HuggingFace
Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation
Text and image conditioned 3D models now generate convincing assets, but they still offer little direct control over ...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs
Open-weight Large Language Models (LLMs) enable scientific progress and broad deployment. However, they make it diffi...
HuggingFace
Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining
As AI labs approach a data ceiling where compute capacity outpaces the rate of new high-quality text generation, lang...
HuggingFace
Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?
Computer-use agents (CUAs) now act on a user's behalf across personal applications such as email, calendars, and to-d...
HuggingFace
Toward Parking Spot Occupancy Recognition: A Self-Supervised Approach
As urban areas expand, automatic monitoring of parking lots becomes essential for efficient and sustainable cities. T...
HuggingFace
AC-ODM: Actor--Critic Online Data Mixing for Sample-Efficient LLM Pretraining
Optimizing pretraining data composition is pivotal for LLM generalization. While dynamic mixing outperforms static st...
HuggingFace
An Exploratory Case Study of LLM-Assisted Refactoring and Gameplay Feature Generation in an Endless Runner Game
Large language models (LLMs) are increasingly used to support software development, but their practical usefulness in...
HuggingFace
Robusto-2: Benchmarking Humans & VLMs for Autonomous Driving in Lima & New York City
As Self-Driving Cars continue to expand internationally and use multi-modal systems such as VLMs as a cognitive backb...
HuggingFace
Vera: A Layered Diffusion Model for Content-Preserving Video Editing
Video diffusion models have enabled remarkable progress in video generation and editing. However, content preservatio...
HuggingFace
A Verifiable Search Is Not a Learnable Chain-of-Thought
It is tempting to assume any task solvable by a short program can be taught to a model as its chain-of-thought: write...
HuggingFace
Libretto: Giving LLM Agents a Sense of Musical Structure
Generative music systems can now produce impressive audio from text prompts, but audio outputs are difficult to inspe...
HuggingFace
Go-with-the-Track: Video Compositing and Motion Control with Point Tracking
Filmmaking demands precise motion control and reference image compositing -- capabilities that existing methods treat...