Daily Papers

This report investigates enhancing semantic caching effectiveness by employing specialized, fine-tuned embedding models. Semantic caching relies on embedding similarity rather than exact key matching, presenting unique challenges in balancing precision, query latency, and computational efficiency. We propose leveraging smaller, domain-specific embedding models, fine-tuned with targeted real-world and synthetically generated datasets. Our empirical evaluations demonstrate that compact embedding models fine-tuned for just one epoch on specialized datasets significantly surpass both state-of-the-art open-source and proprietary alternatives in precision and recall. Moreover, we introduce a novel synthetic data generation pipeline for the semantic cache that mitigates the challenge of limited domain-specific annotated data, further boosting embedding performance. Our approach effectively balances computational overhead and accuracy, establishing a viable and efficient strategy for practical semantic caching implementations.

Large Language Models (LLMs) like ChatGPT and Llama have revolutionized natural language processing and search engine dynamics. However, these models incur exceptionally high computational costs. For instance, GPT-3 consists of 175 billion parameters, where inference demands billions of floating-point operations. Caching is a natural solution to reduce LLM inference costs on repeated queries, which constitute about 31% of the total queries. However, existing caching methods are incapable of finding semantic similarities among LLM queries nor do they operate on contextual queries, leading to unacceptable false hit-and-miss rates. This paper introduces MeanCache, a user-centric semantic cache for LLM-based services that identifies semantically similar queries to determine cache hit or miss. Using MeanCache, the response to a user's semantically similar query can be retrieved from a local cache rather than re-querying the LLM, thus reducing costs, service provider load, and environmental impact. MeanCache leverages Federated Learning (FL) to collaboratively train a query similarity model without violating user privacy. By placing a local cache in each user's device and using FL, MeanCache reduces the latency and costs and enhances model performance, resulting in lower false hit rates. MeanCache also encodes context chains for every cached query, offering a simple yet highly effective mechanism to discern contextual query responses from standalone. Our experiments benchmarked against the state-of-the-art caching method, reveal that MeanCache attains an approximately 17% higher F-score and a 20% increase in precision during semantic cache hit-and-miss decisions while performing even better on contextual queries. It also reduces the storage requirement by 83% and accelerates semantic cache hit-and-miss decisions by 11%.

LLM serving systems process heterogeneous query workloads where different categories exhibit different characteristics. Code queries cluster densely in embedding space while conversational queries distribute sparsely. Content staleness varies from minutes (stock data) to months (code patterns). Query repetition patterns range from power-law (code) to uniform (conversation), producing long tail cache hit rate distributions: high-repetition categories achieve 40-60% hit rates while low-repetition or volatile categories achieve 5-15% hit rates. Vector databases must exclude the long tail because remote search costs (30ms) require 15--20% hit rates to break even, leaving 20-30% of production traffic uncached. Uniform cache policies compound this problem: fixed thresholds cause false positives in dense spaces and miss valid paraphrases in sparse spaces; fixed TTLs waste memory or serve stale data. This paper presents category-aware semantic caching where similarity thresholds, TTLs, and quotas vary by query category. We present a hybrid architecture separating in-memory HNSW search from external document storage, reducing miss cost from 30ms to 2ms. This reduction makes low-hit-rate categories economically viable (break-even at 3-5% versus 15-20%), enabling cache coverage across the entire workload distribution. Adaptive load-based policies extend this framework to respond to downstream model load, dynamically adjusting thresholds and TTLs to reduce traffic to overloaded models by 9-17% in theoretical projections.

LLM-based agentic applications have shown increasingly remarkable capabilities in complex workflows but incur substantial costs due to extensive planning and reasoning requirements. Existing LLM caching techniques (like context caching and semantic caching), primarily designed for serving chatbots, are insufficient for agentic applications where outputs depend on external data or environmental contexts. We propose agentic plan caching, a novel approach that extracts, stores, adapts, and reuses structured plan templates from planning stages of agentic applications across semantically similar tasks to reduce the cost of serving. Unlike traditional semantic caching, our system extracts plan templates from completed agent executions at test-time, employs keyword extraction to match new requests against cached plans, and utilizes lightweight models to adapt these templates to task-specific plans with contexts. Evaluation across multiple real-world agentic applications shows that our system can reduce costs by 46.62% on average while maintaining performance, offering a more efficient solution for serving LLM-based agents that complements existing LLM serving infrastructures.

Generative AI has unlocked new possibilities in content discovery and management. Through collaboration with the National Football League (NFL), we demonstrate how a generative-AI based workflow enables media researchers and analysts to query relevant historical plays using natural language rather than traditional filter-and-click interfaces. The agentic workflow takes a user query as input, breaks it into elements, and translates them into the underlying database query language. Accuracy and latency are further improved through carefully designed semantic caching. The solution achieves over 95 percent accuracy and reduces the average time to find relevant videos from 10 minutes to 30 seconds, significantly increasing the NFL's operational efficiency and allowing users to focus on producing creative content and engaging storylines.

Semantic prompt caches reduce the latency and cost of large language model (LLM) inference by reusing cached LLM-generated responses for semantically similar prompts. Vector similarity metrics assign a numerical score to quantify the similarity between an embedded prompt and its nearest neighbor in the cache. Existing systems rely on a static threshold to classify whether the similarity score is sufficiently high to result in a cache hit. We show that this one-size-fits-all threshold is insufficient across different prompts. We propose VectorQ, a framework to learn embedding-specific threshold regions that adapt to the complexity and uncertainty of an embedding. Through evaluations on a combination of four diverse datasets, we show that VectorQ consistently outperforms state-of-the-art systems across all static thresholds, achieving up to 12x increases in cache hit rate and error rate reductions up to 92%.

Large language models face significant computational and memory challenges when processing long contexts. During inference, efficient management of the key-value (KV) cache, which stores intermediate activations for autoregressive generation, is critical to reducing memory overhead and improving computational efficiency. Traditional token-level efficient KV caching methods overlook semantic information, treating tokens independently without considering their semantic relationships. Meanwhile, existing semantic-preserving KV cache management approaches often suffer from substantial memory usage and high time-to-first-token. To address these limitations, we propose SentenceKV, a novel sentence-level semantic KV caching approach designed to enhance inference efficiency while preserving semantic coherence. During prefilling, SentenceKV groups tokens based on sentence-level semantic similarity, compressing sentence representations into concise semantic vectors stored directly on the GPU, while individual KV pairs are offloaded to CPU. During decoding, SentenceKV generates tokens by selectively retrieving semantically relevant sentence-level KV entries, leveraging the semantic similarity between the prefilling-stage semantic vectors and decoding-stage queries. This ensures efficient and contextually accurate predictions, minimizing the loading of redundant or irrelevant data into GPU memory and significantly reducing memory overhead while maintaining stable inference latency, even for extremely long contexts. Extensive evaluations on benchmarks including PG-19, LongBench, and Needle-In-A-Haystack demonstrate that SentenceKV significantly outperforms state-of-the-art methods in both efficiency and memory usage, without compromising model accuracy.

Diffusion-based large language models (dLLMs) are gaining attention for their inherent capacity for parallel decoding, offering a compelling alternative to autoregressive LLMs. Among various decoding strategies, blockwise semi-autoregressive (semi-AR) approaches are widely adopted due to their natural support for KV caching and their favorable accuracy-speed trade-off. However, this paper identifies two fundamental limitations in the conventional semi-AR decoding approach that applies a fixed block size: i) late decoding overhead, where the unmasking of high-confidence tokens outside the current block is unnecessarily delayed, and ii) premature decoding error, where low-confidence tokens inside the current block are committed too early, leading to incorrect tokens. This paper presents the first systematic investigation challenging the fixed block size assumption in semi-AR decoding. Through a statistical analysis of confidence dynamics during the denoising process, we identify a volatility band (VB) region during dLLM decoding, which encodes local semantic structure and can be used to guide adaptive block sizing. Leveraging these insights, we introduce AdaBlock-dLLM, a training-free, plug-and-play scheduler that adaptively aligns block boundaries with semantic steps by adjusting block size during runtime. Extensive experiments across diverse benchmarks show that AdaBlock-dLLM achieves up to 5.3% accuracy improvement under the same throughput budget. Beyond inference-time optimization, we hope our semantics-aware adaptive scheduling approach and confidence-based analysis will inspire future training strategies for dLLMs.

Large Language Models (LLMs) have been widely deployed in a variety of applications, and the context length is rapidly increasing to handle tasks such as long-document QA and complex logical reasoning. However, long context poses significant challenges for inference efficiency, including high memory costs of key-value (KV) cache and increased latency due to extensive memory accesses. Recent works have proposed compressing KV cache to approximate computation, but these methods either evict tokens permanently, never recalling them for later inference, or recall previous tokens at the granularity of pages divided by textual positions. Both approaches degrade the model accuracy and output quality. To achieve efficient and accurate recallable KV cache compression, we introduce ClusterKV, which recalls tokens at the granularity of semantic clusters. We design and implement efficient algorithms and systems for clustering, selection, indexing and caching. Experiment results show that ClusterKV attains negligible accuracy loss across various tasks with 32k context lengths, using only a 1k to 2k KV cache budget, and achieves up to a 2times speedup in latency and a 2.5times improvement in decoding throughput. Compared to SoTA recallable KV compression methods, ClusterKV demonstrates higher model accuracy and output quality, while maintaining or exceeding inference efficiency.

Self-training has shown great potential in semi-supervised learning. Its core idea is to use the model learned on labeled data to generate pseudo-labels for unlabeled samples, and in turn teach itself. To obtain valid supervision, active attempts typically employ a momentum teacher for pseudo-label prediction yet observe the confirmation bias issue, where the incorrect predictions may provide wrong supervision signals and get accumulated in the training process. The primary cause of such a drawback is that the prevailing self-training framework acts as guiding the current state with previous knowledge, because the teacher is updated with the past student only. To alleviate this problem, we propose a novel self-training strategy, which allows the model to learn from the future. Concretely, at each training step, we first virtually optimize the student (i.e., caching the gradients without applying them to the model weights), then update the teacher with the virtual future student, and finally ask the teacher to produce pseudo-labels for the current student as the guidance. In this way, we manage to improve the quality of pseudo-labels and thus boost the performance. We also develop two variants of our future-self-training (FST) framework through peeping at the future both deeply (FST-D) and widely (FST-W). Taking the tasks of unsupervised domain adaptive semantic segmentation and semi-supervised semantic segmentation as the instances, we experimentally demonstrate the effectiveness and superiority of our approach under a wide range of settings. Code will be made publicly available.

Generating minute-long videos is a critical step toward developing world models, providing a foundation for realistic extended scenes and advanced AI simulators. The emerging semi-autoregressive (block diffusion) paradigm integrates the strengths of diffusion and autoregressive models, enabling arbitrary-length video generation and improving inference efficiency through KV caching and parallel sampling. However, it yet faces two enduring challenges: (i) KV-cache-induced long-horizon error accumulation, and (ii) the lack of fine-grained long-video benchmarks and coherence-aware metrics. To overcome these limitations, we propose BlockVid, a novel block diffusion framework equipped with semantic-aware sparse KV cache, an effective training strategy called Block Forcing, and dedicated chunk-wise noise scheduling and shuffling to reduce error propagation and enhance temporal consistency. We further introduce LV-Bench, a fine-grained benchmark for minute-long videos, complete with new metrics evaluating long-range coherence. Extensive experiments on VBench and LV-Bench demonstrate that BlockVid consistently outperforms existing methods in generating high-quality, coherent minute-long videos. In particular, it achieves a 22.2% improvement on VDE Subject and a 19.4% improvement on VDE Clarity in LV-Bench over the state of the art approaches. Project website: https://ziplab.co/BlockVid. Inferix (Code): https://github.com/alibaba-damo-academy/Inferix.

Low-Rank Adaptation (LoRA) has emerged as a widely adopted technique in text-to-image models, enabling precise rendering of multiple distinct elements, such as characters and styles, in multi-concept image generation. However, current approaches face significant challenges when composing these LoRAs for multi-concept image generation, resulting in diminished generated image quality. In this paper, we initially investigate the role of LoRAs in the denoising process through the lens of the Fourier frequency domain. Based on the hypothesis that applying multiple LoRAs could lead to "semantic conflicts", we find that certain LoRAs amplify high-frequency features such as edges and textures, whereas others mainly focus on low-frequency elements, including the overall structure and smooth color gradients. Building on these insights, we devise a frequency domain based sequencing strategy to determine the optimal order in which LoRAs should be integrated during inference. This strategy offers a methodical and generalizable solution compared to the naive integration commonly found in existing LoRA fusion techniques. To fully leverage our proposed LoRA order sequence determination method in multi-LoRA composition tasks, we introduce a novel, training-free framework, Cached Multi-LoRA (CMLoRA), designed to efficiently integrate multiple LoRAs while maintaining cohesive image generation. With its flexible backbone for multi-LoRA fusion and a non-uniform caching strategy tailored to individual LoRAs, CMLoRA has the potential to reduce semantic conflicts in LoRA composition and improve computational efficiency. Our experimental evaluations demonstrate that CMLoRA outperforms state-of-the-art training-free LoRA fusion methods by a significant margin -- it achieves an average improvement of 2.19% in CLIPScore, and 11.25% in MLLM win rate compared to LoraHub, LoRA Composite, and LoRA Switch.

Large Language Models (LLMs) have gained immense success in revolutionizing various applications, including content generation, search and recommendation, and AI-assisted operation. To reduce high training costs, Mixture-of-Experts (MoE) architecture has become a popular backbone for modern LLMs. However, despite the benefits, serving MoE-based LLMs experience severe memory inefficiency due to sparsely activated experts. Recent studies propose to offload inactive experts from GPU memory to CPU memory to improve the serving efficiency of MoE models. However, they either incur high inference latency or high model memory footprints due to coarse-grained designs. To tame the latency-memory trade-off in MoE serving, we present fMoE, a fine-grained expert offloading system for MoE serving that achieves low inference latency with memory efficiency. We design fMoE to extract fine-grained expert selection patterns from MoE models and semantic hints from input prompts to efficiently guide expert prefetching, caching, and offloading decisions. fMoE is prototyped on top of HuggingFace Transformers and deployed on a six-GPU testbed. Experiments with open-source MoE models and real-world workloads show that fMoE reduces inference latency by 47% and improves expert hit rate by 36% over state-of-the-art solutions.