AI研究論文每日精選

Apollo: An Exploration of Video Understanding in Large Multimodal Models

GenEx: Generating an Explorable World

SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding

Large Action Models: From Inception to Implementation

BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities

FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens

InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption

ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generation

FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing

LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity

FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers

SCBench: A KV Cache-Centric Analysis of Long-Context Methods

Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation

GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs

TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies

Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attacks on Breast Ultrasound Images