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.
Keep the cost down: A review on methods to optimize llm’s kv-cache consumption
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
representative citing papers
KV cache eviction is unified under an information capacity maximization principle derived from a linear-Gaussian attention surrogate, with CapKV proposed as a leverage-score based implementation that outperforms prior heuristics in experiments.
Transformers need depth scaling as the product of ceil(k/s) and log n terms for k-hop pointer chasing under cache size s, with a conjectured lower bound, proved upper bound via windowed pointer doubling, and an adaptive-oblivious error separation.
TriAttention compresses KV cache by exploiting stable pre-RoPE Q/K concentration and trigonometric distance preferences to match full-attention reasoning accuracy with far lower memory and higher speed.
An attack aligns differently shuffled intermediate activations from secure Transformer inference queries to recover model weights with low error using roughly one dollar of queries.
Saliency-R1 uses a novel saliency map technique and GRPO with human bounding-box overlap as reward to improve VLM reasoning faithfulness and interpretability.
EchoKV compresses LLM KV caches by reconstructing missing components from partial data via inter- and intra-layer attention similarities, outperforming prior methods on LongBench and RULER while supporting on-demand full-cache inference.
A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.
Position paper proposes replacing fragmented narrow AI models with LLMs as the cognitive orchestrator in the RAN Intelligent Controller for Level 5 autonomous 6G networks.
citing papers explorer
-
Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost
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.
-
Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective
KV cache eviction is unified under an information capacity maximization principle derived from a linear-Gaussian attention surrogate, with CapKV proposed as a leverage-score based implementation that outperforms prior heuristics in experiments.
-
How Much Cache Does Reasoning Need? Depth-Cache Tradeoffs in KV-Compressed Transformers
Transformers need depth scaling as the product of ceil(k/s) and log n terms for k-hop pointer chasing under cache size s, with a conjectured lower bound, proved upper bound via windowed pointer doubling, and an adaptive-oblivious error separation.
-
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
TriAttention compresses KV cache by exploiting stable pre-RoPE Q/K concentration and trigonometric distance preferences to match full-attention reasoning accuracy with far lower memory and higher speed.
-
On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
An attack aligns differently shuffled intermediate activations from secure Transformer inference queries to recover model weights with low error using roughly one dollar of queries.
-
Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward
Saliency-R1 uses a novel saliency map technique and GRPO with human bounding-box overlap as reward to improve VLM reasoning faithfulness and interpretability.
-
EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
EchoKV compresses LLM KV caches by reconstructing missing components from partial data via inter- and intra-layer attention similarities, outperforming prior methods on LongBench and RULER while supporting on-demand full-cache inference.
-
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.
-
Agents Should Replace Narrow Predictive AI as the Orchestrator in 6G AI-RAN
Position paper proposes replacing fragmented narrow AI models with LLMs as the cognitive orchestrator in the RAN Intelligent Controller for Level 5 autonomous 6G networks.