[arXiv 2026] dVoting: Fast Voting for dLLMs

Elevate your AI research writing, no more tedious polishing ✨

Awesome streaming video understanding

[EMNLP 2025 Main] Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models

slime is an LLM post-training framework for RL Scaling.

Autonomous Agents (LLMs) research papers. Updated Daily.

OmniAgent: Audio-Guided Active Perception Agent for Omnimodal Audio-Video Understanding

[NeurIPS'25] FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance

Academic Personal Homepage of Keda Tao

OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models

This repo integrates DyCoke's token compression method with VLMs such as Gemma3 and InternVL3

[TMLR 2026] Survey: https://arxiv.org/pdf/2507.20198

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

[ICLR'25] Streaming Video Question-Answering with In-context Video KV-Cache Retrieval

VidKV: Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models

[CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models

[ICLR 2025 Spotlight] Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model

face attribute classification based on pytorch

这是一个arcface-pytorch的源码，可以用于训练自己的模型。