BestHub
Sign in
AIWalker
Author

AIWalker

Focused on computer vision, image processing, color science, and AI algorithms; sharing hardcore tech, engineering practice, and deep insights as a diligent AI technology practitioner.

162
Articles
0
Likes
86
Views
0
Comments
Recent Articles

Latest from AIWalker

100 recent articles max
AIWalker
AIWalker
Apr 28, 2025 · Artificial Intelligence

SimpleAR: Autoregressive Visual Generation at 1024×1024 Using Only 0.5B Parameters

SimpleAR is a minimalist autoregressive visual generation framework that, with only 0.5 B parameters, achieves competitive 1024×1024 image synthesis through a three‑stage pipeline of large‑scale pretraining, supervised fine‑tuning, and GRPO‑based reinforcement learning, and demonstrates significant inference speedups using KV‑cache, vLLM, and speculative decoding.

Inference Accelerationautoregressive generationbenchmark
0 likes · 14 min read
SimpleAR: Autoregressive Visual Generation at 1024×1024 Using Only 0.5B Parameters
AIWalker
AIWalker
Apr 17, 2025 · Artificial Intelligence

Unveiling DeepSeek’s Janus Series: Decoupled Visual Encoding for Unified Multimodal Understanding and Generation

This article provides an in‑depth analysis of DeepSeek’s Janus and Janus‑Pro models, explaining how decoupling visual encoding resolves the conflict between multimodal understanding and generation, detailing training stages, data scaling, architectural choices, and presenting extensive benchmark results that demonstrate significant performance gains.

DeepSeekJanusModel Scaling
0 likes · 23 min read
Unveiling DeepSeek’s Janus Series: Decoupled Visual Encoding for Unified Multimodal Understanding and Generation
AIWalker
AIWalker
Apr 16, 2025 · Artificial Intelligence

Plug‑and‑Play Multi‑Scale Attention: A Seamless Boost for Model Performance

This article reviews recent multi‑scale attention breakthroughs—including EMA, MSDA, VWA, and related modules—showing how they improve accuracy, cut FLOPs by up to 70%, and can be inserted into existing models with minimal effort, backed by code and paper links.

Plug-and-Playcomputer visiondeep learning
0 likes · 10 min read
Plug‑and‑Play Multi‑Scale Attention: A Seamless Boost for Model Performance
AIWalker
AIWalker
Apr 13, 2025 · Artificial Intelligence

Huawei Pangu Ultra: 135B Ascend‑Native Dense LLM Without Nvidia GPUs

Huawei's Pangu Ultra introduces a 135‑billion‑parameter dense language model trained entirely on Ascend NPUs, detailing novel stability architectures, a domain‑aware tokenizer, multi‑stage pre‑training, extensive system optimizations, and benchmark results that surpass leading models such as Llama 405B and DeepSeek‑R1.

Ascend NPUDense ModelLarge Language Model
0 likes · 15 min read
Huawei Pangu Ultra: 135B Ascend‑Native Dense LLM Without Nvidia GPUs
AIWalker
AIWalker
Apr 11, 2025 · Artificial Intelligence

Teaching Large Language Models to Predict Image Quality Scores with DeQA-Score

DeQA-Score, a CVPR 2025 work, shows how to train multimodal large language models to regress continuous image quality scores by discretizing scores into soft-label level tokens, preserving Gaussian distribution statistics and achieving state‑of‑the‑art performance without any installation.

CVPR2025DeQA-Scoreimage quality assessment
0 likes · 8 min read
Teaching Large Language Models to Predict Image Quality Scores with DeQA-Score
AIWalker
AIWalker
Apr 10, 2025 · Artificial Intelligence

DCEdit: Precise Text-Guided Image Editing that Preserves Backgrounds

DCEdit introduces a precise semantic localization strategy and a dual-level control mechanism for text‑guided image editing, delivering superior background preservation and editing quality, as demonstrated on the new RW‑800 benchmark and extensive comparisons with state‑of‑the‑art diffusion models.

AIbenchmarkdiffusion models
0 likes · 16 min read
DCEdit: Precise Text-Guided Image Editing that Preserves Backgrounds
AIWalker
AIWalker
Apr 8, 2025 · Artificial Intelligence

AgenticIR: An Agentic System for Restoring Images with Complex Degradations

AgenticIR combines visual language models and large language models in a multi‑stage reasoning workflow—perception, planning, execution, reflection, and adjustment—to evaluate, plan, and iteratively apply specialized restoration tools, achieving superior results on complexly degraded images compared to baseline methods.

Agentic SystemsICLR 2025Vision-Language Models
0 likes · 15 min read
AgenticIR: An Agentic System for Restoring Images with Complex Degradations