Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2608. 13756v1 Announce Type: new Abstract: Two GPU kernels implementing the same scaled INT8 GEMM interface are usually treated as interchangeable.
arXiv:2608. 13966v1 Announce Type: new Abstract: As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model quality.
arXiv:2604. 09508v2 Announce Type: replace-cross Abstract: Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents.
arXiv:2608. 13622v1 Announce Type: new Abstract: Open-ended real-world interaction admits multiple valid behaviors: an agent may answer directly, ask for clarification, provide progress updates, or confirm before acting.
arXiv:2608. 13565v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale large language models (LLMs) while preserving computational efficiency through sparse activation.
arXiv:2608. 14149v1 Announce Type: new Abstract: Recent training-free post-training quantization methods restore model accuracy through closed-form residual compensation.
arXiv:2608. 13711v1 Announce Type: cross Abstract: Computer-aided detection (CADe) systems for colonoscopy promise to reduce clinical miss rates, yet reliable real-world deployment remains elusive.
arXiv:2608. 14144v1 Announce Type: cross Abstract: Visual on-policy distillation relies heavily on an informative teacher-student asymmetry, through either a larger, stronger teacher or privileged supervision, such as reference answers or ground-truth regions of interest.
arXiv:2608. 13787v1 Announce Type: new Abstract: AI agents increasingly act on their users' behalf, handling tasks such as scheduling meetings, comparing offers, and haggling over prices.
arXiv:2608. 14191v1 Announce Type: new Abstract: The key-value (KV) cache stores information from past tokens and is a major memory bottleneck in long-context inference.
arXiv:2608. 14107v1 Announce Type: new Abstract: Reasoning-intensive retrieval requires text representations to capture not only semantic similarity, but also the reasoning needed to determine relevance under a given retrieval instruction.
arXiv:2603. 28026v2 Announce Type: replace Abstract: Multimodal multiple-choice question answering (MCQA) provides a standardized and objectively measurable setting for evaluating vision-language models (VLMs).
Recent advances in large language models (LLMs) have reshaped semantic analysis. Opinion Extraction (OE) for Science and Technology Intelligence (STI) requires concise core opinions from large information streams.
arXiv:2605. 01928v2 Announce Type: replace Abstract: We optimize losses that jump: spiking thresholds, quantized layers, and discrete routing put jumps in the forward pass, where backpropagation does not apply.
arXiv:2608. 12146v1 Announce Type: cross Abstract: Training Mixture-of-Experts (MoE) models for reinforcement learning (RL) couples two load-balancing problems: sequence composition determines dense attention work in each data-parallel microbatch, while token routing determines sparse expert work on expert-parallel ranks.
arXiv:2608. 13226v1 Announce Type: cross Abstract: While 3D Vision-Language Models (3D VLMs) have demonstrated remarkable spatial reasoning capabilities, they suffer from massive visual token counts that create severe computational bottlenecks during inference.
arXiv:2608. 13057v1 Announce Type: cross Abstract: In expert-parallel (EP) MoE serving, every layer synchronizes at the slowest GPU.
arXiv:2608. 13179v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) offers a verifier-bounded performance ceiling for training multi-turn tool-use agents, yet its trajectory-level credit assignment conflates heterogeneous per-turn outcomes into a single reward signal.
arXiv:2608. 12987v1 Announce Type: cross Abstract: Generative information retrieval (GIR) has emerged as a compelling alternative to the conventional index-retrieve-then-rank retrieval pipeline by training a generator to produce the identifiers of relevant items directly.
arXiv:2608. 13293v1 Announce Type: new Abstract: Edge AI deployment demands neural architectures that are simultaneously accurate, computationally efficient, and hardware-deployable - a challenge addressed by hardware-aware Neural Architecture Search (NAS).