Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2608. 15567v1 Announce Type: new Abstract: Weight-only post-training quantization (PTQ) enables the deployment of large language models under tight memory budgets, but accuracy often collapses at 2-3 bits.
arXiv:2608. 14624v1 Announce Type: new Abstract: Multi-agent LLM systems have emerged as an important deployment paradigm for AI services, where each user request is decomposed into a sequence of specialized agents.
arXiv:2608. 14647v1 Announce Type: cross Abstract: Dirty-history rollouts make multi-turn on-policy self-distillation (OPSD) brittle: once a student emits an erroneous intermediate reply, later turns are conditioned on that reply, and uniform distillation can spend loss on tokens that carry little corrective signal.
arXiv:2608. 15299v1 Announce Type: cross Abstract: Sparsely-activated Mixture-of-Experts (MoE) Transformers universally fix the same number of routed experts across all layers, a convention that ignores the well-documented heterogeneity in layer-wise redundancy.
arXiv:2608. 15602v1 Announce Type: cross Abstract: While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of specialized hardware kernels, thus failing to unleash the full acceleration potential due to persistent reliance on expensive floating-point arithmetic or runtime dequantization overheads.
arXiv:2608. 14906v1 Announce Type: cross Abstract: Watermarking provides a principled way to authenticate text generated by large language models (LLMs).
arXiv:2608. 16797v1 Announce Type: cross Abstract: Industrial recommenders rely on two model families that have evolved largely independently: feature-interaction models over multi-field user/item features, and sequential models over user-behavior histories.
arXiv:2608. 15369v1 Announce Type: cross Abstract: Lossy audio compression algorithms traditionally rely on psychoacoustic modeling and frequency-domain representations (e.
arXiv:2605. 21333v2 Announce Type: replace-cross Abstract: Natively trained spiking language models must preserve information across time while operating through sparse binary activations, a combination that has produced a persistent quality gap relative to dense Transformers.
arXiv:2608. 15407v1 Announce Type: cross Abstract: An invariant behavioral profile is the defining vulnerability of traditional honeypot installations: a skilled adversary can confirm the presence of a deception environment within only a few diagnostic commands, limiting its intelligence value.
arXiv:2608. 14644v1 Announce Type: new Abstract: Real-world LLM deployments increasingly rely on runtime-injected prohibitions--enterprise policies, PII redlines, tool boundaries--that vary per request and per tenant.
arXiv:2608. 14945v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) gives language agents dense token-level supervision from a privileged self-teacher on the policy's own trajectories.
arXiv:2608. 15584v1 Announce Type: cross Abstract: Production paged-serving engines apply uniform paging granularity to the KV cache, even though the two regions of a multi-agent workload have opposite storage requirements: a long shared prefix demands contiguity, while the per-request suffix demands fine-grained allocation.
arXiv:2608. 15776v1 Announce Type: cross Abstract: Despite the powerful multi-scale modeling methods and high-throughput infrastructures established in the materials community, real material computation workflows remain fragmented and heavily manual, requiring researchers to constantly bridge software tools, data analysis, and intermediate decisions.
arXiv:2608. 16373v1 Announce Type: cross Abstract: Despite comprising over 70\% of its surface, the world's oceans are critically underobserved compared to the land surface or the atmosphere.
arXiv:2608. 15117v1 Announce Type: new Abstract: Analytical models of peak VRAM consumption for LLM inference decompose memory into weight-storage, KV-cache, and activation terms parameterized by step count, tool invocations, and context expansion.
arXiv:2608. 14774v1 Announce Type: new Abstract: Modern sequence models heavily rely on massive memory footprints and large-batch stochastic optimization, barriers that restrict sample efficiency and continual learning.
arXiv:2608. 15062v1 Announce Type: cross Abstract: Scaling transformer language models creates an inherent tension between expressivity and memory efficiency.
arXiv:2608. 16010v1 Announce Type: new Abstract: Model compression is critical for deploying networks on resource-constrained edge devices.
arXiv:2603. 21933v2 Announce Type: replace-cross Abstract: The pruning of 3D Gaussian splats is essential for reducing their complexity to enable efficient storage, transmission, and downstream processing.