Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
Interactive segmentation of 3D Gaussians offers a compelling opportunity for real-time manipulation of 3D scenes, thanks to the real-time rendering capability of 3D Gaussian Splatting (3DGS). However, existing methods require a time-consuming per-scene setup - typically tens of seconds or even minutes - before interactive segmentation can begin on a raw 3DGS scene.
arXiv:2512. 04390v2 Announce Type: replace-cross Abstract: Joint video super-resolution and deblurring (VSRDB) requires both efficient long-range temporal modeling and robustness to frame-wise exposure-duration variation, which changes the extent of motion blur across video frames.
arXiv:2605. 24251v2 Announce Type: replace Abstract: Continual anomaly detection (CAD) addresses the need for industrial inspection systems to adapt to evolving production conditions, yet existing methods share three critical gaps: unrealistic evaluation, no systematic comparison, and no consideration of edge deployment constraints.
arXiv:2605. 09235v2 Announce Type: replace-cross Abstract: One-step generative modeling has emerged as a leading approach for amortizing the inference cost of diffusion and flow-matching models.
arXiv:2510. 10895v2 Announce Type: replace Abstract: Medium Access Control (MAC) protocols, essential for wireless networks, are typically manually configured.
arXiv:2509. 10406v4 Announce Type: replace Abstract: Pretraining transformers on long sequences (entire code repositories, collections of related documents) is bottlenecked by quadratic attention costs.
arXiv:2606. 31259v1 Announce Type: cross Abstract: Diffusion-based text-to-audio (TTA) models achieve impressive synthesis quality but suffer from high inference latency due to iterative multi-step denoising.
arXiv:2606. 31275v1 Announce Type: cross Abstract: Online Continual Self-Supervised Learning (OCSSL) aims to learn representations from a continuous stream of unlabeled data, without knowledge of task boundaries and under memory constraints.
arXiv:2606. 31230v1 Announce Type: new Abstract: We study the task of learning the structure of a $d$-sparse Gaussian graphical model on $n$ variables from a single trajectory of Glauber dynamics.
arXiv:2606. 31609v1 Announce Type: cross Abstract: Radar sensors provide reliable perception under adverse weather and lighting conditions, but their sparse, noisy, and weakly semantic measurements make dense semantic segmentation challenging.
arXiv:2606. 32034v1 Announce Type: cross Abstract: LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions.
arXiv:2606. 30780v1 Announce Type: cross Abstract: Audio deepfakes are a growing challenge for the general public, as well as for journalists and fact-checkers.
arXiv:2606. 30709v1 Announce Type: cross Abstract: Hierarchical Global Attention (HGA) is a drop-in replacement for dense causal attention in pretrained long-context transformers.
arXiv:2512. 21002v3 Announce Type: replace-cross Abstract: Distilling the capabilities from a large reasoning model (LRM) to a smaller student model often involves training on substantial amounts of reasoning data.
arXiv:2606. 31456v1 Announce Type: new Abstract: With an increasing number of Object Detection (OD) models being deployed on edge devices, Zero-Shot Quantization for OD (ZSQ-OD) aims to quantize these models when access to the original training data is prohibited.
arXiv:2508. 13836v2 Announce Type: replace-cross Abstract: Pruning is a core technique for compressing neural networks to improve computational efficiency.
arXiv:2606. 31808v1 Announce Type: new Abstract: Language model systems built around proprietary APIs often operate on a token-based cost model.
arXiv:2606. 31519v1 Announce Type: new Abstract: Long-context Large Language Model inference is severely bottlenecked by the massive Key-Value (KV) cache, yet existing sparse attention methods often suffer from static fixed-budget (Top-k) retrieval or rely on proxy scores that are computationally expensive and biased.
arXiv:2606. 31167v1 Announce Type: cross Abstract: VLA models have emerged as a powerful paradigm for transferring semantic knowledge from web-scale data to physical robotic control.
arXiv:2606. 30923v1 Announce Type: cross Abstract: Imitation Learning is a natural framework for learning in sequential decision-making systems and has emerged as the dominant paradigm through which we understand language model training.