Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2409. 03682v2 Announce Type: replace Abstract: Learning new tasks by leveraging prior experience is a fundamental trait of intelligent systems.
arXiv:2608. 11688v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models are attractive for edge deployment because they provide high model capacity while activating only a small subset of parameters per token, improving compute efficiency.
arXiv:2608. 12026v1 Announce Type: new Abstract: Post-training quantization pipelines routinely leave the softmax output layer in high precision.
arXiv:2608. 11937v1 Announce Type: new Abstract: Foundation models for time-dependent partial differential equations (PDEs) are trained on large and diverse collections of physical systems and can generalize effectively to new downstream tasks.
arXiv:2510. 26690v3 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) has become a popular technique for parameter-efficient fine-tuning of large language models (LLMs).
arXiv:2608. 11283v1 Announce Type: cross Abstract: Computation-ready metal-organic framework (MOF) databases are essential for high-throughput screening, yet many reported crystal structures remain chemically unreasonable or disordered, compromising simulation fidelity.
arXiv:2511. 18191v2 Announce Type: replace Abstract: Time series forecasting drives operational decisions under tight latency budgets, and autoregressive time series foundation models (TSFMs) increasingly deliver the most accurate forecasts.
arXiv:2608. 12140v1 Announce Type: cross Abstract: Boosted decision trees (BDTs) are widely used in latency-critical applications, but efficient hardware deployment remains challenging.
arXiv:2608. 11705v1 Announce Type: new Abstract: Aligned large language models (LLMs) are expected to exhibit safety behavior based on the content of the user request: they should refuse unsafe requests and comply with safe ones.
arXiv:2608. 11271v1 Announce Type: cross Abstract: Next-generation Synthetic Aperture Radar (SAR) missions will generate data far faster than they can downlink, making onboard data reduction essential for near-real-time Earth observation.
arXiv:2507. 14267v2 Announce Type: replace Abstract: Large language model (LLM) agents can execute long-horizon scientific workflows, but their numerical outputs are difficult to trust: agents lose context, game verification checks, and can produce large volumes of plausible yet invalid results.
arXiv:2608. 11231v1 Announce Type: new Abstract: LLM serving is increasingly accelerated by position-independent caching (PIC).
arXiv:2608. 11698v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own trajectories under dense token-level supervision from a teacher.
arXiv:2608. 12032v1 Announce Type: cross Abstract: Video diffusion transformers are costly to sample: every denoising step applies self-attention over a long 3D token sequence, a quadratic cost that dominates as resolution and duration grow.
arXiv:2608. 11492v1 Announce Type: cross Abstract: IoT firmware vulnerability detection remains challenging due to heterogeneous firmware ecosystems, resource-constrained platforms, and limitations in existing benchmarks.
arXiv:2608. 11212v1 Announce Type: new Abstract: Top-k Mixture-of-Experts (MoE) routing is discontinuous, so a deployment-motivated numerical disturbance -- simulated 4-bit KV-cache quantization read by a protected BF16 gate -- pushes tokens across decision boundaries and flips which experts fire.
arXiv:2608. 11249v1 Announce Type: cross Abstract: We study the problem of lossless text compression, motivated by the rapid growth in the collection and storage of digital textual data - including plain text, source code, and structured formats such as XML - and by recent advances in neural language model-based compression.
arXiv:2608. 11604v1 Announce Type: new Abstract: Large language model-based shopping agents are increasingly deployed in real-world e-commerce platforms, generating massive amounts of user interaction logs that provide valuable supervision for improving these agents.
Diffusion Transformers (DiTs) incur quadratic self-attention cost over spatiotemporal tokens. Existing training-free sparse attention methods often construct sparse masks from block-level or cluster-level proxy scores, which can obscure fine-grained differences among keys and miss high contribution keys under aggressive sparsity.
Fashion retrieval often requires satisfying multiple attributes at once, such as category, color, pattern, and demographic. Monolithic embeddings mix these signals into a single vector, making attribute-specific control difficult at retrieval time.