Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2608. 03407v1 Announce Type: cross Abstract: Road network segmentation from satellite imagery remains challenging due to large geographic variation in road appearance, occlusions, and domain shifts introduced by differing resolutions and sensors.
arXiv:2608. 03796v1 Announce Type: cross Abstract: Small language models are often the only option for deployment under tight latency, cost, and on-premises constraints, but they are rarely trained from scratch: a compressed model is usually recovered through knowledge distillation (KD).
arXiv:2608. 03228v1 Announce Type: new Abstract: Existing low rank KV cache methods preserve either model weights or key variance, neither of which directly reflects the attention scores used during inference.
arXiv:2608. 03111v1 Announce Type: new Abstract: Double descent is commonly studied by scaling an explicit capacity parameter, such as neural-network width.
arXiv:2608. 03036v1 Announce Type: cross Abstract: Large Language Models (LLMs) are integrated into software systems and AI services, making efficient LLM serving a concern for software engineering.
arXiv:2605. 30580v2 Announce Type: replace-cross Abstract: Speculative decoding is a popular technique for large language model (LLM) inference, enabling faster generation by drafting multiple tokens with a smaller draft model.
arXiv:2608. 03930v1 Announce Type: cross Abstract: Pre-pretraining language models (LMs) on symbolic data can accelerate and improve natural language acquisition.
arXiv:2608. 02950v1 Announce Type: new Abstract: Checkpoint staffing requires accurate forecasts of when screening demand will occur, yet flight schedules record departure times rather than passenger arrival times at security checkpoints.
arXiv:2608. 03673v1 Announce Type: new Abstract: Many critical reasoning tasks, including clinical diagnosis, legal judgment, and industrial fault diagnosis, require step-dependent causal chains in which early errors propagate and correct conclusions can mask invalid reasoning.
arXiv:2608. 02975v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated impressive performance in MQM-based translation quality (TQ) evaluation, and recent advances in large reasoning models (LRMs) promise even greater improvements.
arXiv:2608. 03565v1 Announce Type: new Abstract: While modern tabular learners excel at capturing statistical patterns, they frequently operate in a semantic vacuum, treating textual features as discrete symbols, ignoring the rich semantics inherent in feature names or cell entries.
arXiv:2608. 03269v1 Announce Type: cross Abstract: Video dataset distillation aims to compress a large video dataset into a compact surrogate set that preserves its training utility.
arXiv:2511. 21095v2 Announce Type: replace Abstract: Early Stage Ranking (ESR) in large-scale recommendation systems is dominated by ''user--item decoupling'' Two Tower architectures, which scale efficiently but cannot capture fine-grained, target-aware user--item interactions directly.
arXiv:2608. 03579v1 Announce Type: cross Abstract: Modern multi-tenant Low-Rank Adapters (LoRAs) serving systems concurrently host tens to hundreds of LoRA adapters.
arXiv:2608. 03403v1 Announce Type: new Abstract: The performance bottleneck of agents is increasingly shifting from model capability to the robustness of their execution processes.
arXiv:2608. 03218v1 Announce Type: cross Abstract: Dataset distillation compresses a large training set into a compact synthetic set while retaining its downstream utility.
arXiv:2511. 13300v1 Announce Type: cross Abstract: Generative models have shown remarkable performance in speech enhancement (SE), achieving superior perceptual quality over traditional discriminative approaches.
arXiv:2608. 02938v1 Announce Type: cross Abstract: Graph attention normalizes neighborhood scores with softmax, the maximum-entropy choice under Shannon statistics.
arXiv:2608. 03041v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) approaches for flexible job shop scheduling (FJSP) heavily rely on attention-centric architectures to achieve state-of-the-art performance.
arXiv:2608. 03127v1 Announce Type: cross Abstract: Hand motion carries the finest-grained information in human activity, yet the representations behind hand generation, understanding, and robot learning are overwhelmingly continuous--joint angles or MANO parameters.