AI研究論文每日精選

Style-Friendly SNR Sampler for Style-Driven Generation

TÜLU 3: Pushing Frontiers in Open Language Model Post-Training

OminiControl: Minimal and Universal Control for Diffusion Transformer

A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection

MyTimeMachine: Personalized Facial Age Transformation

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

Large Multi-modal Models Can Interpret Features in Large Multi-modal Models

VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection

Efficient Long Video Tokenization via Coordinated-based Patch Reconstruction

Novel View Extrapolation with Video Diffusion Priors

VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinement

WildLMa: Long Horizon Loco-Manipulation in the Wild

Adapting Vision Foundation Models for Robust Cloud Segmentation in Remote Sensing Images

One to rule them all: natural language to bind communication, perception and action