Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2607. 09886v1 Announce Type: new Abstract: Inverse Reinforcement Learning recovers reward functions from expert demonstrations, but standard formulations assume that all demonstrations come from a single expert.
arXiv:2311. 00314v2 Announce Type: replace Abstract: Topic modeling has emerged as a valuable tool for discovering patterns and topics within large collections of documents.
arXiv:2607. 09708v1 Announce Type: new Abstract: Solving large-scale instances of the Traveling Salesman Problem (TSP) exactly is computationally expensive.
arXiv:2607. 09696v1 Announce Type: cross Abstract: Deep neural models for click-through rate prediction often exhibit a sharp decline in validation performance immediately after the first training epoch despite continued improvement in training loss.
arXiv:2510. 11546v3 Announce Type: replace-cross Abstract: High-dimensional regression often suffers from heavy-tailed noise and outliers, which can severely undermine the reliability of least-squares based methods.
arXiv:2112. 06362v5 Announce Type: replace Abstract: We consider the problem of scheduling in multi-class, parallel-server queuing systems with uncertain rewards from job-server assignments.
arXiv:2607. 10582v1 Announce Type: cross Abstract: Large language model (LLM) agents accumulate heterogeneous context, including system instructions, plans, user turns, retrieved documents, tool outputs, and intermediate reasoning, whose key-value (KV) cache can become a major memory bottleneck.
arXiv:2603. 10926v2 Announce Type: replace-cross Abstract: Automotive anomaly detectors are often selected from accuracy only benchmarks on workstation class hardware, whereas in-vehicle monitoring requires predictable scoring latency under limited CPU parallelism.
arXiv:2607. 10618v1 Announce Type: cross Abstract: We consider the recovery of a pair of sparse vectors from a limited number of nonlinear observations of their superposition: $y_i=g(\inner{\ba_i}{\bPhi\bw^\ast+\bPsi\bz^\ast})+e_i$, $i=1,\dots,m$, with $m\ll n$, incoherent orthonormal bases $\bPhi,\bPsi$, a scalar link $g$, and noise $e_i$ that may be heavy-tailed or contaminated.
arXiv:2607. 10803v1 Announce Type: cross Abstract: Understanding which parameters are influential in Large Language Models (LLMs) is central to improving their efficiency, reliability, and interpretability.
arXiv:2607. 10661v1 Announce Type: cross Abstract: Speculative decoding has significantly accelerated Large Language Model (LLM) inference by alleviating memory-bound bottlenecks.
arXiv:2607. 10295v1 Announce Type: cross Abstract: We demonstrate that AI-driven program synthesis can autonomously discover fundamental strategies for decomposing unitary matrices in photonic networks.
arXiv:2607. 10386v1 Announce Type: cross Abstract: Large language models (LLMs) excel at generating long chains of thought, but long reasoning traces are often verbose and memory-inefficient.
arXiv:2607. 11266v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs), yet it often incurs substantial computational costs due to over-reasoning: the generation of redundant, verbose, or irrelevant steps.
arXiv:2607. 11826v1 Announce Type: cross Abstract: Neural Architecture Search (NAS) has automated the design of deep learning models but traditionally requires massive computational resources, often measured in thousands of GPU-days.
arXiv:2607. 11317v1 Announce Type: new Abstract: Low-bit quantization makes small reasoning models inexpensive to deploy but can degrade their chains of thought.
arXiv:2607. 10044v1 Announce Type: new Abstract: Constrained decoding is essential in generative retrieval, where document identifiers generated directly from a query must exactly match a predefined library of valid IDs.
arXiv:2607. 10109v1 Announce Type: cross Abstract: Deploying large-scale transformer models on resource-constrained edge devices remains a challenge due to the high energy and memory overhead inherent in static inference, which processes simple and complex tokens with uniform intensity.
arXiv:2506. 22036v2 Announce Type: replace Abstract: With the increasing multimodal knowledge privatization requirements, multimodal knowledge graphs in different institutes are usually decentralized, lacking of effective collaboration system with both stronger reasoning ability and transmission safety guarantees.
arXiv:2602. 23565v2 Announce Type: replace Abstract: In many economically relevant contexts where machine learning is deployed, multiple platforms obtain data from the same pool of users, each of whom selects the platform that best serves them.