AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
3,920 papers
This work proposes Counterfactual Evidence Disentanglement (CED), a training-time evidence audit for VLM grounding, which outperforms prior RL-based post-training methods, with targeted analyses verifying its object-centric signal.
We present DynActiveGS, a dynamic-aware active reconstruction framework based on 3D Gaussian Splatting (3DGS) for autonomous exploration in dynamic environments. The framework incrementally reconstructs a 3D Gaussian scene representation while suppressing motion-corrupted observations through online uncertainty predict...
Flow-Map GRPO enables effective RL alignment of pretrained deterministic flow-map generators while retaining their original parameterization, without retraining them as native stochastic models.
The results position JuZhou 1.0 as a practical approach to mobile text-to-image generation and provide a concrete reference for Chinese-native generation, domestic-compute training, and fully offline on-device deployment after one-time installation.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Unified Slots (Unified Slots), an unsupervised framework for learning robust and disentangled object-centric representations from videos, is introduced, achieving state-of-the-art performance in unsupervised object-centric video decomposition and tracking.
This work aggregates patch features from all views onto a single equirectangular panoramic canvas, and introduces a spatial pretraining curriculum by procedurally placing patch features of objects at chosen 3D world positions on an otherwise empty canvas, generating on-the-fly supervision spanning a broad range of spat...
This work proposes SelectStream, a selective latent-memory framework that keeps the current observation directly visible to a frozen VLM while exposing historical information only through a compact, query-conditioned evidence budget.
This work introduces Sci-Rho (Science Rhobustness), a dynamic benchmark for visually-grounded STEM problems spanning five subjects and seven languages, comprising 4,242 problem templates crafted by domain experts, including Olympiad medalists.
A transferability baseline for peach leaf diagnosis is established and the adaptation cost of moving from public benchmarks to operational orchards is quantified, establish a transferability baseline for peach leaf diagnosis and quantify the adaptation cost of moving from public benchmarks to operational orchards.
Text-to-video generation has advanced rapidly in visual quality, but remains under-evaluated for factuality and practical usefulness. We introduce knowledge-intensive video generation (KIVI), where models generate videos from short information-seeking prompts that ask for explanations, procedures, or demonstrations. To...
One-Forcing is proposed, a simple yet effective approach that augments the DMD objective with an auxiliary GAN loss for high-quality and efficient one-step video generation, and finds that framewise autoregression stabilizes adversarial training, enabling higher-quality generation with substantially fewer training iter...
This work proposes Counterfactual Relational Policy Optimization (CRPO), which explicitly trains Video LLMs to respond to controlled changes in the visual input, and introduces DyBench, a paired counterfactual benchmark with 3{,}014 videos and a strict pair-accuracy metric.
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
GPT-Lab
· gpt-lab.eu
Oct 8, 2026
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
A Blog post by H company on Hugging Face
A Blog post by Liquid AI on Hugging Face
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
