Introducing multimodal retrieval for Amazon Bedrock Knowledge Bases

Introducing multimodal retrieval for Amazon Bedrock Knowledge Bases

⋅

We are excited to announce the general availability of multimodal retrieval for Amazon Bedrock Knowledge Bases. This new capability adds native support for video and audio content, on top of text and images. With it you can build Retrieval Augmented Generation (RAG) applications that can search and retrieve information across text, images, audio, and video—all within a fully managed service. Modern enterprises store valuable information in multiple formats. Product documentation includes diagrams and screenshots, training materials contain instructional […]

Ver mais

Liked Liked

Using Grok to Avoid Personal Attacks While Correcting Misinformation on X

⋅

arXiv:2601.04251v1 Announce Type: new Abstract: Correcting misinformation in public online spaces often exposes users to hostility and ad hominem attacks, discouraging participation in corrective discourse. This study presents empirical evidence that invoking Grok, the native large language model on X, rather than directly confronting other users, is associated with different social responses during misinformation correction. Using an observational design, 100 correction replies across five high-conflict misinformation topics were analyzed, with corrections balanced between Grok-mediated and direct human-issued responses. […]

Ver mais

Liked Liked

Harnessing Implicit Cooperation: A Multi-Agent Reinforcement Learning Approach Towards Decentralized Local Energy Markets

⋅

This paper proposes implicit cooperation, a framework enabling decentralized agents to approximate optimal coordination in local energy markets without explicit peer-to-peer communication. We formulate the problem as a decentralized partially observable Markov decision problem that is solved through a multi-agent reinforcement learning task in which agents use stigmergic signals (key performance indicators at the system level) to infer and react to global states. Through a 3×3 factorial design on an IEEE 34-node topology, we evaluated three training paradigms […]

Ver mais

Liked Liked

[D] Ph.D. from a top Europe university, 10 papers at NeurIPS/ICML, ECML— 0 Interviews Big tech

⋅

I just wrapped up my CS Ph.D on anomaly detection. Here’s my profile in a nutshell: Research: 8 publications, 5 first-author at top ML venues (ICML, NeurIPS, ECML). 2 A* ICML, NeurIPS (both first author) Rest mid A* and some A. Reviewer for ICLR, KDD, ICML etc. Industry: Two working Student— one in ML one in deep learning. Skills: Python, PyTorch, scikit-learn, deep learning, classical ML, NLP, LLMs. Education: M.Sc. top 10%, I’m applying to research scientist and […]

Ver mais

Liked Liked

[P] WASM bash shell sandbox for AI agents

⋅

We built a WASM-based sandbox for running LLM-generated code in agentic workflows. The problem: most agent frameworks execute code via subprocess or exec() directly on the host. One prompt injection and you’re exposed. Our approach: QuickJS runtime compiled to WASM (no syscalls, no network, no filesystem escape) Capability-based tool access—agents can only call functions you explicitly provide Per-tool constraints (e.g., Param(“amount”) <= 1000) Virtual filesystem that resets between executions It’s a Python package wrapping a Rust/WASM binary. Install […]

Ver mais

Liked Liked

DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights

⋅

arXiv:2601.05052v1 Announce Type: cross Abstract: Building efficient and effective generative models for neural network weights has been a research focus of significant interest that faces challenges posed by the high-dimensional weight spaces of modern neural networks and their symmetries. Several prior generative models are limited to generating partial neural network weights, particularly for larger models, such as ResNet and ViT. Those that do generate complete weights struggle with generation speed or require finetuning of the generated models. In […]

Ver mais

Liked Liked

Impact of Separation Distance on the Performance and Annual Energy Production of a Dual-Flap Oscillating Surge Wave Energy Converter

⋅

arXiv:2602.10301v1 Announce Type: new Abstract: Among the different concepts for wave energy conversion, oscillating surge wave energy converters have been shown to have a high capture width ratio. The primary wave capture structure consists of a flap hinged at the seabed or to a floating platform. Different flap configurations, including single and dual-flap, have been investigated. The separation distance between the oscillating surge wave energy converters can have an impact on their response when deployed in arrays. We […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2025