4 accepted papers
Lossy KV cache compression is a well-explored subfield of machine learning efficiency, with improved latency being one of its major gains. However, lossy compression techniques can fumble from time to time, exhibiting various — and often catastrophic — failure patterns that are not only difficult to…
Self-attention dominates the computational and memory cost of long-context LLM inference across both prefill and decode phases. To address this challenge, we introduce **Sketch\&Walk** Attention, a training-free sparse attention method that determines sparsity with lightweight sketches and determini…
Large Language Models (LLMs) are increasingly adopted across real-world applications, yet traditional evaluations rely on expensive, domain-specific ground-truth labels that are often unavailable or infeasible. We introduce a ground-truth-free evaluation framework focused on reasoning consistency an…
Large Reasoning Models (LRMs) are often bottlenecked by the high cost of output tokens. We show that a significant portion of these tokens are useless self-repetitions — what we call “word salad” — that exhaust the decoding budget without adding value. Interestingly, we observe that LRMs are self-aw