Research, explained
The papers behind modern multimodal search — retrieval, vector indexing, embeddings, segmentation, and personalization — each explained in about a minute, with what it actually means for Mixpeek.
79sGoogle's MUVERA: The One-Vector Trick Behind Fast Multi-Vector Search
MUVERA collapses a multi-vector (ColBERT-style) representation into a single Fixed Dimensional Encoding whose dot product provably approximates the multi-vector score — so late-interaction quality can ride an ordinary single-vector ANN index.
81sMeta's SAM 3: Type a Phrase, Segment Every Instance
SAM 3 introduces promptable concept segmentation: a short noun phrase or exemplar image makes one model detect, segment, and track every instance of that concept across images and video.
80sBaidu's Unlimited-OCR: The Model Whose Memory Never Grows
Baidu's Unlimited-OCR replaces decoder attention with Reference Sliding Window Attention, turning the KV cache into a fixed-size queue so 40+ page PDFs parse in one forward pass instead of being chopped at page breaks.
65sMamba Explained: The LLM Architecture With No Attention (5x Faster, Million-Token Context)
Mamba replaces attention with a selective state space model — one fixed-size state updated per token with a learned keep-or-forget decision — reporting linear scaling and 5x Transformer inference throughput with quality holding to million-token sequences.
76sLoRA Fine-Tuning Explained on a Real Model: Train 1% of Qwen2.5-1.5B
LoRA freezes the base model and trains a small low-rank adapter beside each weight matrix — roughly 1% of the parameters — merged in afterward with zero added inference latency.
77sLate Interaction: How ColBERT and ColPali Search Documents as Images
Late interaction keeps one embedding per token (ColBERT) or per image patch (ColPali) and scores query–document pairs with MaxSim, recovering fine-grained matching that single-vector embeddings flatten away — ColPali retrieves documents as images, no OCR.
61sCluster with Auctions: The FAISS Team Teaches Vector Indexes to Learn From Queries
Most IVF vector indexes assign queries with the same function that partitioned the data. Cluster with Auctions jointly learns a balanced partition and a neural probing function, reassigning vectors by a large-scale auction while the probe learns the live query distribution.
106sLearned Indexes Explained: When a Model Replaces the B-Tree
The classic case for learned index structures: a model that has learned the data distribution can predict where a key lives, replacing B-trees and hash maps with smaller, faster learned models — the idea that seeded a decade of learned-index research.
74sHow Meta Cut Its Ads Model Serving Cost From 24.6x to 3.9x (HILL, Explained)
Meta's teardown of MoNN (the retrieval model behind Facebook/Instagram ads) plus HILL, the hierarchical index that made it affordable: organizing every item into a learned tree keeps +6.0% recall at 3.9x cost instead of 24.6x.
87sMeta SiRA: The Retrieval System That Beats Dense Embeddings With Zero Training
SIRA is a learned sparse retrieval approach: instead of a dense embedding, documents and queries expand into weighted term sets, keeping the exact-match precision and inverted-index efficiency of lexical search while learning which terms matter.
63sHow Apple TV Ranks Search Results From Two Keystrokes (RecSys 2026)
Apple's search-as-you-type system gives every title two embeddings — a text encoder fine-tuned on co-engagement and an ID embedding learned from co-watching — and fuses per-keystroke similarities with boosted trees for +2.99% NDCG@10.
56sEvoGraph-R1: The Knowledge Graph That Edits Itself (CVPR 2026)
EvoGraph-R1 treats a knowledge graph as a workspace agents edit — retrieve, reason, then write back new nodes, corrected edges, and multimodal hyperedges — so every query leaves the graph slightly smarter.
63sComposed Image Retrieval With No Vision Model: 44% R@1 Zero-Shot
Composed image retrieval ('this jacket, but in red, with a hood') done with images represented purely as text: a caption plus an attribute checklist at ingest, an LLM to merge the modification, plain text retrieval, then an LLM reranker — 44.04% R@1 on CIRR zero-shot.
68sWhy Fine-Tuning Quietly Breaks Your Embedding Index (and AlphaWiSE's Fix)
Fine-tune a CLIP-style model and the cross-modal alignment that made old queries work shifts underneath your index — recall erodes with no warning. AlphaWiSE interpolates two frozen checkpoints with one learned coefficient per tensor to keep both, at zero added inference cost.
87sBrain2Qwerty: What Meta's Brain-to-Text Decoder Actually Does
Brain2qwerty decodes text from non-invasive brain recordings as a person types — a research milestone in reading language from neural signals without implanted electrodes.
79sTen Minutes of AI Help Made People Worse: The Persistence Study
A controlled study found people who leaned on an AI assistant for ten minutes performed worse on their own afterward and gave up on hard problems faster — a caution about assistance that replaces understanding rather than supporting it.