Yuxuan Zhu, David H. Yang, Parisa Shiravani, Mohammad Mohammadi Amiri, Tejaswini Pedapati, Subhajit Chaudhury, Keerthiram Murugesan, Pin-Yu Chen
Key-value (KV) caching is a core mechanism in large language models, where intermediate key and value representations are stored to accelerate autoregressive decoding. As generation length increases, KV cache memory and computation grow linearly, making compression critical for efficient long-output reasoning. Dictionary-based sparse KV compression is appealing because it represents each token's KV states as a sparse combination of learned basis elements (atoms) in a dictionary, preserving token-level structure without enforcing a global low-rank constraint. However, existing dictionary-based methods face two practical limitations during decoding: iterative sparse coding methods such as Orthogonal Matching Pursuit add decoding-time overhead, and static dictionaries may mismatch evolving KV distributions under test-time generation. While adaptive dictionary updates can reduce this mismatch, naive append-only strategies lead to dictionary growth during generation. We propose FAD-KV, a \textbf{F}ast \textbf{A}daptive \textbf{D}ictionary KV caching framework for efficient reasoning decoding. FAD-KV integrates (i) a screening-based sparse coding scheme, where a one-shot Top-\(n\) selection identifies a small candidate pool followed by lightweight coefficient refinement, and (ii) a fixed-size dictionary adaptation mechanism that reuses inactive atoms instead of expanding the dictionary. By controlling both sparse coding cost and adaptive dictionary growth, FAD-KV provides a memory-bounded and computation-efficient KV compression framework for long reasoning workloads. Experiments on reasoning and long-context benchmarks show that FAD-KV achieves a strong quality-efficiency trade-off while avoiding unbounded dictionary growth during decoding.
Erik Miehling IBM Research, Karthikeyan Natesan Ramamurthy International Business Machines, Praveen Venkateswaran International Business Machines, Ching-Yun Ko International Business Machines, Pierre Dognin International Business Machines, Moninder Singh International Business Machines, Tejaswini Pedapati, Avinash Balakrishnan International Business Machines 等 13 位作者
The AI Steerability 360 toolkit is an extensible, open-source Python library for steering LLMs. Steering abstractions are designed around four model control surfaces: input (modification of the prompt), structural (modification of the model’s weights or architecture), state (modification of the model’s activations and attentions), and output (modification of the decoding or generation process). Steering methods exert control on the model through a common interface, termed a steering pipeline, which additionally allows for the composition of multiple steering methods. Comprehensive evaluation and comparison of steering methods/pipelines is facilitated by use case classes (for defining tasks) and a benchmark class (for performance comparison on a given task). The functionality provided by the toolkit significantly lowers the barrier to developing and comprehensively evaluating steering methods. The toolkit is Hugging Face native and is released under an Apache 2.0 license at https://github.com/IBM/AISteer360.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · 2026 · 正式发表
David H. Yang Rensselaer Polytechnic Institute, Yuxuan Zhu, Mohammad Mohammadi Amiri Rensselaer Polytechnic Institute, Keerthiram Murugesan International Business Machines, Tejaswini Pedapati, Subhajit Chaudhury International Business Machines, Pin-Yu Chen International Business Machines
Large language models (LLMs) have shown great performance on complex reasoning tasks but often require generating long intermediate thoughts before reaching a final answer. During generation, LLMs rely on a key-value (KV) cache for autoregressive decoding. However, the memory footprint of the KV cache grows with output length. Prior work on KV cache optimization mostly focus on compressing the long input context, while retaining the full KV cache for decoding. For tasks requiring long output generation, this leads to increased computational and memory costs. In this paper, we introduce ZoomR, a novel approach that enables LLMs to adaptively compress verbose reasoning thoughts into summaries and uses a dynamic KV cache selection policy that leverages these summaries while also strategically “zooming in” on fine-grained details. By using summary keys as a coarse-grained index during decoding, ZoomR uses the query to retrieve details for only the most important thoughts. This hierarchical strategy significantly reduces memory usage by avoiding full-cache attention at each step. Experiments across math and reasoning tasks show that our approach achieves competitive performance compared to baselines, while reducing inference memory requirements by more than 4 \times. These results demonstrate that a multi-granularity KV selection enables more memory efficient decoding, especially for long output generation.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表