arXiv:2601.16231v1 Announce Type: new Abstract: Multimodal foundation models that integrate audio, vision, and language achieve strong performance on reasoning and generation tasks, yet their robustness to adversarial manipulation remains poorly understood. We study a realistic and underexplored threat model: untargeted, audio-only adversarial attacks on trimodal audio-video-language models. We analyze six complementary attack objectives that target different stages of multimodal processing, including audio encoder representations, cross-modal attention, hidden states, and output likelihoods. Across three state-of-the-art models and multiple benchmarks, […]

Ver mais

Multimodal misinformation demands robust Cross-modal Entity Consistency (CEC) verification, aligning textual entities with visual depictions. Current large vision-language models (LVLMs) struggle with fine-grained entity verification, especially in complex “contextual mismatch” scenarios, failing to capture intricate relationships or leverage auxiliary information. To address this, we propose the Entity-Aware Cross-Modal Fusion Network (EACFN), a novel architecture for deep semantic alignment and robust integration of external visual evidence. EACFN incorporates modules for entity encoding, cross-attention for reference image enhancement, and a […]

Ver mais

I’ve recently been reading about Hierarchical Reinforcement Learning (HRL) and noticed that many papers rely on techniques such as state abstraction, temporal abstraction, and planning. However, I’m still relatively new to this area and finding it difficult to understand how these ideas fit together. Could anyone recommend good learning resources, tutorials, or survey papers that provide an accessible introduction to HRL and its core concepts? I only know about traditional RL and some model-based RL like Dreamer, TDMPC. […]

Ver mais

Implementing your own neural network can be hard, especially if you’re like me, coming from a computer science background, math equations/syntax makes you dizzy and you would understand things better using actual code. Today I’ll show you how easy it is to implement a flexible neural network and train it using the backpropagation algorithm.

Ver mais

Crypto users are expanding rapidly beyond on-chain native audiences. Most new users access blockchain functionality through intermediaries and embedded abstractions. A growing layer of infrastructure hides the underlying complexity of blockchain, enabling adoption without users being explicitly aware they are using crypto. As a result, real-world blockchain usage is scaling quickly. Common use cases include: Stablecoin and on-chain payments by institutions and enterprises. For example, BitPay enables purchases such as Ferrari with ETH, and our portfolio company Align […]

Ver mais

The ubiquity of machine learning (ML) and the demand for ever-larger models bring an increase in energy consumption and environmental impact. However, little is known about the energy scaling laws in ML, and existing research focuses on training cost — ignoring the larger cost of inference. Furthermore, tools for measuring the energy consumption of ML do not provide actionable feedback. To address these gaps, we developed Energy Consumption Optimiser (ECOpt): a hyperparameter tuner that optimises for energy efficiency […]

Ver mais