Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606. 15652v1 Announce Type: new Abstract: 4-bit quantization significantly reduces the memory footprint and accelerates the inference of large language models (LLMs).
arXiv:2606. 15621v1 Announce Type: new Abstract: Per-token counterfactual credit estimation asks which token in a language-model rollout caused the final answer to be right or wrong: cut the transcript at a pivot, substitute an alternative token, replay continuations, and compare outcomes.
arXiv:2605. 21312v2 Announce Type: replace-cross Abstract: Modern LLM serving is no longer homogeneous or monolithic.
arXiv:2605. 27599v2 Announce Type: replace-cross Abstract: Agentic AI workloads - where a single user goal triggers multi-step orchestration, tool calls, retries, and failure recovery - are being targeted for edge deployment, with NVIDIA, Dell, HP, ASUS, MSI, Acer, and Gigabyte all shipping GB10-based desktop AI systems in 2026.
arXiv:2604. 27128v2 Announce Type: replace-cross Abstract: Foundation-model pipelines for individual-level livestock monitoring -- combining open-vocabulary detection, promptable video segmentation, and self-supervised visual embeddings -- have raised the accuracy ceiling of precision livestock farming (PLF), but their GPU memory budgets exceed the envelope of commodity edge accelerators.
arXiv:2604. 13085v2 Announce Type: replace-cross Abstract: Autonomous AI agents operating in dynamic environments face a persistent challenge: acquiring new capabilities without erasing prior knowledge.
arXiv:2603. 03417v2 Announce Type: replace-cross Abstract: Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance.
arXiv:2512. 22560v2 Announce Type: replace-cross Abstract: Agentic Reinforcement Learning (RL) trains LLMs through multi-turn interactions with environments, producing workloads that mix compute-bound prefill, bandwidth-bound decoding, CPU-heavy environment execution, and bursty reward evaluation.
arXiv:2511. 16681v3 Announce Type: replace-cross Abstract: Vector databases (VecDBs) are increasingly deployed in retrieval-augmented generation (RAG) pipelines where query processing and document ingestion occur concurrently.
arXiv:2510. 07651v3 Announce Type: replace-cross Abstract: Large language models (LLMs) with extended context windows enable powerful applications but impose significant memory overhead, as caching all key-value (KV) states scales linearly with sequence length and batch size.
arXiv:2508. 00956v3 Announce Type: replace-cross Abstract: User representation learning serves as a fundamental pillar for personalized services on large-scale web platforms.
arXiv:2506. 16738v2 Announce Type: replace-cross Abstract: With the rapid progress of speech language models (SLMs), discrete speech tokens have emerged as a core interface between speech and text, enabling unified modeling across modalities.
arXiv:2605. 29796v3 Announce Type: replace Abstract: Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search.
arXiv:2606. 16996v1 Announce Type: cross Abstract: Segment Anything Model 3 (SAM 3) provides a strong frozen backbone for concept-prompted segmentation, but applying it directly to open-vocabulary semantic segmentation (OVSS) is inefficient: full-resolution decoding is typically run over the entire dataset vocabulary, whereas each image contains only a small active subset of classes.
arXiv:2606. 16316v1 Announce Type: cross Abstract: Retrieving external knowledge is essential for solving real-world tasks, yet it remains challenging when the relationship between a query and its relevant knowledge involves implicit and complex reasoning beyond surface-level semantic or lexical matching (e.
arXiv:2606. 16799v1 Announce Type: cross Abstract: Existing vision-language model (VLM)-based AI-generated image quality assessment (AIGIQA) methods suffer from a fundamental semantic-distortion dimensional conflict: monolithic representations optimized for semantic discrimination inherently entangle compositional understanding with low-level perceptual sensitivity, rendering them blind to fine-grained quality degradations.
arXiv:2606. 06510v2 Announce Type: replace-cross Abstract: Conventional HPC holds that native hardware FP64 is the irreducible foundation of scientific computing.
arXiv:2606. 16093v1 Announce Type: cross Abstract: Modeling long-range dependencies remains a central challenge in natural language processing.
arXiv:2606. 15980v1 Announce Type: cross Abstract: Activation monitors-lightweight probes trained on a language model's internal representations-are an increasingly common layer in deployment safety stacks.
arXiv:2606. 15912v1 Announce Type: cross Abstract: Multi-turn agents that plan, invoke tools, and interact with environments offer a promising paradigm for solving complex tasks, yet their capabilities typically rely on very large models whose inference cost is prohibitive in practice.