ZipRerank delivers state-of-the-art multimodal listwise reranking accuracy for long documents at up to 10x lower latency via early interaction and single-pass scoring.
Advances in Neural Information Processing Systems , volume=
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
representative citing papers
Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
TAGO performs sparse jailbreak optimization on audio LMs by retaining only high-gradient-energy tokens, preserving near-full ASR at 25% retention across three models.
PartRep selects high-NLL tokens via a lightweight early-exit gate for partial prompt repetition, retaining most full-repetition gains at 59.4% KV cache and 79% prefill FLOPs on eight benchmarks.
ScaleSearch optimizes block floating point scales via fine-grained search to cut quantization error by 27% for NVFP4, improving PTQ by up to 15 points on MATH500 for Qwen3-8B and attention PPL by 0.77 on Llama 3.1 70B.
SSA uses learned gist tokens to score and selectively unfold relevant context chunks, achieving sparse attention without auxiliary KV caches or architectural changes.
DASH-KV accelerates long-context LLM inference to linear complexity via asymmetric KV cache hashing and mixed-precision retention, matching full attention performance on LongBench.
RetentiveKV uses entropy to drive state-space model transitions that retain and reactivate low-attention visual tokens in a continuous memory instead of pruning them, delivering 5x KV cache compression and 1.5x faster decoding.
MoBA routes attention over blocks via MoE-style gating to enable dynamic, bias-light long-context attention that matches full attention performance at lower cost.
NSA is a hardware-aligned sparse attention mechanism that enables end-to-end trainable long-context modeling by combining coarse token compression with fine-grained selection.
citing papers explorer
-
Search Your Block Floating Point Scales!
ScaleSearch optimizes block floating point scales via fine-grained search to cut quantization error by 27% for NVFP4, improving PTQ by up to 15 points on MATH500 for Qwen3-8B and attention PPL by 0.77 on Llama 3.1 70B.
-
Simplified Sparse Attention via Gist Tokens
SSA uses learned gist tokens to score and selectively unfold relevant context chunks, achieving sparse attention without auxiliary KV caches or architectural changes.
-
RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction
RetentiveKV uses entropy to drive state-space model transitions that retain and reactivate low-attention visual tokens in a continuous memory instead of pruning them, delivering 5x KV cache compression and 1.5x faster decoding.
-
MoBA: Mixture of Block Attention for Long-Context LLMs
MoBA routes attention over blocks via MoE-style gating to enable dynamic, bias-light long-context attention that matches full attention performance at lower cost.