Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2607. 08786v1 Announce Type: cross Abstract: With the growing deployment of large language models (LLMs), LLM inference cost has become a key challenge.
arXiv:2509. 22557v5 Announce Type: replace Abstract: Mixed bundle pricing is a classic revenue management problem arising in industries such as e-commerce, tourism, and video games.
arXiv:2607. 08930v1 Announce Type: new Abstract: Efficient serving of diffusion large language models (dLLMs) is hindered by convergence heterogeneity: when batching multiple requests, different sequences converge at different rates, causing faster requests to stall behind slower stragglers and introducing compute bubbles and tail latency.
arXiv:2607. 09202v1 Announce Type: cross Abstract: Continual learning commonly relies on post-hoc mechanisms such as replay, elastic regularization, or distillation.
arXiv:2607. 08960v1 Announce Type: cross Abstract: Warehouse operations are governed by Standard Operating Procedures (SOPs) that encode complex, multi-system decision logic, which must be executed reliably under strict time constraints, yet LLM agents lack mechanisms to enforce procedural compliance and degrade under the context overload full SOP specifications introduce.
arXiv:2607. 09287v1 Announce Type: new Abstract: Large language models (LLMs) remain expensive to fine-tune because full-parameter updates require substantial memory, compute, and per-task storage.
arXiv:2607. 09520v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are the perceptual backbone of embodied AI, but their energy footprint on edge hardware remains poorly understood.
arXiv:2607. 09104v1 Announce Type: cross Abstract: While the growing availability of image data has driven significant advances, labeling datasets remains costly and time-consuming.
arXiv:2502. 12446v3 Announce Type: replace-cross Abstract: Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.
arXiv:2405. 16361v4 Announce Type: replace Abstract: To protect privacy in regulated domains such as healthcare and finance, model owners may allow only remote API access while keeping both the training data and model parameters private.
arXiv:2607. 09153v1 Announce Type: new Abstract: Process Reward Models (PRMs) have been proven to be highly effective in guiding test-time scaling (TTS) methods, which significantly boost the capabilities of LLM-based multi-agent systems.
arXiv:2607. 09063v1 Announce Type: new Abstract: Edge devices are increasingly utilized for deploying deep learning applications on embedded systems.
Conventional language-model distillation often relies on fixed teacher-generated data, which may not cover the states encountered by an evolving student policy. On-policy distillation (OPD) instead collects teacher or evaluator supervision on student-generated rollouts.
Precise Event Spotting (PES) requires distinguishing visually similar yet semantically distinct adjacent frames, making it fundamentally different from image classification and coarse action recognition. Although self-distillation methods such as DINO have shown strong representation learning ability in images, we find that directly applying them to PES is ineffective: without supervised guidance, subtle but crucial motion cues are often suppressed as noise, leading to representations that are insensitive to precise event boundaries.
Speculative decoding has significantly accelerated Large Language Model (LLM) inference by alleviating memory-bound bottlenecks. However, traditional speculative decoding typically relies on auxiliary draft modules, incurring significant training and communication overhead.
LLMs don’t fail because they forget—they fail because they remember too much. As conversations grow, prompts accumulate redundant and low-value tokens, driving up cost and latency while silently degrading output quality.
Recommendation systems, from traditional multi-stage to recent unified generative architectures, face challenges in incorporating diverse contextual signals, such as trending topics, breaking news, cultural events, and cross-surface user activities, into their ranking pipelines. These systems are designed to consume structured behavioral signals with consistent schemas, and lack the reasoning capability to naturally process unstructured or heterogeneously formatted contextual information.
arXiv:2607. 08029v1 Announce Type: new Abstract: The emergence of vision language models with fewer than 3 billion parameters has accelerated the implementation of on-device multimodal intelligence.
arXiv:2607. 08605v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept.
arXiv:2607. 08406v1 Announce Type: new Abstract: Backpropagation (BP) dominates deep learning training, but its reliance on gradients brings inherent troubles -- vanishing and exploding gradients.