Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
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. 12842v1 Announce Type: new Abstract: Model merging has recently attracted significant attention as a promising paradigm for constructing unified multi-task models without requiring additional retraining.
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. 12695v1 Announce Type: new Abstract: Self-supervised electrocardiogram (ECG) models are often trained on a few seconds of ECG signal and, increasingly, on discretized token sequences.
arXiv:2608. 13061v1 Announce Type: new Abstract: As the feature representation changes, replay must preserve the earlier classes.
arXiv:2505. 12532v3 Announce Type: replace-cross Abstract: Efficiently adapting large pretrained models is critical under tight compute and memory budgets.
arXiv:2608. 12331v1 Announce Type: cross Abstract: Reasoning language models generate lengthy chain-of-thought (CoT) sequences whose key-value (KV) cache grows linearly and becomes a memory bottleneck during decoding.
arXiv:2608. 13057v1 Announce Type: cross Abstract: In expert-parallel (EP) MoE serving, every layer synchronizes at the slowest GPU.
arXiv:2607. 27539v2 Announce Type: replace Abstract: Exact deletion from persistent language-model memory depends on whether a record's effect remains addressable after later computation.
arXiv:2608. 12655v1 Announce Type: new Abstract: A flat training curve does not reveal whether a neural network has reached a global optimum, is locally trapped, is representation-limited, or is mismatched to its trainer.
arXiv:2608. 12929v1 Announce Type: new Abstract: The study presents a systematic machine learning (ML) study of 6G-IoT beamforming optimization (6GBO) using supervised and unsupervised approaches.
arXiv:2608. 12854v1 Announce Type: cross Abstract: Autonomous driving requires planning under both semantic constraints and predictive dynamics.
arXiv:2506. 13452v3 Announce Type: replace-cross Abstract: Background and Objective: As Deep Brain Stimulation (DBS) advances toward directional leads and optimization-based current steering, selecting electrode contact configurations becomes complex.
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. 12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment.
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. 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).
arXiv:2608. 13144v1 Announce Type: cross Abstract: As edge-side vision services continue to expand toward low-latency, high-throughput scenarios, reducing the inference cost of vision models without sacrificing reliability has become a central concern.
arXiv:2608. 12574v1 Announce Type: new Abstract: Large language models increasingly need to generate structured outputs that conform to predefined schemas, with one common constraint being selection from a finite set of valid strings.
arXiv:2608. 13524v1 Announce Type: new Abstract: Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel.