AI研究論文每日精選

Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective

A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intents

SelfCodeAlign: Self-Alignment for Code Generation

BitStack: Fine-Grained Size Control for Compressed Large Language Models in Variable Memory Environments

Constraint Back-translation Improves Complex Instruction Following of Large Language Models

Language Models can Self-Lengthen to Generate Long Texts

NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks

Learning Video Representations without Natural Videos

AAAR-1.0: Assessing AI's Potential to Assist Research

Navigating the Unknown: A Chat-Based Collaborative Interface for Personalized Exploratory Tasks

BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays

DELTA: Dense Efficient Long-range 3D Tracking for any video

Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use

Minimum Entropy Coupling with Bottleneck

GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages