HuggingFace
Multimodal Reranking Is a System One Decision
Multimodal rerankers are usually dedicated models: a vision-language model (VLM) is trained on retrieval data to scor...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading
Mixture-of-experts (MoE) models often exceed a single accelerator's memory capacity. Offloading experts to host memor...
HuggingFace
Evolving Agent Interfaces
Computer-use agents are limited by the interfaces humans give them. An agent may type a spreadsheet cell by cell when...
HuggingFace
λ_0: Scaling Open-World Egocentric Human Data for Humanoid Loco-Manipulation
Humanoid loco-manipulation requires coordinated whole-body interaction with the physical world, yet collecting robot ...
HuggingFace
OmniCam: Omni-Camera Trajectory Generation via Geometry-Grounded Pose Token Learning
Camera trajectories control viewpoint changes in video generation, scene reconstruction, and robotic perception. Gene...
HuggingFace
Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research
We present Épi, an autonomous research agent that sustains investigations across model sessions and evolves its metho...
HuggingFace
SpecKCast: Spectral Kalman Forecasting for Diffusion Acceleration
Diffusion Transformers (DiTs) achieve high-fidelity image and video generation, but they suffer from substantial infe...
HuggingFace
On the Limits of Scale: Inverse Scaling in Vision-Language Models
Scaling laws suggest that increasing model size, training data, and compute generally yields monotonic performance im...
HuggingFace
Joints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary Rigs
Video generation models can now depict remarkably realistic motion. Yet it is unclear how to use this motion beyond p...
HuggingFace
Muse Glimmer 30B: An On-Device Agentic Model
We introduce Muse Glimmer, an open-source 30B parameter causal language model with perception encoder, purpose-built ...
HuggingFace
Event-STVG: Spatio-Temporal Video Grounding for Long-Form Event Reasoning
Spatio-Temporal Video Grounding (STVG) aims to jointly localize a target in space and time given a natural-language q...
HuggingFace
Unsupervised Tool Evolution for Coding Agents in Data-Lake Analytics
Coding agents can answer analytical questions over a data lake by discovering, cleaning, and joining the relevant dat...