLMs are Sum-of-Square Solvers

LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation

Preference Learning Unlocks LLMs' Psycho-Counseling Skills

Tell me why: Visual foundation models as self-explainable classifiers

Chain of Draft: Thinking Faster by Writing Less

Optimal Brain Apoptosis

How far can we go with ImageNet for Text-to-Image generation?

LettuceDetect: A Hallucination Detection Framework for RAG Applications

HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models

Predictive Data Selection: The Data That Predicts Is the Data That Teaches

MIGE: A Unified Framework for Multimodal Instruction-Based Image Generation and Editing

Multi-Turn Code Generation Through Single-Step Rewards

TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval

EgoNormia: Benchmarking Physical Social Norm Understanding

ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents

Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids