AdaSpark delivers up to 57% FLOP reduction in Video-LLMs for long videos through adaptive cube- and token-level sparsity without apparent loss in performance on hour-scale benchmarks.
Abdi, Dongsheng Li, Jianfeng Gao, Yuqing Yang, and Lili Qiu
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Veda formulates tile selection in video diffusion attention as a reconstruction problem from full attention maps, using statistics-aware and head-aware scoring to enable high sparsity with maintained quality and hardware speedups up to 5.1x end-to-end.
LiveVLM introduces VSB and PaR to compress and retrieve KV cache in streaming video LLMs, enabling LLaVA-OneVision to reach SOTA accuracy among training-free query-agnostic and training-based online models.
Ada-KV is the first head-wise adaptive KV cache budget allocator for LLMs, using a theoretical loss upper bound to allocate eviction differently per attention head and yielding higher quality than uniform methods on long-context benchmarks.
CABLE uses ego-motion compensated prior masks refined by residual cues and corridor envelopes to select ROIs for cloud LMM inference, cutting pixel upload 73-87% with 5-8x prefill speedup and modest quality loss across five driving datasets.
citing papers explorer
-
AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding
AdaSpark delivers up to 57% FLOP reduction in Video-LLMs for long videos through adaptive cube- and token-level sparsity without apparent loss in performance on hour-scale benchmarks.
-
Veda: Scalable Video Diffusion via Distilled Sparse Attention
Veda formulates tile selection in video diffusion attention as a reconstruction problem from full attention maps, using statistics-aware and head-aware scoring to enable high sparsity with maintained quality and hardware speedups up to 5.1x end-to-end.
-
LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval
LiveVLM introduces VSB and PaR to compress and retrieve KV cache in streaming video LLMs, enabling LLaVA-OneVision to reach SOTA accuracy among training-free query-agnostic and training-based online models.
-
Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
Ada-KV is the first head-wise adaptive KV cache budget allocator for LLMs, using a theoretical loss upper bound to allocate eviction differently per attention head and yielding higher quality than uniform methods on long-context benchmarks.
-
CABLE: Cloud-Assisted Bandwidth-efficient LMM-based Encoding for V2X Systems
CABLE uses ego-motion compensated prior masks refined by residual cues and corridor envelopes to select ROIs for cloud LMM inference, cutting pixel upload 73-87% with 5-8x prefill speedup and modest quality loss across five driving datasets.