state-of-the-art — 4 Technical Articles

Jan 27, 2026 · Artificial Intelligence

How ACLNet Boosts Skeleton-Based Action Recognition with Affinity Contrastive Learning

ACLNet, an Affinity Contrastive Learning Network introduced by researchers from the Chinese Academy of Sciences, BUPT and Moonshot AI, tackles the ambiguity of skeleton‑based human activity recognition by modeling inter‑class structural similarities and intra‑class margins, achieving state‑of‑the‑art results on NTU‑RGB+D, Kinetics‑Skeleton, FineGYM and other benchmarks.

affinity contrastive learninggraph convolutional networkhuman activity analysis

0 likes · 11 min read

How ACLNet Boosts Skeleton-Based Action Recognition with Affinity Contrastive Learning

Amap Tech

Jul 24, 2025 · Artificial Intelligence

FingER: Fine-Grained, Reasoning‑Based Evaluation of AI‑Generated Videos

This article introduces FingER, a novel entity‑level evaluation framework and the FingER‑Instruct‑60k dataset for assessing AI‑generated video quality with fine‑grained reasoning, and demonstrates its state‑of‑the‑art performance on multiple benchmarks using advanced training strategies such as GRPO.

AI-generated videofine-grained evaluationmultimodal model

0 likes · 9 min read

FingER: Fine-Grained, Reasoning‑Based Evaluation of AI‑Generated Videos

AIWalker

May 16, 2025 · Artificial Intelligence

GPDiT Sets New SOTA in Video Generation with Faster, Unified Diffusion‑Autoregressive Framework

GPDiT, a novel autoregressive diffusion transformer, unifies diffusion and autoregressive modeling for video generation, introducing lightweight causal attention and a parameter‑free rotation‑based time conditioning that boost temporal consistency and cut training/inference costs, achieving state‑of‑the‑art results on multiple benchmarks.

Diffusion Modelsautoregressive modelingcausal attention

0 likes · 16 min read

GPDiT Sets New SOTA in Video Generation with Faster, Unified Diffusion‑Autoregressive Framework

Alibaba Cloud Big Data AI Platform

Feb 18, 2025 · Artificial Intelligence

One-Click Deployment of Cutting-Edge Text-to-Video and Voice Interaction Models

This article introduces the state‑of‑the‑art Step‑Video‑T2V text‑to‑video model and the Step‑Audio‑Chat voice interaction model, outlines their technical specifications and benchmark results, and provides a detailed step‑by‑step guide for deploying both models with a single click using Alibaba Cloud's PAI Model Gallery.

AI Model DeploymentPAI Model GalleryVoice Interaction

0 likes · 9 min read

One-Click Deployment of Cutting-Edge Text-to-Video and Voice Interaction Models