Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606. 04922v1 Announce Type: cross Abstract: Current prompt-based and adapter-based tuning of vision-language models (VLMs) is attractive for medical imaging, where clinical data sensitivity favors frozen backbones and annotations are limited.
arXiv:2606. 04522v1 Announce Type: cross Abstract: Approximate nearest neighbor (ANN) search has become a core primitive in information retrieval and modern machine learning tasks, from classification to retrieval-augmented generation.
arXiv:2606. 04438v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) and looped architectures scale models along two orthogonal axes, namely parameter capacity and effective depth.
arXiv:2606. 04040v1 Announce Type: cross Abstract: Brain-computer interfaces aim to decode naturalistic stimuli from neural signals, yet most progress to date has focused on vision and language.
arXiv:2606. 04419v1 Announce Type: cross Abstract: MRI provides excellent soft-tissue contrast without ionizing radiation, but long acquisition times increase patient discomfort while also raising exam costs and limiting scanner throughput.
arXiv:2606. 04374v1 Announce Type: cross Abstract: Despite rapid progress of continuous embeddings for e-commerce search relevance, a long-standing open problem is the difficulty in capturing fine-grained attribute distinctions.
arXiv:2606. 04063v1 Announce Type: cross Abstract: Deploying large language models (LLMs) is challenging due to their significant memory and computational requirements.
arXiv:2605. 30120v3 Announce Type: replace-cross Abstract: Multi-vector retrieval (MVR) models, exemplified by ColBERT, have established new benchmarks in retrieval accuracy by preserving fine-grained token-level interactions.
arXiv:2606. 05152v1 Announce Type: cross Abstract: Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sample many responses and reward each with a single bit indicating whether the final answer is correct.
arXiv:2606. 04115v1 Announce Type: cross Abstract: Quantizing large language models (LLMs) to low-precision floating-point representations is central to efficient deployment, yet applying a single bit-width uniformly across all layers is sub-optimal in terms of both performance and accuracy.
arXiv:2606. 04513v1 Announce Type: new Abstract: Lane-level maps are critical infrastructure for autonomous driving and lane-level navigation, yet constructing and maintaining standardized lane networks for hundreds of cities remains highly labor-intensive.
arXiv:2606. 04920v1 Announce Type: new Abstract: Quantizing deep neural networks is essential for efficient inference on resource-constrained devices.
arXiv:2606. 04703v1 Announce Type: cross Abstract: Experience internalization converts contextual experience from past interactions into reusable parametric capability, offering a promising path toward continual learning in large language models (LLMs).
arXiv:2605. 29076v2 Announce Type: replace-cross Abstract: LLMs have advanced text classification, yet existing paradigms face a trade-off: supervised (label only) fine-tuning is scalable but offers limited reasoning on complex text and lacks broader model transparency, while discrete prompt optimization offers human-readable instructions but struggles with performance and scalability.
arXiv:2606. 04349v1 Announce Type: cross Abstract: Conventional Post-Training Quantization (PTQ) methods struggle with 4-bit Omni-modal Large Language Models (OLLMs) due to the extreme distribution heterogeneity and disparate outlier patterns across modalities.
arXiv:2511. 21035v2 Announce Type: replace Abstract: Holography offers significant potential for AR/VR applications.
arXiv:2510. 01902v2 Announce Type: replace Abstract: Language Models (LMs) are increasingly used in applications where generated outputs must satisfy strict semantic or syntactic constraints.
arXiv:2606. 04493v1 Announce Type: cross Abstract: Correspondence pruning aims to identify inliers from an initial set of correspondences.
arXiv:2602. 02405v2 Announce Type: replace-cross Abstract: Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or the existence of a stronger model able to solve the problem.
arXiv:2606. 04302v1 Announce Type: cross Abstract: Key-value (KV) caching accelerates inference of large language models (LLMs) by reusing past computations for generated tokens.