PReM (Preserve and Refresh Memory), a context-compression framework that maintains the long context as the model's internal layer-wise KV memory and learns what to preserve and when to refresh it, is introduced.
Abstract
Efficient long-context inference is not only about reducing memory cost, but also about keeping useful contextual evidence accessible as generation proceeds. However, existing compression-oriented approaches, such as key-value (KV) cache compression and context compression, often either make an early decision about which contextual information to keep or rely on an external compressor. Such designs make it difficult to adapt the compressed context to the evidence needed by later reasoning steps. This paper introduces PReM (Preserve and Refresh Memory), a context-compression framework that maintains the long context as the model's internal layer-wise KV memory and learns what to preserve and when to refresh it. Specifically, PReM uses a dedicated memory layer to make memory-selection decisions, and a special memory tokento trigger refreshes during generation. To train this behavior, PReM introduces Phase-Separated Refresh Training, aligning memory selection with memory-conditioned generation while preserving continuity across refreshes. Experiments with 32K-token contexts show that PReM outperforms strong baselines under both 16x and 32x compression, while maintaining a favorable balance between answer quality and inference efficiency.
SeDeM is proposed, a selective decompression framework that decouples compact memory storage from decoder conditioning and reduces online time-to-first-token and improves autoregressive decoding throughput relative to ICAE.
Maryam Haghifam, Jason Cong, Yizhou Sun· 1 citation
Retrieval-augmented generation (RAG) improves language-model responses by grounding generation in external passages, which comes with overhead: retrieved context lengthens the prompt, increasing prefill work, KV-cache footprint, memory traffic, latency, and energy. Context compression offers a natural remedy by pruning retrieved text before generation. However, state-of-the-art context-compression methods are typically used with a fixed compression budget, or with the rate selected offline and then applied at inference time. This static view ignores both workload variation and the live state of the edge device. On an edge SoC, compression is not free: the compressor itself runs on the same SoC and consumes latency and energy that can offset any generation savings. This paper proposes a vision for telemetry-informed adaptive compression in edge RAG, grounded in experimental evidence. We characterize the compression tradeoff on the NVIDIA Jetson AGX Thor using Llama and Qwen generators, Natural Questions and HotpotQA datasets, and LLMLingua-2 compression. Our measurements show that generation dominates the RAG budget for larger models, reaching roughly 90% of per-query latency and 91% of GPU energy for 7B-8B generators. Exploring the impact of the compression rate reveals an adaptive operating region: mild compression can miss energy opportunities, and overly aggressive compression can hurt inference quality. Intermediate compression can reduce GPU energy by up to 53.2%, and SoC energy by up to 48.2%, with negligible quality loss. We argue for runtime policies that dynamically manage compression, guided by workload features and edge telemetry.
Z. Feric, Amir Taherin, Yanzhi Wang et al.· 0 citations
Long-context inference is central to modern large language model (LLM) applications such as retrieval-augmented generation. To mitigate the growing inference cost, recent work has explored non-prefix key-value (KV) cache reuse to reduce redundant prefill computation. However, existing reuse methods primarily focus on computation savings and overlook a critical bottleneck in long-context LLM serving: the cost of storing and accessing large KV caches. While KV compression appears to be a natural complement, naively combining compression with non-prefix KV reuse often leads to severe accuracy degradation. In this work, we propose C2KV, a unified framework for non-prefix KV reuse that jointly optimizes KV cache compression and concatenation. C2KV learns a composable and compressed KV cache manifold that is explicitly designed to be position-agnostic. Our approach introduces a lightweight sidecar Extractor with learnable compression tokens and a structured attention flow, enabling modular KV representations that can be flexibly reused and concatenated without modifying the frozen base model. We further employ a compression-concatenation co-training strategy to align extraction-time representations with their downstream reuse behavior. Extensive experiments across multiple long-context benchmarks and model families demonstrate that C2KV significantly reduces KV cache storage and transfer costs, achieving up to 17× inference speedup under long contexts, while preserving generation quality.
Chuheng Du, Junyi Chen, Hanlin Tang et al.· Proceedings of the 32nd ACM...· 1 citation
This is the first work to formulate compression-aware abstention as a learning problem, in which a model learns to answer when supporting evidence survives compression and abstain when it does not, and controlled-deletion experiments show that the learned behavior is driven by evidence content rather than input length alone.
This work instantiates a new paradigm of incremental memory activation, where the effective capacity of memory is progressively expanded as the context grows, and applies this paradigm to state-of-the-art models, observing consistent improvements on standard language modeling and reasoning, as well as on long-context retrieval and understanding.
Reza Bayat, Ali Behrouz, V. Mirrokni et al.· 0 citations
Large language models deployed in specialized domains must improve in-domain performance without sacrificing general capabilities. Existing parameter-efficient fine-tuning methods are typically always on: their learned perturbations are applied to every input, which can degrade out-of-domain (OOD) performance. We propose Engram Adapter, a framework that repurposes pretraining-time conditional memory as a post-hoc adapter for frozen LLMs. It uses multi-channel matching over local n-gram patterns with explicit occupancy tracking as a lightweight selectivity prior, making residual injection more likely on in-domain inputs while a learned scalar gate suppresses incoherent OOD retrievals. We evaluate on Qwen3-4B and Qwen3-8B with AG-News and MedMCQA as adaptation tasks and OOD benchmarks spanning reasoning, translation, code generation, and legal reasoning. Engram Adapter improves in-domain accuracy while preserving 99.4%--100.1% of average OOD performance; on LegalBench it slightly exceeds the frozen base model on average, whereas comparable always-on baselines degrade sharply. Mechanistic analyses show that although OOD activations are non-zero, gate and projection attenuation reduce residuals to approximately 0.08% of hidden-state norm, yielding small KL drift and negligible accuracy change. These results suggest conditional activation is a promising route toward modular, retention-preserving domain specialization over frozen backbones.
Jiaxuan Hou, Lei Wang· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
