HuggingFace
Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning
While generative AI has significantly advanced video editing, existing methods primarily focus on single-shot or shor...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Procedura: Agentic 3D Modeling with Procedural Control
Native 3D generators now recover impressive mesh geometry from a single image. However, a dense mesh stays soft where...
HuggingFace
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models
A common strategy for scaling world models is to train on more crawled video with more compute. We argue that this st...
HuggingFace
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents
Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvem...
HuggingFace
LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale
We introduce LibriBrain100, a large-scale MEG dataset for speech decoding designed from the ground up for reproducibl...
HuggingFace
Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling
The development of 0.1^{circ} global weather forecasting models based on machine learning (ML) is constrained by the ...
HuggingFace
Prefix Sliding for efficient test-time scaling
Test-time scaling uses extra test-time compute to improve performance, such as letting language models reason longer ...
HuggingFace
Skill Issue: Are Skills Language-Invariant in LLMs?
Large language models access knowledge inconsistently across languages, but to what extent do they differ in their sk...
HuggingFace
GUI-Primitives: Diagnosing Spatial Reasoning Failures in Vision-Language GUI Grounding
Computer-use agents ground natural-language instructions in screenshots to locate interface elements, yet existing be...
arXiv
DualOPSD: Adaptive Privileged Teachers for On-Policy Self-Distillation
On-policy self-distillation (OPSD) uses a privileged copy of the student model to provide dense supervision without a...
arXiv
Trace Integrity for LLM Data Agents: A Vision for Auditable Structured Reasoning in Real-World Systems
Answer accuracy is an insufficient reliability signal for LLM data agents. In structured-data tasks, a benchmark-corr...
arXiv
The Value of Human Expertise
We consider optimization applications with unknown parameters where the decision maker believes that the optimal valu...