Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
Machine unlearning aims to remove the influence of specific training data while preserving model utility. Many state-of-the-art approaches pursue this goal by restricting the forgetting update to a subset of parameters selected through gradient-based saliency.
Almost every large language model that reaches a broad audience is quantized: trained in full precision, then compressed for efficiency. This step is assumed harmless and its safety is rarely re-checked.
Efficient multimodal inference is increasingly constrained not only by model quality or FLOP count, but also by the cost of preserving, moving, routing, caching, and quantizing multimodal representations under latency, memory, and energy constraints. This paper reviews recent advances in efficient vision-language and multimodal large language models, covering visual token compression, video token management, KV-cache optimization, Mixture-of-Experts (MoE) routing, low-bit quantization, edge deployment, and hardware-aware benchmarking.
arXiv:2602. 01051v5 Announce Type: replace Abstract: Repertoire-level analysis of T cell receptors offers a biologically grounded signal for disease detection and immune monitoring, yet practical deployment is impeded by label sparsity, cohort heterogeneity, and the computational burden of adapting large encoders to new tasks.
arXiv:2607. 19398v1 Announce Type: new Abstract: Multi-entity compositional questions pose significant challenges to existing retrieval-augmented language models.
arXiv:2602. 18047v4 Announce Type: replace-cross Abstract: City-scale person re-identification across distributed cameras must handle severe appearance changes from viewpoint, occlusion, and domain shift while complying with data protection rules that prevent sharing raw imagery.
arXiv:2602. 15423v4 Announce Type: replace-cross Abstract: As the burgeoning power requirements of sophisticated neural architectures escalate, the information retrieval community has recognized ecological sustainability as a pivotal priority that necessitates a fundamental paradigm shift in model design.
arXiv:2607. 19510v1 Announce Type: new Abstract: Modern LLM deployments use a number of implementation choices and inference optimizations (e.
arXiv:2605. 22069v3 Announce Type: replace-cross Abstract: Novel view synthesis from sparse-view inputs poses a significant challenge in 3D computer vision, particularly for achieving high-quality scene reconstructions with limited viewpoints.
arXiv:2607. 20125v1 Announce Type: cross Abstract: Autoregressive (AR) video diffusion models have become a promising paradigm for long and streaming video synthesis, but the continuously growing Key-Value (KV) cache makes attention the dominant inference cost, especially at high resolution where each frame contributes many tokens.
arXiv:2607. 19592v1 Announce Type: new Abstract: Self-improving AI systems typically treat the agent as the object that improves, by optimizing prompts, workflows, harnesses, or even the agent's own code.
arXiv:2601. 00821v4 Announce Type: replace Abstract: A growing class of conversational-memory systems compresses dialogue history into structured artifacts (extracted facts, decisions, or events) on the premise that distilled structure retrieves better than raw text.
arXiv:2607. 19563v1 Announce Type: cross Abstract: Quantum error correction can be enhanced by post-selecting out runs that are likely to produce a logical failure, but the most accurate measures for that require costly decoder-level information.
arXiv:2607. 20129v1 Announce Type: new Abstract: Quantized small autoregressive reasoning models can enter long, repetitive, or unproductive trajectories, yet inference-time compute is usually allocated without observing how a trajectory develops.
arXiv:2607. 19426v1 Announce Type: cross Abstract: Single-cell datasets are increasingly costly to store, audit, and reuse for model training.
arXiv:2607. 19956v1 Announce Type: cross Abstract: Knowledge distillation (KD) is a standard approach for compressing sequence-to-sequence models, but its per-sample effects are rarely examined.
arXiv:2602. 18109v3 Announce Type: replace Abstract: Real-time schedulers must reason about tight deadlines under strict compute budgets.
arXiv:2607. 19957v1 Announce Type: cross Abstract: Key-Value (KV) cache reduces inference latency in large language models (LLMs).
arXiv:2607. 19353v1 Announce Type: new Abstract: Confidential computing is becoming a practical deployment requirement for AI inference workloads that process sensitive inputs or protect proprietary model assets.
arXiv:2607. 20214v1 Announce Type: cross Abstract: The quadratic $N\times N$ attention score matrix remains a central obstacle to extending Transformers to longer input lengths.