Generating high-fidelity videos with diffusion models has long been bottlenecked by computational inefficiency. Even on powerful GPUs, producing just a…
LLaMA-MoE: High-Performance Mixture-of-Experts LLM with Only 3.5B Active Parameters 994
If you’re a developer, researcher, or technical decision-maker working with large language models (LLMs), you’ve likely faced a tough trade-off:…
MedLSAM: Slash Annotation Effort in 3D CT Segmentation with Fully Automatic Localization and SAM Integration 505
Medical image segmentation—especially in 3D CT scans—is a cornerstone of clinical decision support, surgical planning, and radiological research. Yet, despite…
HaluEval: Detect and Benchmark LLM Hallucinations Across QA, Dialogue, and Summarization 536
Large language models (LLMs) like ChatGPT are transforming how we interact with AI—but they often “make things up.” These fabricated,…
pyvene: Intervene on Any PyTorch Model’s Internal States—No Code Rewriting Required 819
Imagine being able to precisely edit, steer, or probe a trained PyTorch model—without touching its source code or retraining it…
IoA: Enable Heterogeneous AI Agents to Collaborate Like the Internet — Solve Complex Tasks Beyond Single-Agent Limits 770
Imagine a world where AI agents—each with unique skills like web browsing, code execution, or data analysis—can autonomously find one…
SVFR: Restore Blurry, Damaged, or Black-and-White Face Videos in One Unified Workflow 835
Video face restoration is a critical yet challenging task in real-world applications—whether you’re enhancing surveillance footage, digitizing decades-old home videos,…
HarmBench: A Standardized Framework to Evaluate LLM Safety Against Malicious Prompts 752
Large language models (LLMs) are increasingly deployed in high-stakes applications—from customer support chatbots to enterprise decision aids—but they remain vulnerable…
FSD V2: High-Performance, Fully Sparse 3D Object Detection for Autonomous Systems 868
For engineers and technical decision-makers building perception stacks in autonomous driving, robotics, or 3D scene understanding, accurately detecting objects from…
LServe: Accelerate Long-Context LLM Inference with Unified Sparse Attention—No Accuracy Trade-Off 790
Deploying large language models (LLMs) to handle long documents, extensive chat histories, or detailed technical manuals remains a major bottleneck…