conftrace_

sparse attention

142 papers

Explore in graph

Co-occurring keywords

attention mechanism (4001) efficient computing (781) transformer architecture (1560) large language model (13587) inference acceleration (244) vision transformer (1106) computational efficiency (362) self-attention mechanism (352) model compression (3302) multimodal learning (4645)

Papers

Latent-Condensed Transformer for Efficient Long Context Modeling ACL 2026
S²Flow: Towards Fast and Authentic Training-Free High-Resolution Video Generation AAAI 2026
OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs AAAI 2026
Threshold Differential Attention for Sink-Free, Ultra-Sparse, and Non-Dispersive Language Modeling ACL 2026
Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing ACL 2026
Sparse Attention Across Multiple-Context KV Cache AAAI 2026
Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction AAAI 2026
Learning to LEAP: Efficient Dense Point Tracking by Focusing Where It Matters AAAI 2026
S2O: Early Stopping for Sparse Attention via Online Permutation ACL 2026
MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers ACL 2026
Octopus: Gated Selective Attention for Memory-Bounded Long-Context Inference in Large Language Models ACL 2026
RRAtention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference ACL 2026
Evolving Sparsity: Leveraging Token Importance Dynamics for Efficient LLM Decoding with Sparse Attention ACL 2026
RoBSA: RoPE-based Blockwise Sparse Multi-head Latent Attention ACL 2026
Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers AAAI 2026
Self-Indexing KVCache: Predicting Sparse Attention from Compressed Keys AAAI 2026
Making Every Head Count: Sparse Attention Without the Speed-Performance Trade-off AAAI 2026
Iterative Sparse Attention for Long-sequence Recommendation AAAI 2025
Training-free and Adaptive Sparse Attention for Efficient Long Video Generation ICCV 2025
Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs ACL 2025
MalDetectFormer: Leveraging Sparse SpatioTemporal Information for Effective Malicious Traffic Detection AAAI 2025
Associative Transformer CVPR 2025
AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity EMNLP 2025
Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features ICCV 2025
Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis ICCV 2025