token merging

BiGain: Unified Token Compression for Joint Generation and Classification CVPR 2026 Co-Me: Confidence Guided Token Merging for Visual Geometric Transformers CVPR 2026 CORE: Compact Object-centric REpresentations as a New Paradigm for Token Merging in LVLMs CVPR 2026 D3ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs AAAI 2026 DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation CVPR 2026 Efficient Encoder-Free Fourier-based 3D Large Multimodal Model CVPR 2026 Efficient Vision Transformers via Token Merging with Head-wise Attention Correction WACV 2026 FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding WACV 2026 HTTM: Head-wise Temporal Token Merging for Faster VGGT CVPR 2026 Listening Between the Frames: Bridging Temporal Gaps in Large Audio-Language Models AAAI 2026 LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging CVPR 2026 Merge3D: Efficient 3D Multimodal LLMs via Joint 2D-3D Token Merging CVPR 2026 MergeDNA: Context-Aware Genome Modeling with Dynamic Tokenization Through Token Merging AAAI 2026 MeToM: Metadata-Guided Token Merging for Efficient Video LLMs CVPR 2026 Mobile-Oriented Video Diffusion: Enabling Text-to-Video Generation on Mobile Devices Without Retraining, Compression, or Pruning WACV 2026 QuEPT: Quantized Elastic Precision Transformers with One-Shot Calibration for Multi-Bit Switching AAAI 2026 QuietPrune: Query-Guided Early Token Pruning for Vision-Language Models CVPR 2026 Rethinking Visual Token Reduction in LVLMs Under Cross-Modal Misalignment AAAI 2026 Saliency-Driven Token Merging for Vision Transformers CVPR 2026 SSM-Aware Token-Efficient VMamba via Adaptive Patch Pruning and Merging for Person Re-Identification CVPR 2026 TrajTok: Learning Trajectory Tokens Enhances Video Understanding CVPR 2026 AdaptMerge: Inference Time Adaptive Visual and Language-Guided Token Merging for Efficient Large Multimodal Models EMNLP 2025 AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning ICCV 2025 Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration CVPR 2025 AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark ICLR 2025