Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2608. 13616v1 Announce Type: cross Abstract: We consider a heterogeneous mobile-agent network composed of uncontrolled task agents and controllable communication agents.
arXiv:2608. 14112v1 Announce Type: cross Abstract: Scientific simulations often produce scalar volumes faster than they can be stored, transferred, and loaded, while in situ reduction must use only a limited share of simulation resources.
arXiv:2608. 13773v1 Announce Type: cross Abstract: Neural networks are increasingly deployed in high-stakes applications with growing privacy leakage concerns.
arXiv:2608. 14016v1 Announce Type: cross Abstract: Live game commentary is scarce: it exists for professional esports broadcasts and almost nowhere else.
arXiv:2608. 13905v1 Announce Type: cross Abstract: HTTPS website fingerprinting (WF) aims to identify visited websites from metadata observable in encrypted traffic.
arXiv:2608. 13787v1 Announce Type: new Abstract: AI agents increasingly act on their users' behalf, handling tasks such as scheduling meetings, comparing offers, and haggling over prices.
arXiv:2608. 14126v1 Announce Type: cross Abstract: To mitigate attention dilution in high-entropy TLS 1.
arXiv:2608. 13932v1 Announce Type: new Abstract: Iterative Generative Models (IGMs) span autoregressive and diffusion paradigms, and hybrid variants that couple them can achieve remarkable image-generation fidelity.
arXiv:2608. 13756v1 Announce Type: new Abstract: Two GPU kernels implementing the same scaled INT8 GEMM interface are usually treated as interchangeable.
arXiv:2608. 13622v1 Announce Type: new Abstract: Open-ended real-world interaction admits multiple valid behaviors: an agent may answer directly, ask for clarification, provide progress updates, or confirm before acting.
arXiv:2608. 14107v1 Announce Type: new Abstract: Reasoning-intensive retrieval requires text representations to capture not only semantic similarity, but also the reasoning needed to determine relevance under a given retrieval instruction.
arXiv:2608. 13922v1 Announce Type: new Abstract: Detecting distributional changes in high dimension is difficult when neither the pre-change nor post-change density is parametrically specified.
arXiv:2603. 28026v2 Announce Type: replace Abstract: Multimodal multiple-choice question answering (MCQA) provides a standardized and objectively measurable setting for evaluating vision-language models (VLMs).
arXiv:2608. 14022v1 Announce Type: cross Abstract: Action-conditioned video world models require low-latency causal generation and reliable responses to game-native controls.
arXiv:2608. 13961v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative model training across distributed devices without sharing raw data; however, it faces significant communication bottlenecks and channel impairments in practice.
arXiv:2608. 14191v1 Announce Type: new Abstract: The key-value (KV) cache stores information from past tokens and is a major memory bottleneck in long-context inference.
arXiv:2404. 02692v3 Announce Type: replace-cross Abstract: The explosion of data available in life sciences is fueling an increasing demand for expressive models and computational methods.
arXiv:2608. 13966v1 Announce Type: new Abstract: As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model quality.
arXiv:2607. 28336v3 Announce Type: replace Abstract: On-policy distillation provides dense supervision for multimodal reasoners, but its trajectory-level reward cannot determine whether a failed answer arose from perception or subsequent reasoning.
arXiv:2608. 13608v1 Announce Type: new Abstract: Agentic "Continual Learning Harnesses", systems that pair an LLM with retrieval or memory to improve from feedback without retraining, have shown growing value in cybersecurity.