Invisible Unicode perturbations, optimized from surrogate compressors then adapted by prior-guided evolution under a low query budget, cause large information loss in agent context compression without changing human-visible text.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
A learned weighted sum of intermediate-layer activations compresses an instruction prompt into a single patch vector that, injected at an early layer, recovers task accuracy within ~2% of the full prompt.
SSA uses learned gist tokens to score and selectively unfold relevant context chunks, achieving sparse attention without auxiliary KV caches or architectural changes.
Absorber LLM introduces causal synchronization to absorb context into parameters for memory-efficient long-context LLM inference while preserving causal effects.
citing papers explorer
-
Out of Sight: Compression-Aware Content Protection against Agentic Crawlers
Invisible Unicode perturbations, optimized from surrogate compressors then adapted by prior-guided evolution under a low query budget, cause large information loss in agent context compression without changing human-visible text.
-
Prompt Compression via Activation Aggregation
A learned weighted sum of intermediate-layer activations compresses an instruction prompt into a single patch vector that, injected at an early layer, recovers task accuracy within ~2% of the full prompt.
-
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.
-
Absorber LLM: Harnessing Causal Synchronization for Test-Time Training
Absorber LLM introduces causal synchronization to absorb context into parameters for memory-efficient long-context LLM inference while preserving causal effects.