Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2607. 13051v1 Announce Type: cross Abstract: TriAttention is a recent method for shrinking the KV cache of long-reasoning LLMs: it scores each cached key by how much attention it is likely to receive and evicts the lowest-scoring ones.
arXiv:2607. 13770v1 Announce Type: cross Abstract: Video diffusion transformers (vDiTs) generate high quality video but introduce extremely high compute cost due to the long diffusion timesteps and self attention computation.
arXiv:2607. 13205v1 Announce Type: cross Abstract: Attention-based KV cache eviction (H2O and its descendants) compresses the memory-constrained state of a long-context model by ranking tokens on accumulated attention mass, treated here as signal energy, and keeping the heaviest.
arXiv:2505. 18231v3 Announce Type: replace-cross Abstract: Large Language Model (LLM) inference is typically memory-intensive, especially when processing large batch sizes and long sequences, due to the large size of key-value (KV) cache.
arXiv:2607. 13203v1 Announce Type: cross Abstract: False alarms remain a major barrier to deploying network intrusion detection systems (NIDS).
arXiv:2607. 13452v1 Announce Type: cross Abstract: Incremental object detection (IOD) aims to extend detectors to new categories while retaining previously acquired knowledge.
arXiv:2607. 13511v1 Announce Type: cross Abstract: We introduce ExTernD (Expanded-rank Ternary Decomposition), a post-training factorization of each LLM weight matrix $A \in \mathbb{R}^{m \times n}$ into $A \approx B \mathrm{diag}(D) C$ with ternary factors $B \in \{-1,0,+1\}^{m \times k}$, $C \in \{-1,0,+1\}^{k \times n}$ and a real scale vector $D \in \mathbb{R}^k$.
arXiv:2607. 13399v1 Announce Type: cross Abstract: On-policy distillation (OPD) has become a key paradigm in LLM post-training, yet its training dynamics remain poorly understood.
arXiv:2502. 07780v4 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved significant success across various NLP tasks.
arXiv:2606. 05981v2 Announce Type: replace-cross Abstract: Aggressive distillation of the diffusion U-Net inverts the per-frame bottleneck of real-time text-to-image pipelines: once the denoiser is a 4-step or 1-step distilled student, the text encoder becomes the critical path.
arXiv:2607. 13891v1 Announce Type: new Abstract: Multi-object detection and tracking from noisy point clouds remain challenging in many data-scarce radar applications.
arXiv:2607. 07050v2 Announce Type: replace-cross Abstract: Agentic language models must learn when to call tools, when to consume tool responses, and when to answer directly.
arXiv:2607. 13099v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable success but raise growing concerns about content provenance and misuse, motivating the need for reliable watermarking techniques.
arXiv:2607. 13119v1 Announce Type: cross Abstract: In standard federated learning systems, the parameter server broadcasts the global model to the participating devices in every iteration.
arXiv:2607. 13093v1 Announce Type: cross Abstract: On-device LLM inference faces a trilemma of response latency, limited hardware resources and user privacy.
arXiv:2607. 13643v1 Announce Type: cross Abstract: Sampling multiple solutions and returning the majority answer is among the most reliable ways to improve the reasoning accuracy of large language models without labels, and a growing family of methods converts this consensus signal into training supervision.
arXiv:2607. 09776v2 Announce Type: replace-cross Abstract: When adapting Vision Language Action (VLA) models to downstream tasks, multiple rounds of post-training are often required to progressively address policy weaknesses.
arXiv:2607. 13080v1 Announce Type: cross Abstract: Autonomous coding agents force engineering organizations to choose between API-based frontier models -- strong reasoning at high token cost -- and on-premise quantized open-weights models, which promise low-marginal-cost scaling and data sovereignty at some loss of reasoning fidelity.
arXiv:2509. 08685v2 Announce Type: replace-cross Abstract: Given encoded 3D point cloud geometry available at the decoder, we study the problem of lossy attribute compression in a multi-resolution B-spline projection framework.
arXiv:2607. 13735v1 Announce Type: new Abstract: The rapid deployment of machine learning systems across cloud, edge, and enterprise environments has brought model optimization to the forefront of systems-engineering.