Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2607. 24577v1 Announce Type: new Abstract: Reinforcement Learning (RL) agents are increasingly deployed in safety-critical domains such as robotics, autonomous driving, and drone control, where unexpected behaviors may lead to severe real-world consequences.
arXiv:2607. 23503v1 Announce Type: cross Abstract: Internet of Things (IoT) applications generate vast amounts of Correlated Time Series (CTS) data that often contain missing values and require imputation.
arXiv:2607. 22578v1 Announce Type: new Abstract: The proliferation of Large Language Models (LLMs) has shifted serving systems from processing isolated requests to orchestrating high-concurrency, multi-tenant agentic workflows.
arXiv:2607. 22648v1 Announce Type: new Abstract: Inspired by the design of client caching in Content Delivery Networks (CDNs), PTStore distributes and replicates popular tensors that form reusable KV cache prefixes, which are the main technique used by state of art approaches to accelerate inferences.
Multi-turn long-horizon planning is critical for foundation model agents, yet how to fundamentally improve it remains unclear. Existing models are trained on uncontrollable and opaque Internet data, making it difficult to identify how planning ability is acquired, shaped, and integrated.
Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory. We target latency-critical single-user settings where routed experts are staged on demand from CPU memory to a GPU or from Flash to a mobile NPU.
Vision-language models commonly project all tokens produced by a pretrained vision encoder into a large language model. However, final-layer features can discard text, local attributes, and spatial relationships, while high-resolution inputs substantially increase context length and inference latency.
Document-level relation extraction (DocRE) aims to extract relations among multiple entities across extended contexts while maintaining consistency across predicted triples. Although large language models (LLMs) show remarkable reasoning capabilities in information extraction, their predictions are typically generated independently for each candidate triple and may violate fundamental relational constraints such as transitivity, symmetry, and functional uniqueness, leading to contradictory and unreliable outputs.
Infrared small target detection (IRSTD) is important for low-altitude perception, unmanned-system warning, and security monitoring. However, weak targets in infrared imagery usually occupy only a few pixels and are easily submerged by cloud clutter, ground edges, and bright noise, making it difficult for lightweight segmentation-based methods to preserve local target structures while suppressing background interference.
Modern computer vision pipelines remain fragmented, with tasks such as text-to-image generation, editing, restoration, and classical perception handled by separate models. We study Unified Visual Generation (UVG), where a single model produces diverse image-valued outputs through a unified multimodal interface.
Vision-Language-Action (VLA) models have demonstrated strong potential for embodied AI, yet their high inference latency on GPUs limits real-time deployment. Existing accelerators, such as Dadu-Corki, improve efficiency but treat VLA models as full-precision workloads, leaving substantial redundancy in both memory and computation underexploited.
arXiv:2607. 21985v1 Announce Type: cross Abstract: The increasing deployment of large language models (LLMs) has magnified the computational and memory bottlenecks of autoregressive decoding, where low compute intensity and bandwidth-bound kernels dominate inference cost.
arXiv:2607. 21624v1 Announce Type: cross Abstract: Transformer-based models have enabled unprecedented capabilities across language, vision, and multimodal tasks.
arXiv:2607. 22389v1 Announce Type: cross Abstract: With the rapid adoption of long-context large language models (LLMs), the continuously growing KV cache during decoding has become the critical memory bottleneck.
arXiv:2607. 22334v1 Announce Type: new Abstract: Open-weight language models from different families exhibit complementary capabilities, motivating their consolidation into a compact student through on-policy distillation (OPD).
arXiv:2607. 21680v1 Announce Type: new Abstract: Bridge infrastructure deteriorates gradually, yet its root causes---salt intrusion, freezing, fatigue cracking, and others---remain invisible to the naked eye.
arXiv:2607. 22489v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become a widely adopted technique for efficient neural network fine-tuning, decomposing model updates into low-rank matrices.
arXiv:2607. 21817v1 Announce Type: cross Abstract: Longitudinal studies often collect data at sparse, irregular, and unequally spaced time points.
arXiv:2607. 21671v1 Announce Type: new Abstract: Neural network compression and interpretability remain open challenges in modern deep learn- ing, where billion-parameter architectures deliver impressive accuracy at the cost of trans- parency, computational efficiency, and reliable uncertainty quantification.
arXiv:2607. 22045v1 Announce Type: new Abstract: Counterfactual explanations are a prominent approach in explainable artificial intelligence (xAI), providing actionable guidance on what input changes would alter a model's prediction to a desired outcome.