Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2401. 04890v2 Announce Type: replace-cross Abstract: This work introduces a novel principle for disentanglement we call mechanism sparsity regularization, which applies when the latent factors of interest depend sparsely on observed auxiliary variables and/or past latent factors.
arXiv:2605. 26854v2 Announce Type: replace Abstract: The scalable solution of large sparse linear systems is a bottleneck in scientific computing and graph analysis.
arXiv:2607. 28639v1 Announce Type: cross Abstract: We show that knowledge distillation in small instruction-tuned language models has asymmetric effects on bias.
arXiv:2607. 29235v1 Announce Type: cross Abstract: Although world-action models (WAMs) enhance long-horizon robot control by predicting visual evolution before acting, long-horizon reliability demands repeated re-grounding in real observations--not recursive rollout.
arXiv:2601. 22876v2 Announce Type: replace Abstract: Spiking neural networks (SNNs) promise energy-efficient inference for large language models (LLMs), yet most reported savings rely on compute-operation counts that overlook data movement.
arXiv:2602. 15751v2 Announce Type: replace-cross Abstract: This paper presents an end-to-end demonstration of a viable, ultra-fast, radiation-hard machine learning (ML) application on FPGAs, which could be used in future high-energy physics experiments.
arXiv:2607. 29221v1 Announce Type: cross Abstract: We address the challenge of securely and efficiently outsourcing AI computations from a trusted but computationally weak client to an untrusted but powerful server, in the setting where the client holds both the input and the model, and the server must learn neither.
arXiv:2607. 29071v1 Announce Type: cross Abstract: Federated learning of foundation models faces a fundamental resource-asymmetry challenge: the institutions holding the most valuable domain-specific data cannot host billion-parameter models.
arXiv:2607. 28826v1 Announce Type: new Abstract: Autonomous Cyber Operations (ACO) are increasingly important for defending enterprise networks as cyber threats continue to evolve in sophistication.
arXiv:2607. 28955v1 Announce Type: cross Abstract: AI-generated videos are becoming increasingly realistic and difficult to distinguish from authentic ones, which facilitates malicious misuse and poses growing threats to cybersecurity and social governance.
arXiv:2607. 29078v1 Announce Type: new Abstract: On-policy distillation (OPD) trains student models on their own rollouts to reduce exposure bias.
arXiv:2607. 29158v1 Announce Type: cross Abstract: We introduce implicit machine learning force fields (I-MLFFs), which replace explicit stacks of neural network layers with self-consistent fixed-point equations.
arXiv:2607. 29659v1 Announce Type: new Abstract: Deploying state-of-the-art deep neural networks (DNNs) at the wireless edge is severely bottlenecked by the strict energy and resource constraints of mobile devices.
arXiv:2607. 28986v1 Announce Type: cross Abstract: Zero-shot image captioning (ZIC) describes images without paired image-caption supervision during captioner training, relying on text-only corpora and frozen pretrained image-text scorers.
arXiv:2607. 28699v1 Announce Type: cross Abstract: KV-cache quantization is validated today by offline benchmark averages; a deployed system cannot tell whether compression is damaging the request it is serving right now.
arXiv:2607. 28693v1 Announce Type: cross Abstract: Industrial NILM remains challenging because measurement noise and widespread concurrent machine operation reduce the generalization of models tuned on residential data.
arXiv:2607. 29320v1 Announce Type: new Abstract: Graphical user interface (GUI) agents based on large language models are increasingly deployed across mobile, web, and desktop environments.
arXiv:2607. 29209v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) broadcasts a single response-level reward to every token, while on-policy distillation (OPD) scores each token against a stronger teacher for a dense advantage but caps performance at teacher quality and discourages exploration beyond it.
arXiv:2605. 26168v2 Announce Type: replace-cross Abstract: Any device that runs Linux uses the Linux page cache, a central pillar in OS and application performance, serving to reduce extraneous disk access.
arXiv:2509. 25146v2 Announce Type: replace-cross Abstract: This paper develops a mathematical argument and algorithms for building representations of data from event-based cameras, that we call Fast Feature Field ($\text{F}^3$).