Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
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. 16612v1 Announce Type: cross Abstract: An accurate estimation of the state of health (SOH) underpins a safe and optimized use of the battery system.
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. 15369v1 Announce Type: cross Abstract: Lossy audio compression algorithms traditionally rely on psychoacoustic modeling and frequency-domain representations (e.
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. 16316v1 Announce Type: cross Abstract: Large Multimodal Models (LMMs) for video reasoning have long been hindered by the high computational cost of processing vast amounts of visual information.
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. 15592v1 Announce Type: new Abstract: Efficient LLM serving is often bottlenecked by the need to pad sequences to a fixed maximum length, and this wastes compute and degrades throughput.
arXiv:2608. 14712v1 Announce Type: cross Abstract: Each row of a transformer's attention matrix is a probability distribution over tokens, and in trained models most of that probability lands on a single \emph{sink} token, usually the first.
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. 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. 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. 15919v1 Announce Type: cross Abstract: Retrieval-Augmented Generation over knowledge graphs (Graph-RAG) has emerged as a powerful paradigm for grounding large language models in domain-specific corpora.
arXiv:2608. 16309v1 Announce Type: cross Abstract: Static pruning is widely used to accelerate sparse neural retrieval, yet existing studies each validate their conclusions within a single custom pipeline, leaving it unclear which findings transfer to modern engines with different index organizations and dynamic pruning mechanisms.
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. 14828v1 Announce Type: new Abstract: Aligning a language agent to several objectives at once is a persistent failure mode of preference-based training: when objectives are combined additively, optimization collapses onto whichever is cheapest to improve and sacrifices the rest, so a support agent learns to sound warm while giving no real help.
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. 15145v1 Announce Type: new Abstract: Large Language Models (LLMs) have been increasingly adopted in Text-to-SQL systems, yet SQL errors remain a major obstacle in real-world Text-to-SQL inference pipelines.
arXiv:2608. 14648v1 Announce Type: cross Abstract: In this study, we revisit three widely used techniques in vector search and utilize them to optimize vector embedding indexing through clustering: dimensionality reduction, quantization, and dimension pruning.
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.