DropthePDF.Watchthepaperthink.
Prism refracts dense research into an interactive experience — animated diagrams, plain-language narration, and figures you can touch. Understand any paper in minutes, not weekends.
13
papers visualized
64
interactive widgets
7
topics
100%
fact-checked explainers
The problem
Every breakthrough starts as 30 pages almost nobody finishes.
Dense notation. Buried results. Figures that assume you already understand them. Great ideas die inside PDFs — not because they're wrong, but because they're unreadable.
Before / after
Same paper. Same 20 minutes.
Drag the slider. One of these you'll actually remember.
28.4
8
O(1)
How it works
Drop · Refract · Explore
Drop
Paste an arXiv link, drop a PDF, or pick from our library. We ingest the text, math, and figures.
Refract
Prism splits the paper into a clear spectrum — summary, key results, method, and glossary.
Explore
Read it as an interactive story, play with the visuals, or jump straight to the part you need.
Living figures
We don't summarize the paper. We turn it on.
Living figures
Static plots come alive — hover any data point for a plain-English explanation of what it means.
Plain-language layer
Toggle between “Researcher” and “Explain like I'm curious.” Jargon glows and reveals its meaning on tap.
Touchable math
Equations expand into interactive sliders, so you can feel how each variable moves the outcome.
Step-through mechanisms
Complex processes unfold one stage at a time — watch attention flow, or a sentence translate itself.
Start here
Featured papers
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Ask a big model to show its work — and it starts to reason
Big language models were surprisingly bad at multi-step problems — grade-school math, logic puzzles — often blurting a wrong final answer. This paper found a shockingly simple fix that requires no training at all: in the few examples you show the model (the “prompt”), don't just show it question-and-answer pairs — show it the *reasoning in between*. Write out the step-by-step thinking that leads to each answer. The model then imitates that pattern on new problems, producing its own “chain of thought” before answering — and accuracy leaps. The headline result: prompting a 540-billion-parameter model with just eight worked examples hit 56.9% on the GSM8K math benchmark — up from 17.9% with ordinary prompting — beating the previous best (a model specially fine-tuned for the task and paired with a separate verifier, at 55%). The twist: this only works in *large* models. In small ones, showing the steps does little or even hurts. Reasoning-by-prompting is an ability that *emerges* with scale — a discovery that reshaped how people use LLMs.
QLoRA: Efficient Finetuning of Quantized LLMs
Fine-tune a 65-billion-parameter model on one gaming GPU
LoRA already made fine-tuning cheaper by training tiny add-on matrices instead of the whole model. But there was still a wall: you had to fit the giant frozen base model in GPU memory just to run it — and a 65-billion-parameter model needs over 780 GB, far beyond any single GPU. QLoRA smashes that wall by squashing the frozen base model down to 4 bits per number (instead of the usual 16), roughly a 4× shrink, so the whole thing fits in under 48 GB — a single high-end GPU. It does this without hurting quality, using three clever tricks: a new 4-bit number format (NF4) tuned to how weights are actually distributed, “double quantization” that even compresses the compression bookkeeping, and “paged optimizers” that spill memory to the CPU during brief spikes instead of crashing. The tiny LoRA add-ons still train in full precision on top. To prove it works, they fine-tuned a chatbot called Guanaco in 24 hours on one GPU — and it reached 99.3% of ChatGPT's score on a popular benchmark. QLoRA is why hobbyists and small labs can now fine-tune enormous models at home.
Retrieval-Augmented Generation for Large Language Models: A Survey
RAG — giving a language model an open book to read from
A language model only knows what it saw during training. So it can confidently make things up (“hallucinate”), it can't know anything recent, and it can't see your private documents. Retrieval-Augmented Generation (RAG) fixes this with a simple, powerful idea: before the model answers, go fetch relevant text from an external library and hand it to the model along with the question — like turning a closed-book exam into an open-book one. The basic recipe has three steps: (1) Indexing — chop your documents into chunks and store them so they're searchable by meaning; (2) Retrieval — when a question comes in, pull the few most relevant chunks; (3) Generation — feed those chunks plus the question to the model so its answer is grounded in real sources. This survey organizes the whole field into three generations of increasingly sophisticated RAG — Naive, Advanced, and Modular — and breaks every system into three parts: what you retrieve, how you use it, and how the model generates. RAG is now one of the most widely used techniques in real-world AI, because it makes answers more accurate, up-to-date, and traceable to a source.
Fresh off the press
Recently added
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
The paper that introduced RAG — a model with two memories
A big language model stores everything it knows inside its own weights — call that its “memory from studying.” That memory is fuzzy: the model can't quote a source, can't easily be corrected, and forgets nothing gracefully. This 2020 paper — the one that actually coined “RAG” — gives a model a *second*, separate memory: a searchable index of all of Wikipedia (about 21 million passages). When you ask a question, a **retriever** finds the most relevant passages, and a **generator** (a seq2seq model, BART) writes the answer using both its own internal knowledge *and* those retrieved passages. The whole thing is trained end-to-end. They test two flavors — one that uses a single retrieved passage for the whole answer (RAG-Sequence), and one that can draw on a different passage for each word (RAG-Token) — and set new records on open-domain question answering, while producing answers that are more specific, more factual, and *traceable to a source*. Best of all, you can update what the model knows just by swapping the index — no retraining.
Introducing the Model Context Protocol (MCP)
One universal way to plug AI into the outside world
A language model on its own is a brain in a box: brilliant at talking, but it can't see your files, query your database, or press any buttons in the real world. To fix that, people used to hand-build a custom connector for every pairing of AI-app-and-tool — a combinatorial mess that never scaled. The Model Context Protocol (MCP), open-sourced by Anthropic in November 2024, replaces all those one-off bridges with a single open standard. The official analogy: MCP is “a USB-C port for AI applications.” Just as USB-C is one socket that any device can plug into, MCP is one standard so any compliant AI app can plug into any compliant tool or data source — build it once, and it works everywhere. Under the hood it's refreshingly simple: small programs called MCP servers expose three things — Tools (actions the AI can do), Resources (data it can read), and Prompts (templates the user can pick) — and AI apps (the hosts) talk to them by trading little JSON-RPC messages. This paper walks a total beginner all the way from “why does this exist?” to writing a working MCP server in Python or TypeScript, watching a real tool call travel end-to-end, and poking a live JSON-RPC console — then hands you an “MCP Certified” badge.
Attention Is All You Need
The Transformer — the architecture behind modern AI
Before this paper, the best translation systems read sentences one word at a time, carrying a running memory forward (recurrent networks). That was slow — you can't process word 5 until word 4 is done — and forgetful over long sentences. The 2017 Transformer threw out that sequential machinery entirely and replaced it with attention: a mechanism that lets every word look directly at every other word and decide which ones matter. Because nothing waits its turn, the model trains fully in parallel on GPUs, captures long-range relationships in a single step, and set new translation records while training in a fraction of the time. This design became the foundation of GPT, BERT, Claude, and essentially all modern AI.
Made for
Whoever you are, the paper meets you where you are
Students
Go from lost to lecture-ready before the seminar.
Researchers
Triage papers for your lit review in an afternoon.
The curious
Read the paper behind the headline — and actually get it.
The next paper you open could actually make sense.
Start with a landmark. No account needed to explore.
Or get the next one in your inbox: