Introduces state commitment learning and Counterfactual Erasure RL (CERL) to train models to commit only persistent state, reducing answer dependence on hidden thoughts across math, logic, QA, and tool-use tasks without accuracy loss.
Snapkv: Llm knows what you are looking for before generation
4 Pith papers cite this work, alongside 15 external citations. Polarity classification is still indexing.
4
Pith papers citing it
15
external citations · OpenAlex
years
2026 4representative citing papers
GRKV applies global ridge regression to KV cache merging for span-based retention in long-context LLMs, claiming to be the only method that improves benchmark performance with minimal overhead.
AudioKV prioritizes audio-critical attention heads identified via ASR analysis and applies spectral score smoothing to evict KV cache tokens, achieving high compression with minimal accuracy loss in LALMs.
citing papers explorer
-
State commitment learning: training language models to distinguish computation from memory
Introduces state commitment learning and Counterfactual Erasure RL (CERL) to train models to commit only persistent state, reducing answer dependence on hidden thoughts across math, logic, QA, and tool-use tasks without accuracy loss.
-
GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs
GRKV applies global ridge regression to KV cache merging for span-based retention in long-context LLMs, claiming to be the only method that improves benchmark performance with minimal overhead.
-
AudioKV: KV Cache Eviction in Efficient Large Audio Language Models
AudioKV prioritizes audio-critical attention heads identified via ASR analysis and applies spectral score smoothing to evict KV cache tokens, achieving high compression with minimal accuracy loss in LALMs.
- FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion