Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2607. 23693v1 Announce Type: new Abstract: Long-horizon agents increasingly reuse their KV cache as memory: a serving system keeps a subset of cached entries and drops the rest.
arXiv:2506. 05678v3 Announce Type: replace Abstract: The evolution of sequence modeling architectures, from recurrent neural networks and convolutional models to Transformers and structured state-space models, reflects ongoing efforts to address the diverse temporal dependencies inherent in sequential data.
arXiv:2602. 15491v2 Announce Type: replace-cross Abstract: Neural audio codecs (NACs) typically encode the short-term energy (gain) and normalized structure (shape) of speech/audio signals jointly within the same latent space.
arXiv:2607. 22785v1 Announce Type: cross Abstract: Apple-Silicon SoCs share CPU, GPU, and Neural Engine over one unified memory system, raising the question of whether transformer inference can be accelerated by splitting single operators across units.
arXiv:2607. 22633v1 Announce Type: new Abstract: Table Question Answering (TableQA) aims to reason over tables to answer user queries.
arXiv:2607. 22614v1 Announce Type: new Abstract: RL-based LLM post-training increasingly disaggregates Rollout and Training across separate GPU resources, but static GPU partitioning suffers from severe pipeline bubbles under long-tail rollout latency.
arXiv:2607. 24280v1 Announce Type: new Abstract: Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval, yet optimizing this with outcome-based reinforcement learning (RL) provides only sparse supervision.
arXiv:2607. 23503v1 Announce Type: cross Abstract: Internet of Things (IoT) applications generate vast amounts of Correlated Time Series (CTS) data that often contain missing values and require imputation.
arXiv:2607. 24260v1 Announce Type: new Abstract: Modern LLM systems increasingly rely on knowledge-selection processes that produce high-value structured priors, such as ranked evidence, graph topology, multimodal alignment, and confidence signals.
arXiv:2607. 23389v1 Announce Type: cross Abstract: Conventional CAPTCHAs pose puzzles that modern AI systems increasingly solve, while behavioral and cryptographic-attestation defenses carry privacy or enrollment costs.
arXiv:2607. 24562v1 Announce Type: new Abstract: Large language models serve heterogeneous populations structured by domain, topic difficulty, and linguistic style.
arXiv:2511. 05582v3 Announce Type: replace Abstract: Real-Time Auction (RTA) interception decides which incoming advertising requests reach downstream systems, and therefore controls the quality of the data those systems learn from.
arXiv:2607. 23293v1 Announce Type: cross Abstract: Image-source-method (ISM)-based room impulse response (RIR) simulation is a useful and physically interpretable tool for acoustic scene modeling, but full-order ISM becomes computationally expensive as the reflection order and room complexity increase.
arXiv:2607. 23044v1 Announce Type: cross Abstract: Quantum devices are open systems whose dynamics interleave coherent evolution with dissipation, and benchmarking, error mitigation, and error correction all rest on a faithful model of both.
arXiv:2607. 24440v1 Announce Type: cross Abstract: Vision-language models (VLMs) deployed on consumer hardware must decide when to answer and when to defer, and that decision depends on having a confidence signal that tracks correctness.
arXiv:2607. 22634v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs, generating tokens in parallel.
arXiv:2607. 24588v1 Announce Type: new Abstract: Early warning of extreme weather is essential for mitigating the societal, economic, and environmental risks posed by hazardous weather events.
arXiv:2607. 23237v1 Announce Type: cross Abstract: Effective flood risk management relies on accurate forecasting, yet the "black box" nature of stateof-the-art Deep Learning models creates a barrier to trust and accountability in high-stakes public safety decisions.
arXiv:2607. 24062v1 Announce Type: cross Abstract: Reinforcement Learning (RL) training for Large Language Models (LLMs) often suffers from instability due to the discrepancy between training and inference.
arXiv:2607. 23263v1 Announce Type: new Abstract: Deciding whether a trajectory actually fulfills its instruction governs how we measure computer-use agents on long-horizon graphical-user-interface tasks and how we train them with reinforcement learning.