SparseTalk - Sparsifying 3D Gaussian Language Fields for Efficient 3D Visual Question Answering

arXiv:2609.15137 · cs.CV, cs.LG · Submitted 2026-09-14 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-09-14

Updated: 2026-09-14

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Embeddings — 24× in this paper · explained in 2 episodes
• Redundancy — 10× in this paper · explained in 2 episodes
• Gaussian Splatting — 8× in this paper · explained in 4 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Large Language Model — 5× in this paper
• Pruning — 5× in this paper · explained in 4 episodes
• 3D Gaussian Splatting — 4× in this paper · explained in 2 episodes
• alpha — 4× in this paper · explained in 1 episode
• Decode — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Scaled Visually Attributable Performance — 2× in this paper
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Vision-Language Model (VLM) — 1× in this paper · explained in 3 episodes

Sources

• LLaVA-OneVision: Easy Visual Task Transfer
• SeGPruner: Semantic-Geometric Visual Token Pruner for 3D Question Answering
• ChatSplat: 3D Conversational Gaussian Splatting
• An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
• MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models