334 citations · 1.4k across the 54 of their papers we have counts for
32 papers · 1 filter
Joules-to-GDP: How Much Economic Value Do AI Systems Produce per Unit of Energy?
Amirreza Zeinali, Jon Saad-Falcon, Avanika Narayan +5
An AI system can produce more economically valuable work while delivering less value for the energy it consumes. We therefore ask: How much economic value does an AI system create…
ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement Learning
Seil Kang, Hangoo Kang, Tarun Suresh +4
Language models are moving beyond generating answers to pursuing long-horizon goals in interactive environments. Post-training these agents requires long, heterogeneous trajectorie…
Block Parallelism For Efficient Distributed Long-Context Diffusion Language Model Training
Tarun Suresh, Pranshu Chaturvedi, Hangoo Kang +4
Block diffusion language models (BDLMs) combine autoregressive dependencies across blocks with parallel denoising within blocks, but long-context training is constrained by distrib…
KernelBench-Verified: Do LLM-Generated Kernels Actually Beat PyTorch?
Yunxiang Zhang, Ping Yu, Jianyu Wang +5
Recent large language models (LLMs) can generate custom CUDA kernels that appear to outperform PyTorch on benchmarks such as KernelBench. Building upon this foundational framework,…
Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling
Caleb Winston, Ron Yifeng Wang, Azalia Mirhoseini +1
Computer-use agents (CUAs) automate tasks specified with natural language such as "order the cheapest item from Taco Bell" by generating sequences of calls to tools such as click,…
OpenJarvis: Personal AI, On Personal Devices
Jon Saad-Falcon, Avanika Narayan, Robby Manihani +10
Personal AI stacks, like OpenClaw and Hermes Agent, are becoming central to daily work, yet they route nearly every query (often over sensitive local data) to cloud-hosted frontier…
Federation of Experts: Communication Efficient Distributed Inference for Large Language Models
Muhammad Shahir Abdurrahman, Chun Deng, Azalia Mirhoseini +1
Mixture of experts has emerged as the primary mechanism for making Large Language Models (LLMs) computationally efficient. However, in distributed settings, communicating token emb…
Exploring Diffusion Transformer Designs via Grafting
Keshigeyan Chandrasegaran, Michael Poli, Daniel Y. Fu +9
Designing model architectures requires decisions such as selecting operators (e.g., attention, convolution) and configurations (e.g., depth, width). However, evaluating the impact…
Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
Narmeen Oozeer, Luke Marks, Shreyans Jain +2
Controlling multiple behavioral attributes in large language models (LLMs) at inference time is a challenging problem due to interference between attributes and the limitations of…
Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models
Caia Costello, Simon Guo, Anna Goldie +1
Large language models (LLMs) have demonstrated strong capabilities in programming and mathematical reasoning tasks, but are constrained by limited high-quality training data. Synth…
Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL
Mohammadreza Pourreza, Shayan Talaei, Ruoxi Sun +5
Text-to-SQL is a challenging task involving multiple reasoning-intensive subtasks, including natural language understanding, database schema comprehension, and precise SQL query fo…
KernelBench: Can LLMs Write Efficient GPU Kernels?
Anne Ouyang, Simon Guo, Simran Arora +4
Efficient GPU kernels are crucial for building performant machine learning architectures, but writing them is a time-consuming challenge that requires significant expertise; theref…
CodeMonkeys: Scaling Test-Time Compute for Software Engineering
Ryan Ehrlich, Bradley Brown, Jordan Juravsky +3
Scaling test-time compute is a promising axis for improving LLM capabilities. However, test-time compute can be scaled in a variety of ways, and effectively combining different app…
Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactions
Taedong Yun, Eric Yang, Mustafa Safdari +13
We present an end-to-end framework for generating synthetic users for evaluating interactive agents designed to encourage positive behavior changes, such as in health and lifestyle…
Archon: An Architecture Search Framework for Inference-Time Techniques
Jon Saad-Falcon, Adrian Gamarra Lafuente, Shlok Natarajan +8
Inference-time techniques, such as repeated sampling or iterative revisions, are emerging as powerful ways to enhance large-language models (LLMs) at test time. However, best pract…
Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
Bradley Brown, Jordan Juravsky, Ryan Ehrlich +4
Scaling the amount of compute used to train language models has dramatically improved their capabilities. However, when it comes to inference, we often limit models to making only…
CHESS: Contextual Harnessing for Efficient SQL Synthesis
Shayan Talaei, Mohammadreza Pourreza, Yu-Chen Chang +2
Translating natural language questions into SQL queries, known as text-to-SQL, is a long-standing research problem. Effective text-to-SQL synthesis can become very challenging due…
CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models
Donghyun Lee, Je-Yong Lee, Genghan Zhang +2
Large Language Models (LLMs) have dramatically advanced AI applications, yet their deployment remains challenging due to their immense inference costs. Recent studies ameliorate th…
Hydragen: High-Throughput LLM Inference with Shared Prefixes
Jordan Juravsky, Bradley Brown, Ryan Ehrlich +3
Transformer-based large language models (LLMs) are now deployed to hundreds of millions of users. LLM inference is commonly performed on batches of sequences that share a prefix, s…
Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification
Neel Guha, Mayee F. Chen, Kush Bhatia +3
Recent work has shown that language models' (LMs) prompt-based learning capabilities make them well suited for automating data labeling in domains where manual annotation is expens…
Representing Long-Range Context for Graph Neural Networks with Global Attention
Zhanghao Wu, Paras Jain, Matthew A. Wright +3
Graph neural networks are powerful architectures for structured datasets. However, current methods struggle to represent long-range dependencies. Scaling the depth or width of GNNs…
A Transferable Approach for Partitioning Machine Learning Models on Multi-Chip-Modules
Xinfeng Xie, Prakash Prabhu, Ulysse Beaugnon +6
Multi-Chip-Modules (MCMs) reduce the design and fabrication cost of machine learning (ML) accelerators while delivering performance and energy efficiency on par with a monolithic l…
Delving into Macro Placement with Reinforcement Learning
Zixuan Jiang, Ebrahim Songhori, Shen Wang +5
In physical design, human designers typically place macros via trial and error, which is a Markov decision process. Reinforcement learning (RL) methods have demonstrated superhuman…
A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators
Dan Zhang, Safeen Huda, Ebrahim Songhori +4
The rapidly-changing deep learning landscape presents a unique opportunity for building inference accelerators optimized for specific datacenter-scale workloads. We propose Full-st…