Explore
Everything AION read, in seven sections. Pick one, a topic or a time window.
VideoTeaching Agents to Search with NVIDIA Data Designer — Dhruv Nathawani, NVIDIA
Dhruv Nathawani uses that funnel to explain how NVIDIA builds synthetic data that teaches a model to search, rather than answer from memory.
What's up with google scholar citations ? [D]
These papers have been there for months, but Google Scholar still has not updated its citations, and it has occurred before, but I ignored it and thought it was a one-time error.
OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video
We introduce OneSearch-VL, a unified agent centered on the Visually Grounded Evidence Graph (VGEG), which encodes these dependencies as a shared task-level reference for data construction, process supervision, and operation-level evaluation.
EmbeddingGemma 2: an open, lightweight multimodal embedding model
EmbeddingGemma 2: an open, lightweight multimodal embedding model
Open-source Mac app that runs EmbeddingGemma 2 locally to search your files by what’s in them
DigUp is a free Mac app that runs Google DeepMind’s new EmbeddingGemma 2 locally over your own files.
unsloth/embeddinggemma-2-GGUF
unsloth published the model embeddinggemma-2-GGUF on Hugging Face.
Marformer: A Transformer for Predicting Missing Data Distributions
We present the Marformer, a Transformer trained to directly predict conditional marginals given any set of observed values.
Rethinking access control for RAG with Amazon Quick and Amazon Bedrock
Enterprise organizations are adopting Retrieval Augmented Generation (RAG) to unlock insights from company knowledge sources like Microsoft SharePoint, Google Drive, and Atlassian Confluence.
Radisson Hotel Group brings hotel discovery into ChatGPT
Radisson partnered with Accenture to build a ChatGPT plugin using OpenAI technology, helping travelers find, compare, and book hotels while planning their trips.
Lune
The search engine built for scientific AI agents
VideoVector Isn't Enough: Hybrid Search & Retrieval — Jeff Vestal & James Williams, Elastic
Jeff Vestal and James Williams work backward from that agent behavior to the retrieval layer in Elasticsearch.
I built a browser tool to visualize how a small LLM picks its next word and see what it's attending to [P]
You give it a prompt, it generates one token at a time, and for each step you get the next-token candidates with probabilities, plus the attention from the current token back to the earlier ones drawn as links with the weights labeled.
Sliced Wasserstein embeddings + HNSW for color-scheme search over 48k paintings [P]
The embedding: project the colors (OKLab) onto 8 directions on a Fibonacci hemisphere, sort, and average into 16 quantiles.
Personalization Matters: Long-Horizon Conversation Agent with User-Centric Information in Online Shopping Interactions
We propose a multi-agent, multimodal Retrieval-Augmented Generation (RAG) framework that decomposes dialogue state tracking, recommendation retrieval, preference-aware reasoning, and response generation, while integrating product metadata, product reviews, image-derived descriptions, and user historical reviews.
RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees
Retrieval-augmented generation (RAG) grounds language models in external corpora.
RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation
We introduce RAG-Stress, a controlled diagnostic protocol for examining the limits of evidence reliance in retrieval-augmented generation.
Compile the Table: Query-Calibrated Operator Compression for Tabular In-Context Learning
We propose QCOC (Query-Calibrated Operator Compression), which exploits the exchangeability and repeated use of in-context examples by compiling their full KV cache once into compact memory shared across subsequent queries.
NativeScope: Relation-Localized Retrieval over Native Topology with a Correct Anchor
We propose NativeScope, a scope-then-rank method for queries with a known anchor and relation.
Chaos in the Text: Revealing the Modality Preference in Mixed-Modality Retrievers
Dense retrievers have made significant progress on text and image corpora, but whether these capabilities extend reliably to mixed corpora containing text, image, and fused text-image documents remains unclear.
Softmax Attention on Gaussian Mixtures: Linear When It Can, Selective When It Must
This work studies the infinite-prompt limit of softmax attention on Gaussian mixtures, which retain the tractability of Gaussian data while introducing latent structure, multimodality, and nonlinear dependencies.
Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search
Project Greenhouse represents our exploration of a simple thesis: We believe that it is possible to build fully open and sovereign models for agentic search with only modest computational resources.
EntroPrefill: Renyi-Guided Context Pruning with Conditional Stability Guarantees for Retrieval-Augmented Generation
Mid-prefill pruning can reduce the sequence processed by deeper transformer layers, but attention concentration alone does not certify that discarded context is dispensable.
From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue
Large Language Models (LLMs) serving as long-term dialogue agents require memory systems that support reliable reasoning over extended interactions.
Task-Sufficient Contraction: Source Selection for Machine Information Interfaces
This paper studies when one such reduction preserves the complete downstream problem family, a property termed Task-Sufficient Contraction.
Autoregressive Retriever: Improving Query Understanding from Item Feedback for Universal Multimodal Retrieval
We introduce the AutoRegressive Retriever (ARR), a multimodal retrieval model that learns both to select informative items and to use their content to refine subsequent retrieval.
Beyond Resolution: Object-to-Image Ratio Mismatch in Instance Retrieval
We show that the dominant cause is usually not resolution loss but object-to-image (O2I) ratio mismatch: the object occupies different fractions of the two images.
RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing
In this work, we introduce RECAST (Routing Evidence through Computation, Access, and Synthesized Tools), a learned framework that formulates evidence construction as a sequential decision process over heterogeneous retrieval and computation operations, allowing evidence to be actively derived rather than merely retrieved.
Embedding-Bias in Conditional Independence Testing
To test conditional independence of $X$ and $Y$ given a text or an image $Z$, one conditions on an embedding $ψ(Z)$ in place of $Z$.
Beyond Sequences: Distilling Structured Decision Memory for LLM Recommendation
To bridge this gap, we propose MARI (Memory-Augmented Recommendation with Interpretability), which grounds predictions in explicit, structured decision evidence.
Region-Aware CLS Token Augmentation for Fine-Grained Image Retrieval
Image retrieval methods often rely on a single global semantic descriptor extracted from an image, e.g., the [CLS] token in vision transformers.
From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA
Retrieval-Augmented Generation (RAG) is widely used to ground answers in documents.
Efficient Multi-Granularity Knowledge Transfer for Radiology Report Generation
Radiology report generation can automatically generate clinical descriptions from X-ray images, thereby significantly improving the efficiency of radiologists.
SteerCast: Retrieval-Based Latent Steering for Decoder-Only Time Series Forecasting
We propose SteerCast, a retrieval-based latent steering method that improves decoder-only forecaster at inference time, without updating its parameters.
Multimodal Graph Retrieval-Augmented Sequential Recommendation via Collaborative Filtering Paths
To address these challenges, we propose MGRASRec, a multimodal graph retrieval-augmented framework for sequential recommendation.
Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition
Generative recommenders return a limited candidate set and may omit observed targets before reranking.
KGATE : a Knowledge Graph Embedding Training Environment
Knowledge graph embedding (KGE) models encode the entities and relations of a knowledge graph into a low-dimensional latent space, enabling tasks such as classification or link prediction.
Thinking in Depth: Retrospective Inference for Tabular Foundation Models
We introduce Retro, a tabular foundation model based on retrospective inference, where later stages can explicitly revisit and recombine intermediate information produced earlier in the network.
ExperienceIndex: Artifact-Grounded Memory
We introduce ExperienceIndex, a novel experience layer for AI agents that captures and reuses knowledge about artifacts based on prior reasoning traces.
Quantize by Drift: Label-Free Mixed-Precision Post-Training Quantization for Text Embedders
Mixed-precision post-training quantization needs a per-module sensitivity signal; for a text embedder the obvious one -- the retrieval quality a module costs when quantized -- needs relevance labels that deployments rarely have.
Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora
Retrieval-augmented generation systems increasingly rely on document-structure treatments: structure-aligned chunking, LLM-generated chunk contexts, heading-path metadata, and hierarchical two-stage retrieval.
Lossy Compressive Text Autoencoders
Our work explores learning a compressed latent representation of text, at the intersection of data compression and representation learning.
EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding
In this paper, we propose Event Chain Retrieval-Augmented Generation (EC-RAG), a training-free framework that organizes video content into an explicit event chain before question answering.
RAG-PIBench: A Leakage-Aware Benchmark for Prompt-Injection Detection in Trustworthy RAG Systems
We introduce RAG-PIBench, a benchmark for RAG-style prompt-injection detection containing 4,876 contextual examples across frozen train, validation, and protected-test splits.
Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding Models
Prompted embedding models have recently received increasing attention, particularly for retrieval, where detailed retrieval instructions are provided as part of the retrieval prompt.
Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents
We introduce Agentic AutoRAG, an LLM-agent optimizer for multi-objective RAG hyperparameter optimization with retrieval-versus-generation failure attribution.
Disentangling Paradigm, Identifier, and Decoding in Generative Retrieval
Generative retrieval trains a language model to generate the identifier of a relevant document.
Interval-valued SHAP in Tree-Based Models
In this paper, we propose an imprecise Dirichlet model (IDM) based method to analyze the robustness of Shapley values in decision trees and random forests.
Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents
To address these limitations, we propose QGMem, a novel memory construction and activation framework motivated by human memory, in which experience is organized into events and query-relevant events are modeled by graph as working memory.