75 citations · 315 across the 34 of their papers we have counts for
37 papers
Theories of Mind as Domain-Specific Languages of Thought
Kartik Chandra, Jonathan Ragan-Kelley, Joshua B. Tenenbaum +1
What kind of thing is a ``theory of mind''? We propose to formalize theories of mind as domain-specialized programming languages, which can be used to reason about the mental state…
Exo-GPU: Safe, Imperative, User-schedulable Programming for Tensor Cores
David Zhao Akeley, Yuka Ikarashi, Jonathan Ragan-Kelley
Modern GPUs require not only SIMT-style parallelism but also software-managed concurrency between compute and data movement to reach maximum performance. Performance engineers must…
Finding Fast Filters
Karima Ma, Andrew Adams, Jonathan Ragan-Kelley
Processing images, video, and audio often requires running large finite impulse response (FIR) filters with strict performance and latency requirements. Prior methods for fast filt…
Meschers: Geometry Processing of Impossible Objects
Ana Dodik, Isabella Yu, Kartik Chandra +4
Impossible objects, geometric constructions that humans can perceive but that cannot exist in real life, have been a topic of intrigue in visual arts, perception, and graphics, yet…
Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians
Kartik Chandra, Max Kleiman-Weiner, Jonathan Ragan-Kelley +1
"AI psychosis" or "delusional spiraling" is an emerging phenomenon where AI chatbot users find themselves dangerously confident in outlandish beliefs after extended chatbot convers…
Modular GPU Programming with Typed Perspectives
Manya Bansal, Daniel Sainati, Joseph W. Cutler +2
To achieve peak performance on modern GPUs, one must balance two frames of mind: issuing instructions to individual threads to control their behavior, while simultaneously tracking…
Bonsai: Compiling Queries to Pruned Tree Traversals
Alexander J Root, Christophe Gyurgyik, Purvi Goel +4
Trees can accelerate queries that search or aggregate values over large collections. They achieve this by storing metadata that enables quick pruning (or inclusion) of subtrees whe…
Locality-Aware Automatic Differentiation on the GPU for Mesh-Based Computations
Ahmed H. Mahmoud, Rahul Goel, Jonathan Ragan-Kelley +1
We present a GPU-based system for automatic differentiation (AD) of functions defined on triangle meshes, designed to exploit the locality and sparsity in mesh-based computation. O…
Empathy in Explanation
Katherine M. Collins, Kartik Chandra, Adrian Weller +2
Why do we give the explanations we do? Recent work has suggested that we should think of explanation as a kind of cooperative social interaction, between a why-question-asker and a…
FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference
Aniruddha Nrusimha, William Brandon, Mayank Mishra +4
The size and compute characteristics of modern large language models have led to an increased interest in developing specialized kernels tailored for particular training and infere…
Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding
Tian Jin, Ellie Y. Cheng, Zack Ankner +6
Decoding with autoregressive large language models (LLMs) traditionally occurs sequentially, generating one token after another. An emerging line of work explored parallel decoding…
Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping
Muru Zhang, Mayank Mishra, Zhongzhu Zhou +7
Large language model inference is both memory-intensive and time-consuming, often requiring distributed algorithms to efficiently scale. Various model parallelism strategies are us…
Exo 2: Growing a Scheduling Language
Yuka Ikarashi, Kevin Qian, Samir Droubi +3
User-schedulable languages (USLs) help programmers productively optimize programs by providing safe means of transforming them. Current USLs are designed to give programmers exactl…
Sketching With Your Voice: "Non-Phonorealistic" Rendering of Sounds via Vocal Imitation
Matthew Caren, Kartik Chandra, Joshua B. Tenenbaum +2
We present a method for automatically producing human-like vocal imitations of sounds: the equivalent of "sketching," but for auditory rather than visual representation. Starting w…
Fast Matrix Multiplications for Lookup Table-Quantized LLMs
Han Guo, William Brandon, Radostin Cholakov +3
The deployment of large language models (LLMs) is often constrained by memory bandwidth, where the primary bottleneck is the cost of transferring model parameters from the GPU's gl…
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
William Brandon, Mayank Mishra, Aniruddha Nrusimha +2
Key-value (KV) caching plays an essential role in accelerating decoding for transformer-based autoregressive large language models (LLMs). However, the amount of memory required to…
WatChat: Explaining perplexing programs by debugging mental models
Kartik Chandra, Katherine M. Collins, Will Crichton +6
Often, a good explanation for a program's unexpected behavior is a bug in the programmer's code. But sometimes, an even better explanation is a bug in the programmer's mental model…
Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding
Zachary Ankner, Rishab Parthasarathy, Aniruddha Nrusimha +3
To combat the memory bandwidth-bound nature of autoregressive LLM inference, previous research has proposed the speculative decoding frame-work. To perform speculative decoding, a…
How to guess a gradient
Utkarsh Singhal, Brian Cheung, Kartik Chandra +4
How much can you say about the gradient of a neural network without computing a loss or knowing the label? This may sound like a strange question: surely the answer is "very little…
Striped Attention: Faster Ring Attention for Causal Transformers
William Brandon, Aniruddha Nrusimha, Kevin Qian +4
To help address the growing demand for ever-longer sequence lengths in transformer models, Liu et al. recently proposed Ring Attention, an exact attention algorithm capable of over…
The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning
Tian Jin, Nolan Clement, Xin Dong +4
How does scaling the number of parameters in large language models (LLMs) affect their core capabilities? We study two natural scaling techniques -- weight pruning and simply train…
Acting as Inverse Inverse Planning
Kartik Chandra, Tzu-Mao Li, Josh Tenenbaum +1
Great storytellers know how to take us on a journey. They direct characters to act -- not necessarily in the most rational way -- but rather in a way that leads to interesting situ…
Inferring the Future by Imagining the Past
Kartik Chandra, Tony Chen, Tzu-Mao Li +2
A single panel of a comic book can say a lot: it can depict not only where the characters currently are, but also their motions, their motivations, their emotions, and what they mi…
Formal Semantics for the Halide Language
Alex Reinking, Gilbert Louis Bernstein, Jonathan Ragan-Kelley
We present the first formalization and metatheory of language soundness for a user-schedulable language, the widely used array processing language Halide. User-schedulable language…