arXiv subjects

Jesse Cai

Publications and source records attributed to Jesse Cai.

5 recordsLinked to original sources

arXiv2026

How Do AI Agents Waste Your Money?

AI agents may consume massive tokens across a wide range of tasks, but how many of those tokens are really necessary? Although prior work has shown that agents can incur unexpectedly high token costs, we still lack a systematic way to identify and measure token waste. In this work, we introduce a unified framework for measuring token waste across heterogeneous agent systems. Our framework records and normalizes complete agent trajectories, identifies removable spans using an LLM-as-a-Judge (LLMaJ), and maps the identified text spans back to the original trajectory for token-level measurement. We validate the identified waste through direct interventions by removing marked spans, resuming agent execution, and measuring changes in task outcomes and subsequent actions. In online pruning experiments, we remove 41-46% of the model's reasoning while largely preserving task performance across two distinct agent benchmarks. Using this framework, we analyze agents across multiple settings. Our analysis shows that token waste has a system-level structure that aggregate token usage alone cannot reveal. First, waste varies more across tasks and agent settings than across models. Second, reasoning and visible execution can exhibit different waste patterns. Third, different harnesses can introduce distinct sources of inefficiency even under the same model and task. Overall, our framework transforms token waste into an actionable optimization signal, enabling researchers and practitioners to train more efficient models, design better reasoning strategies, and optimize agent harnesses toward reducing unnecessary computation rather than merely reducing token usage.

cs.CL↗

arXiv2026

To 2:4 Sparsity and Beyond: Neuron-level Activation Function to Accelerate LLM Pre-Training

Trainings of Large Language Models are generally bottlenecked by matrix multiplications. In the Transformer architecture, a large portion of these operations happens in the Feed Forward Network (FFN), and this portion increases for larger models, up to 50% of the total pretraining floating point operations. We show that we can leverage hardware-accelerated sparsity to accelerate all matrix multiplications in the FFN, with 2:4 sparsity for weights and v:n:m (Venom) sparsity for activations. Our recipe relies on sparse training steps to accelerate a large part of the pretraining, associated with regular dense training steps towards the end. Overall, models trained with this approach exhibit the same performance on our quality benchmarks, and can speed up training end-to-end by 1.4 to 1.7x. This approach is applicable to all NVIDIA GPUs starting with the A100 generation, and is orthogonal to common optimization techniques, such as, quantization, and can also be applied to mixture-of-experts model architectures.

cs.LG↗

arXiv2025

TorchAO: PyTorch-Native Training-to-Serving Model Optimization

We present TorchAO, a PyTorch-native model optimization framework leveraging quantization and sparsity to provide an end-to-end, training-to-serving workflow for AI models. TorchAO supports a variety of popular model optimization techniques, including FP8 quantized training, quantization-aware training (QAT), post-training quantization (PTQ), and 2:4 sparsity, and leverages a novel tensor subclass abstraction to represent a variety of widely-used, backend agnostic low precision data types, including INT4, INT8, FP8, MXFP4, MXFP6, and MXFP8. TorchAO integrates closely with the broader ecosystem at each step of the model optimization pipeline, from pre-training (TorchTitan) to fine-tuning (TorchTune, Axolotl) to serving (HuggingFace, vLLM, SGLang, ExecuTorch), connecting an otherwise fragmented space in a single, unified workflow. TorchAO has enabled recent launches of the quantized Llama 3.2 1B/3B and LlamaGuard3-8B models and is open-source at https://github.com/pytorch/ao/.

cs.LG↗

arXiv2025

Accelerating Transformer Inference and Training with 2:4 Activation Sparsity

In this paper, we demonstrate how to leverage 2:4 sparsity, a popular hardware-accelerated GPU sparsity pattern, to activations to accelerate large language model training and inference. Crucially we exploit the intrinsic sparsity found in Squared-ReLU activations to provide this acceleration with no accuracy loss. Our approach achieves up to 1.3x faster Feed Forward Network (FFNs) in both the forwards and backwards pass. This work highlights the potential for sparsity to play a key role in accelerating large language model training and inference.

cs.LG↗

arXiv2021

Mars Image Content Classification: Three Years of NASA Deployment and Recent Advances

The NASA Planetary Data System hosts millions of images acquired from the planet Mars. To help users quickly find images of interest, we have developed and deployed content-based classification and search capabilities for Mars orbital and surface images. The deployed systems are publicly accessible using the PDS Image Atlas. We describe the process of training, evaluating, calibrating, and deploying updates to two CNN classifiers for images collected by Mars missions. We also report on three years of deployment including usage statistics, lessons learned, and plans for the future.

cs.LG↗