Related papers: On the Limits of Learned Importance Scoring for KV…

Long-context LLM serving is bottlenecked by the cost of attending over ever-growing KV caches. Dynamic sparse attention promises relief by accessing only a small, query-dependent subset of the KV state per decoding step and extending the KV…

Rotary Position Embedding (RoPE) enables each attention head to capture multi-frequency information along the sequence dimension and is widely applied in foundation models. However, the nonlinearity introduced by RoPE complicates…

KV-cache compression at small budgets is a crowded design space spanning cache representation, head-wise routing, compression cadence, decoding behavior, and within-budget scoring. We study seven mechanisms across these five families under…

The deployment of safe and trustworthy machine learning systems, and particularly complex black box neural networks, in real-world applications requires reliable and certified guarantees on their performance. The conformal prediction…

Sparse inner product (SIP) has the attractive property of overhead being dominated by the intersection of inputs between parties, independent of the actual input size. It has intriguing prospects, especially for boosting machine learning on…

Recent advances in large language models (LLMs) have significantly boosted long-context processing. However, the increasing key-value (KV) cache size poses critical challenges to memory and execution efficiency. Most KV cache compression…

KV cache pruning has emerged as a promising technique for reducing memory and computation costs in long-context auto-regressive generation. Existing methods for vision-language models (VLMs) typically rely on self-attention scores from…

Under modern test-time compute and agentic paradigms, language models process ever-longer sequences. Efficient text generation with transformer architectures is increasingly constrained by the Key-Value cache memory footprint and bandwidth.…

Inference optimizations are critical for improving user experience and reducing infrastructure costs and power consumption. In this article, we illustrate a form of dynamic execution known as speculative sampling to reduce the overall…

Human-interpretable predictions are essential for deploying AI in medical imaging, yet most interpretable-by-design (IBD) frameworks require concept annotations for training data, which are costly and impractical to obtain in clinical…

The growing memory footprint of the Key-Value (KV) cache poses a severe scalability bottleneck for long-context Large Language Model (LLM) inference. While KV cache eviction has emerged as an effective solution by discarding less critical…

Large language models (LLMs) utilize key-value (KV) cache to store historical information during sequence processing. The size of KV cache grows linearly as the length of the sequence extends, which seriously affects memory usage and…

Speculative Decoding (SD) ensures that the output matches the target model's distribution exactly. However, we argue that this distribution matching requirement is too stringent and results in unnecessarily low acceptance rates, limiting…

Modern LLM applications such as deep-research assistants, coding agents, and Retrieval-Augmented Generation (RAG) systems, repeatedly process long prompt histories containing shared document or code chunks, creating significant pressure on…

There is a growing interest in the machine learning community in developing predictive algorithms that are "interpretable by design". Towards this end, recent work proposes to make interpretable decisions by sequentially asking…

While Large Language Models (LLMs) can theoretically support extensive context windows, their actual deployment is constrained by the linear growth of Key-Value (KV) cache memory. Prevailing compression strategies mitigate this through…

Efficient Key-Value (KV) cache management is essential for processing long text sequences in large language models (LLMs), where memory constraints often limit performance. Conventional KV eviction strategies, such as top-k selection based…

Large language models (LLMs) have demonstrated remarkable performance on long-context tasks, but are often bottlenecked by memory constraints. Namely, the KV cache, which is used to significantly speed up attention computations, grows…

Memory-augmented Large Language Models (LLMs) have demonstrated remarkable capability for complex and long-horizon embodied planning. By keeping track of past experiences and environmental states, memory enables LLMs to maintain a global…

Generative Recommendation (GR) has recently transitioned from atomic item-indexing to Semantic ID (SID)-based frameworks to capture intrinsic item relationships and enhance generalization. However, the adoption of high-granularity SIDs…