SATOR is a source‑free, backpropagation‑free framework for test‑time adaptation of 3D point cloud models. It eliminates the need for predefined purge‑size candidates by computing token abnormality scores from attention and geometric graphs, then using an Otsu‑based threshold to partition tokens into retained and pruned sets. A keep‑ratio‑calibrated routing step selects the pruned prediction only when its entropy, adjusted by the keep ratio, is lower than that of the original prediction, achieving state‑of‑the‑art accuracy on three 3D corruption benchmarks.
arXiv:2603.14254v2 Announce Type: replace Abstract: Test-time adaptation (TTA) aims to improve model robustness under distribution shifts by adapting to unlabeled test data, but most existing methods...
arXiv:2609.10346v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) process hundreds or thousands of visual tokens per image, incurring prohibitive inference costs. While existin...
arXiv:2607. 08991v1 Announce Type: new Abstract: Efficient inference in Large Language Models (LLMs) requires deciding where computation can be reduced while preserving model quality.
arXiv:2607. 28418v1 Announce Type: cross Abstract: Pruning is a promising approach for improving the efficiency of LLMs.
Gigapixel Whole-Slide Images (WSIs) present a fundamental computational bottleneck for vision-language models (VLMs) due to extreme sequence lengths. Existing approaches predominantly rely on spatial sampling or training-free pruning, which risk diluting weak but informative signals, leading to the loss of critical diagnostic evidence due to the spatially diffuse nature of pathological cues.
Position Anchor Tuning (PAT) is a parameter‑efficient fine‑tuning method for pre‑trained point cloud transformers that improves inference efficiency. PAT reduces the computational cost of multi‑head attention and feed‑forward networks by using token aggregation‑expansion pairs: a token aggregation module (TAM) selects representative tokens based on 3D position anchors, and a token expansion module (TEM) propagates the learned representations back to the full token set. Combined with base‑sharing low‑rank adaptation (BSLoRA) for the TAMs, PAT achieves performance comparable to state‑of‑the‑art methods while requiring fewer trainable parameters and lower computational overhead.
arXiv:2603. 20895v3 Announce Type: replace-cross Abstract: Existing routers rely on semantic query features or handcrafted features, which often fail to capture model-specific failures or intrinsic task difficulty.
arXiv:2608. 13226v1 Announce Type: cross Abstract: While 3D Vision-Language Models (3D VLMs) have demonstrated remarkable spatial reasoning capabilities, they suffer from massive visual token counts that create severe computational bottlenecks during inference.
arXiv:2605. 25143v2 Announce Type: replace Abstract: Test-time scaling improves language model reasoning by spending additional compute to explore multiple solution trajectories.
arXiv:2608. 01074v1 Announce Type: new Abstract: Tabular data is used extensively in many real-world use cases.
While 3D Vision-Language Models (3D VLMs) have demonstrated remarkable spatial reasoning capabilities, they suffer from massive visual token counts that create severe computational bottlenecks during inference. Existing token pruning methods primarily rely on diversity-based selection, discarding similar tokens to maximize dispersion.
arXiv:2606. 30011v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) deployed in real-world systems typically have fixed weights, often leading to degraded performance under distribution shifts.