ByteDance’s next-gen AI model can generate clips based on text, images, audio, and video

Big Tech’s race to leapfrog the latest AI models continues with the launch of ByteDance’s next-gen video generator. In a blog post, ByteDance – the China-based company behind TikTok – says Seedance ...
IEEE

Data Poisoning Offensive and Defensive System in FL-enabled Low-Altitude IoT Scenario: Unlearnable Example Attack and Model Similarity Defend

Abstract: Low-altitude Internet of Things (LAIOT) integrates sensing, communication, and edge intelligence within aerial networks. As a distributed training paradigm, federated learning (FL) is a ...
ZDNet

Move over, Claude: Moonshot's new AI model lets you vibe-code from a single video upload

Moonshot debuted its open-source Kimi K2.5 model on Tuesday. It can generate web interfaces based solely on images or video. It also comes with an "agent swarm" beta feature. Alibaba-backed Chinese AI ...
GitHub

High-level visual representations in the human brain are aligned with large language models

The human brain extracts complex information from visual inputs, including objects, their spatial and semantic interrelations, and their interactions with the environment. However, a quantitative ...
GitHub

[NeurIPS 2025] ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models

ChartMuseum is a chart question answering benchmark designed to evaluate reasoning capabilities of large vision-language models (LVLMs) over real-world chart images. The benchmark consists of 1162 ...
IEEE

ChipVQA: Benchmarking Visual Language Models for Chip Design

Abstract: Large-language models (LLMs) have exhibited great potential to assist chip designs and analysis. Recent research and efforts are mainly focusing on text-based tasks including general QA, ...