HuggingFace
Training, learning and inference: unified dynamics of neural systems
We define an atomic generation fact f=(u,tau,omega,z;rho), recording the origin, realized transformation, concrete oc...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
LMSM: LLM Security Framework Inspired by Linux Security Modules
Large language models (LLMs) are increasingly deployed with layered defenses, yet malicious prompts can still bypass ...
HuggingFace
Video Generative Models as Geometry Learner
Recent generative approaches to geometry estimation adapt pretrained image diffusion models and treat the task as ima...
HuggingFace
Rubric-to-Code Credit Assignment for Reinforcement Learning
Interactive web application generation requires models to produce usable HTML, CSS, and JavaScript applications from ...
HuggingFace
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing
LLM-based agents can interact with external environments through tool invocation, but this capability also introduces...
HuggingFace
Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction
Streaming 3D reconstruction from extremely long videos requires estimating camera motion and scene geometry online un...
HuggingFace
J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data
Self-evolving language models have recently emerged as a promising path toward superintelligence, with the advantage ...
HuggingFace
StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments
We present StarHarness, a framework for evolving environment-specific agent harnesses while keeping model weights fix...
HuggingFace
Paint What You See: Benchmarking Dexterous Visual Tool Use in Multimodal Agents
Evaluation is shifting from static QA toward agentic settings where models act through external tools. We identify a ...
HuggingFace
Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090
Language model pretraining has become almost synonymous with prohibitive cost, placing it out of reach for much of th...
HuggingFace
LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation
Autoregressive video diffusion enables scalable long-video generation by producing chunks from a bounded recent conte...
HuggingFace
Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion
Scaling video generation to long durations reveals a critical bottleneck: current models lack robust long-term memory...