As edge-based deep learning applications become more complex, optimizing performance on heterogeneous System-on-Chips (SoCs) presents unique challenges. Traditional pipelining techniques distributing the computation across different on-chip processing units, while effective for throughput, do not address the latency demands posed by modern neural networks with complex interdependencies and extensive operator parallelism. There is a potential in leveraging operator parallelism to enable concurrent execution across multiple processing units, thereby reducing inference latency. However, prioritizing pipelining or parallel execution often necessitates a compromise, where optimizing one performance metric adversely impacts the other. This paper introduces Para-Pipe, a hierarchical mapping framework that integrates intra- and inter-stage operator parallelism within a pipelined architecture. Para-Pipe navigates the trade-off between throughput and latency by selectively fine-tuning parallelism levels within and across pipeline stages. This strategy can significantly reduce inter-processor communication overhead, significantly improving energy efficiency. Our evaluation demonstrates that Para-Pipe generates multiple Pareto-optimal configurations, achieving a balance between throughput and latency on an Amlogic SoC equipped with ARM big.LITTLE CPUs and GPU, as well as the Black Sesame Technology SoC featuring a deep learning accelerator and two DSPs. More importantly, throughput-optimized configurations under Para-Pipe on Amlogic SoC show an average energy efficiency improvement of 11.0% over purely pipelined strategies and 23.3% relative to non-pipelined parallel execution.
Effective manager-employee communication is critical for retaining high performers and developing underperformers, yet training managers in these skills remains costly. Text-based chatbots offer a scalable approach but cannot provide realistic rehearsal: managers need to practice speaking aloud to build confidence before high-stakes conversations. In this paper, we propose Conversation Coach, a voice-first AI system that enables managers to rehearse difficult workplace conversations in a realistic spoken format. The system addresses three challenges: achieving low-latency interactions with strong language understanding, enabling adaptive conversations through configurable bot personalities that simulate different employee types, and generating personalized feedback on content and policy compliance. We compare an end-to-end speech-to-speech model with a cascaded approach combining automatic speech recognition, a large language model, and text-to-speech synthesis. The end-to-end approach achieves 3$\times$ lower median (P50) latency with native barge-in capability at an estimated 8$\times$ lower cost, while the cascaded approach offers superior reasoning essential for coaching quality. We deployed the cascaded architecture in production, where 40,000+ managers used it over six months, with adoption patterns indicating selective use for difficult conversations.
This paper proposes a layer bit allocation method for Gemma-3-1B, formulating the problem as performance maximization (latency decrease) given a degradation budget constraint (allowable level of generation quality loss). This approach is different from time- and resource-consuming uniform layer quantization methods that are used in the literature (like GPTQ or AWQ) or allocation methods without proven performance-accelerating effect (like MixLLM or TorchAO). The layer sensitivity profile resulting from our prior work SA-PTQ is applied using the activation pass-through mode inside TensorRT-LLM. For each layer precision is determined individually in blocks, according to a grouping introduced in the prior step (5+5, 10+10, all26), differentiating the contribution of FFN, Attention, and lm_head to the overall speedup. The clock speed was measured for 13 W8A8 variants on an RTX 5090. We find that for FFN and lm_head the time cost of quantization/dequantization is compensated for by the use of integer arithmetic, while for short context lengths, the opposite holds true for Attention: an additional step of quantization slows execution down. We propose a manual implementation of SmoothQuant for TensorRT-LLM which was necessary due to export failures, unavailable for lm_head. The best solution found under joint consideration of all three criteria with minimal degradation was FFN 5+5 with lm_head, providing an 11.0% reduction in latency with negligible quality loss (98.90% Top-1 agreement, +0.85% perplexity degradation). With acceptable quality loss for FFN all26 + lm_head, a speedup up to 19.1% was found possible. We suggest further optimizations: fused attention kernels in INT8, KV-cache quantization, using FP8 instead of INT8 and partial Attention quantization analogous to FFN.
Existing methods for improving Retrieval-Augmented Generation (RAG) efficiency mainly optimize downstream LLM generation, such as context compression or serving optimization. However, RAG is an end-to-end system, and its bottleneck can shift between upstream reranking and downstream generation under different serving loads and reranking budgets.In this paper, we first empirically characterize this shifting-bottleneck behavior and show that upstream reranking can become the dominant bottleneck under high query rates or large reranking budgets. Reducing the reranking budget can relieve this bottleneck, but it may also drop supporting evidence and degrade recall. To address this problem, we propose \textbf{\textsf{PACE}} (\textbf{P}rioritized \textbf{A}daptive \textbf{C}overage of \textbf{E}vidence), a training-free framework that combines \textit{evidence frontloading} with \textit{pressure-adaptive budgeting}. \textsf{PACE} first reorders candidates by marginal evidence coverage, prioritizing documents that are query-relevant, complementary, and useful for forming multi-hop evidence chains. We show that this objective is monotone submodular, giving greedy selection a $(1-1/e)$ approximation guarantee. \textsf{PACE} then dynamically adjusts the reranking budget according to the relative pressure of the reranker and the LLM. Experiments on three multi-hop QA datasets and online serving simulations show that \textsf{PACE} improves evidence recall, reduces p95 latency under ranking-heavy workloads. More importantly, the two components together reveal that \textit{less can be more}: an evidence-dense top-ranked candidates enable higher final recall with fewer reranked documents.
AI-RAN brings large language model (LLM) serving close to mobile users, but cellular handover can separate an active request from its inference state: the user attaches to a target base station (gNB) while the large and growing key-value (KV) cache remains at the source. Retaining inference at the source preserves service continuity but persistently increases inter-token latency (ITL), whereas recovering the state at the target restores serving locality but requires KV-cache transfer, recomputation, or a combination of both only after handover, directly prolonging service interruption time (SIT). This work presents Pallas, a \textit{proactive} KV-cache migration framework that prepares the inference state at the predicted target before handover, in parallel with ongoing source-side inference and token delivery. At the preparation trigger, Pallas partitions the token sequence into a stable historical prefix and an evolving suffix. The target reconstructs the prefix through local prefill, while the source streams the KV blocks generated for the suffix. At handover, the target assembles both portions into an up-to-date KV cache and resumes decoding locally, leaving only unfinished preparation to contribute to SIT. An online scheduler selects the \textit{prefetching window}, which determines how early preparation begins before handover, based on mobility predictions and runtime telemetry. Across three LLMs and $100$--$500~\mathrm{Mbps}$ inter-gNB links, our vLLM-based prototype reduces average SIT by factors of $2.28$--$89.68$ over target-side recovery approaches and lowers average ITL by $16.0\%$--$50.0\%$ compared with source-side forwarding.
UAV on-board vision systems are widely used for different activities, including monitoring in no-fly zones. In this case, the vision-equipped UAV streams a video to a ground server where an operator assists its activities. The latency of video transmission has a profound impact on the effectiveness of the operator assistance. However, most techniques available for video transmission still incur significant latency costs. In this paper, we propose a graph convolutional neural network-assisted (GCN-Assisted A2C) deep reinforcement learning (DRL) system model to find the optimal pixel-correlated area of a suspicious object. We combine the Lagrangian dual form with gradient descent to prevent lack of convergence and over- and under-penalization constraint violation during latency optimization. The proposed system model sends a sub-group pixel-correlated area of the frame from the UAV to the server rather than the transmission of the whole video frame. The proposed framework utilizes the GCN model to explore hidden representations of feature-correlated groups of pixels. Moreover, the GCN supervises the A2C model, which selects a subgroup to enhance transmission latency, thus supervising the training of UAV actions in A2C. Experimental results show that GCN-assisted A2C reduces video frame transmission latency together with false detection rate in UAV vision systems over other DRL and state-of-the-art models.
Liangkai Liu, Kang G. Shincs.RO cs.CV cs.DC eess.SY
Multimodal bird's-eye-view (BEV) perception combines LiDAR depth accuracy with dense camera semantics, but its high computational cost and imperfect sensing conditions make real-time deployment challenging. Existing methods largely compress individual detectors and overlook three opportunities: structured sparsity within camera and LiDAR inputs, timing misalignment between modalities, and the fact that many detected objects do not affect the planner's immediate action. We present MM-BEV, a real-time multimodal BEV system guided by a simple principle: compute where and when it matters. MM-BEV divides perception into mandatory work for safety-critical objects within braking distance of the ego vehicle and with short time-to-collision (TTC), and optional work for less urgent regions. It prioritizes mandatory work and reduces or sheds optional work under tight compute budgets. MM-BEV integrates four mechanisms: (1) a criticality-ranked temporal ROI selector based on motion-extrapolated detections from prior frames; (2) sparse, ROI-aware feature extraction using shared-shape camera crops at context-adaptive resolution and ROI-aware LiDAR voxelization; (3) a latency-aware coordinator that adapts LiDAR sweeps, image resolution, and keyframes according to scene dynamics and TTC; and (4) an asynchronous scheduler that decouples sensing from inference and skips stale frames. On nuScenes, MM-BEV reduces inference latency by 1.96x and end-to-end latency by 2.93x, with no loss in geometry-critical recall and only a 0.2 percentage-point drop in safety-critical recall. On a Clearpath Husky A300 equipped with an Ouster-128 LiDAR, BEV cameras, and a Jetson AGX Orin, MM-BEV further reduces mean latency by 2.11x, demonstrating its potential for real-world autonomous systems.
Load imbalance poses a major bottleneck to the efficiency of expert parallelism in distributed inference of Mixture-of-Experts (MoE) models. The most heavily loaded rank stalls global execution due to skewed routing distributions, directly increasing latency. While offline expert placement can alleviate persistent imbalance, practical multi-task serving workloads exhibit layer- and batch-dependent routing dynamics, making online load balancing indispensable. Existing approaches rely on routing statistics collected after each MoE router, requiring expert weight load or migration to begin only after routing decisions are available, consequently placing migration overhead on the inference critical path. In this work, we observe that online balancing can instead be largely overlapped with computation before target routing (e.g., attention), if routing distributions can be predicted accurately in advance. Therefore, we propose FreeBalance, a lossless online load-balancing framework that overlaps expert migration with preceding computation stages via residual workload prediction. FreeBalance leverages cross-layer similarities in hidden representations within the residual network to build a lightweight workload predictor. This enables proactive expert migration planning before routing decisions are available, creating substantial overlap between weight transfer and computation-heavy pre-routing stages. Furthermore, a cost model constrains the number of swaps to fully hide the synchronization overhead within the available window. Experiments across models and datasets show that FreeBalance reduces the max-to-mean rank load ratio by 32.8% and end-to-end prefill latency by 13.1%. Specifically, our method hides balancing overhead of an average of 5.1 experts per layer, which would otherwise account for about 8.5% of the critical-path latency.
LLM-agent services repeatedly execute small deterministic transitions between model and tool calls: route an outcome, update state, and emit the next effect. We ask when this control path exposes enough concurrent work for GPU execution, and what changes when a GPU-computed route decision remains on device. We formalize the ready-cohort boundary using fixed-partition share F, exact offline share P*, local upper bound U, and online achieved share A. Under zero service time, unlimited capacity, and equal relative launch deadlines, a specialized dynamic program computes P* exactly. In a stationary Poisson replay of one pinned 851-session public trace panel, the primary condition at 100,000 target active sessions, K=256, and a 50 ms launch deadline gives F=30.19%, P*=43.00%, and U=45.85%. Exact packing recovers 81.83% of the opportunity lost at fixed window boundaries. The outcome-derived route key is a conditioning proxy, not proof of executable identity. A separate mechanism study keeps a GPU-computed binary decision on device instead of returning four bytes to the host and redispatching. Across four named GPU placements, the device-resident path is faster in all 36 configurations; within-placement row-median ratios range from 1.19x to 2.39x. Across both admissible mechanisms, all 14,557,440 tested batched invocations match a separately implemented host oracle. A fixed nested device graph that removes no host decision is slower in all 60 configurations across five placements. Together, the studies establish two measurable gates for GPU agent control: deadline-feasible cohort supply and observation placement. A joined finite online runtime is required to measure A, CPU displacement, and service-level benefit.
Muhammad Faizan Raza, Shuo, Yang +1cs.LG cs.CL cs.DC cs.IR
Retrieval-Augmented Generation (RAG) systems in production operate under strict service level objectives (SLOs) on tail latency and infrastructure cost. However, standard retrieval pipelines rely on fixed retrieval budgets that ignore query difficulty, over-retrieving for easy queries and under-serving hard ones, forcing operators to trade answer quality against SLO compliance. This paper proposes SAGE, a learned SLO-aware adaptive retrieval policy that dynamically selects the number of passages k per query. SAGE uses lightweight features derived from initial retrieval (e.g., score distributions, rank gaps, lexical signals) and is trained offline via imitation learning from an oracle that approximates optimal latency-quality trade-offs. At inference, it adds no LLM calls and minimal overhead. On Natural Questions, under a 5s P95 latency SLO, SAGE achieves 95% SLO compliance versus 30% for the best static baseline (k=20), reduces P95 latency by 36% and retrieval cost by 51% with only 2 percentage points Exact Match (EM) loss. A single policy trained on Natural Questions generalizes across HotpotQA, UnSeenTimeQA, and four LLM families (Llama, Qwen, Mistral, Gemma), consistently yielding +45-52 point SLO improvements without quality degradation.
Quantized Neural Networks~(QNN) with low-bitwidth data have proven promising in efficient storage and computation on edge devices. To mitigate accuracy degradation while maximizing speedup, layer-wise mixed-precision quantization~(MPQ) becomes a popular solution. However, existing algorithms for exploring MPQ schemes are limited in flexibility and efficiency. Comprehending the complex impacts of different MPQ schemes on post-training quantization and quantization-aware training results is a challenge for conventional methods. Furthermore, an end-to-end framework for the optimization and deployment of MPQ models is missing in existing work. To address these challenges, we propose the MiCo framework, a holistic MPQ exploration and deployment framework for edge AI applications. The framework adopts a novel optimization algorithm to search for accuracy-optimal quantization configurations under strict latency constraints. We further extended the framework to MiCoPro, which introduces a robust Hardware-Aware Proxy (HAP) model to enhance prediction accuracy and hardware versatility. By leveraging target-specific latency modeling, MiCoPro enables rapid exploration and direct deployment from PyTorch models to bare-metal C code. We demonstrate the versatility of our framework on both the BitFusion accelerator and SIMD-extended RISC-V processors, achieving up to 40\% of latency reduction with less than 3\% of accuracy drop.
Yuchen Huang, Xijiang Ying, Zhenhua Ma +14cs.RO cs.AI
Reasoning-enhanced large language models have achieved remarkable improvements in planning tasks, yet their deployment in embodied systems remains impractical due to prohibitive inference delays-often exceeding minutes per planning instance. The fundamental bottleneck stems from the serial nature of existing paradigms: models must complete all reasoning before any action execution, leaving execution time windows entirely unexploited. We introduce PACE (Planning with Adaptive Cognitive Effort), a framework that enables interleaved reasoning and execution through two key innovations: an Interleaved Think-Act architecture that pipelines cognitive processing with action execution, and a Dynamic Budget Allocator that adapts reasoning token budgets to available execution time windows. On the Robotouille benchmark using Qwen3-8B-AWQ, PACE achieves a 10% success rate-representing a 67% improvement over the ReAct+Think baseline-while delivering 6.9 times acceleration in thinking time compared to unconstrained reasoning. The framework hides 66.8% of thinking time within execution windows, demonstrating that strategic cognitive effort allocation can simultaneously improve both planning quality and time efficiency. These results provide evidence that time-aware architectural innovations enable reasoning models to operate in latency-sensitive embodied domains where they were previously impractical.
Can large language models generate not just correct, but fast hardware? This paper investigates the question in financial FPGA design, where 5-10 nanoseconds of latency determines competitive advantage and designs iterate continuously as protocols, strategies, and regulations evolve. FinHardBench, a benchmark of 33 financial computing tasks, is presented together with three experiments that mirror the real-world FPGA iteration cycle: generating new modules from specifications, tuning system-level configurations across a 6-stage trading pipeline, and adapting existing modules to specification changes. Evaluation of six LLMs on 1530+ experiment rounds yields three findings: (1) models achieve 19-61% functional correctness with timing degradation up to 13.7$\times$ on specific tasks; (2) in system-level design space exploration, top LLMs converge to the optimal configuration with higher reliability than random search, simulated annealing, and Bayesian optimization baselines (5/5 seeds vs. 0-4/5 at the same 24-round budget); (3) strategy-level specification changes remain unsolved for most models. Across the six models, generation and DSE rankings overlap moderately: the strongest code generator is not the fastest architecture optimizer, and the weakest code generator (MiniMax M2.7) still reaches the system optimum on 4 of 5 seeds. On the tasks in FinHardBench, difficulty tracks training data pattern availability more closely than abstraction level. FinHardBench is released as an open-source benchmark.
Large language model agents increasingly act through stateful tools, yet model generation and environment execution remain serialized at every step. As decoding accelerates, tool execution becomes a growing bottleneck. Existing action- or observation-only speculation leaves much of this latency exposed: value is concentrated in a few slow calls, some outcomes emerge only through execution, and longer lookahead typically requires an increasingly unlikely chain of action predictions. We present AOSpec, a lossless framework that co-speculates actions and observations across the full agent-environment loop. Expected Value Decoding (EVD) directs observation speculation toward outcomes with the greatest expected latency benefit, optimizing expected time hidden rather than hit rate. For outcomes only execution can reveal, AOSpec launches latency-critical target actions in isolated forks that contain their effects, while Joint Action-State Verification (JASV) verifies both the action and its origin state against committed execution before reuse. JASV recasts long-horizon action dependency from full-chain prediction into target action-state verification, breaking the lookahead--accuracy tradeoff and unlocking long-range overlap without sacrificing serial semantics. Across Terminal-Bench serving settings spanning four harnesses, five actor models, and five serving speeds, AOSpec outperforms every practical baseline, reducing mean end-to-end latency by 11.8-32.5% and p99 latency by up to 42.8%. Its gains increase as decoding accelerates, and its observation model transfers from Terminal-Bench to SWE-bench Verified without retraining.
Speculative decoding mitigates the latency of sequential generation in autoregressive Large Language Models (LLMs) by interleaving draft generation with target verification. However, existing parallel drafting backends often suffer from rapid accuracy degradation over long horizons, leading to high rejection rates during verification and suboptimal wall-clock speedups. We observe that drafting errors are not uniformly distributed but typically stem from localized high-uncertainty tokens that destabilize downstream generation trajectories. Motivated by this token error pattern, we propose CURE, a budget-aware dynamic repair tree designed to repair errors at uncertainty focal points without incurring prohibitive tree-verification overheads. Specifically, our method uses predictive confidence margins to dynamically locate candidate error tokens within a block-parallel draft, expands bounded repair paths only at these fragile nodes, and employs a novel repair resynchronization mechanism to realign draft states post-verification. Evaluations on code-generation benchmarks (HumanEval, MBPP, and LiveCodeBench-lite) and mathematical reasoning benchmark (GSM8K) demonstrate that CURE increases the average accepted length by 4.2-7.5% over parallel baselines without repair, translating to an end-to-end speedup of $2.66-3.49\times$ over target-only decoding. Furthermore, we provide a plug-and-play repair module compatible with standard parallel drafting frameworks. We also characterize the trade-off between draft compute and verification efficiency.
Computer-use agents often fail on transient GUI events because they produce the correct action only after the relevant window has already closed. We identify the main cause as expensive autoregressive decoding on the decision-time critical path. We propose Adaptive Anticipatory Policy Trees (AAPT), which eliminates this delay without modifying the underlying model. During idle screen periods, the same frozen multimodal model constructs a bounded conditional policy tree with observable guards, pre-authorized actions, and branch-specific deadlines. The tree is sized to cover the model's own decoding latency. When an event occurs, a lightweight observer matches change-gated frames to a prepared branch and immediately executes the corresponding action without generating new text. In paired trials with pre-registered endpoints and exact McNemar tests, AAPT improves the success rate from 0.50 to 0.79 within a contested decision window ($p=1.8\times10^{-3}$), while producing no incorrect actions. Both open-loop and predict-and-replan baselines achieve zero success because they still decode during execution. A preparation-time sweep shows that the gain emerges where the latency-based tree-sizing rule predicts, and ablations reveal three key requirements: fast observer decoding, valid tree planning, and accurate branch routing. A pre-registered oracle probe rejects our initial hypothesis and instead points to branch routing as the causal bottleneck. We further reproduce the effect on an independent general-purpose multimodal model over 126 paired trials ($p=4.9\times10^{-13}$). On an external benchmark, AAPT matches the overall performance of a reactive baseline, although the two methods exhibit complementary strengths. Together, these results suggest that AAPT performs best when candidate actions can be enumerated in advance, whereas reactive execution remains stronger when they cannot.
Large language model agents often spend substantial wall-clock time waiting for tool call results. Tool-call speculation can hide this latency by predicting and pre-executing an agent's next tool call if the prediction matches the agent's eventual tool call, but existing speculators are typically separate draft models or cached traces that are poorly aligned with the deployed agent's own behavior. We identify this speculator-agent gap and show that the target agent itself is a strong next-call speculator. This points to a simpler design: unifying the agent and speculator within the same model. In this paper, we introduce the self-speculating agent, a single model that both solves tasks in agent mode and predicts its next tool call from partial trajectories in speculator mode, fully reusing prefix KV cache. To enable this dual-mode agent without degrading performance, we propose a joint agent-speculator reinforcement learning method, which derives speculation targets from the agent's own rollouts and alternates agent and speculator updates. Across agentic search QA and conversational tool-use agentic tasks, our method improves average next tool-call Hit@1 from 44.1 to 61.2 for Qwen3-4B and from 48.9 to 66.3 for Qwen3.5-4B, while preserving agent task success.
Yihui Zhang, Tianyu Wo, Jinghao Wang +7cs.DC cs.AI cs.LG cs.PF
As LLM agents increasingly rely on the Model Context Protocol (MCP) to invoke isolated external sandboxes, disaggregated sandbox deployment introduces a fundamental tension between resource utilization and interactive tail latency. Persistent long-lived sandbox reservations incur excessive memory overhead at scale, while lazy on-demand instantiation generates severe cold-start penalties that degrade response performance under multi-tenant, multi-turn agent workloads. To resolve this dilemma, we present SpecBox, a runtime built around speculative sandbox preallocation tailored for dynamic LLM agent execution pipelines. At its core, SpecBox implements keyword matching and streaming semantic embedding to enable intent-driven sandbox prewarming, which identifies pending tool execution demands mid-LLM token generation and fully overlaps sandbox bootstrapping with model inference. To extend prewarming windows across sequential agent steps, the framework leverages context-aware stochastic prefetching atop a sandbox dependency graph to probabilistically forecast future sandbox switches ahead of execution. We complement these speculative mechanisms with two orthogonal optimizations: a semantic result cache that prunes redundant repeated sandbox invocations, and a dedicated out-of-band shared-memory transport plane that bypasses conventional network serialization to deliver zero-copy artifact transfers. Evaluated on high-concurrency multi-turn agent traces, our prototype demonstrates that SpecBox cuts P99 end-to-end latency by up to $2.9\times$ relative to the on-demand sandbox baseline, while slashing peak memory consumption by $45.9\%$ compared to permanently reserved sandbox deployments.
Mobile devices increasingly rely on real-time NPU inference for camera and perception workloads. Under low-voltage conditions, however, a single inference can induce an instantaneous voltage droop in the power-delivery network, causing the power management integrated circuit to invoke dynamic voltage and frequency scaling (DVFS) and increase latency. We present a measurement study of this effect on a commercial smartphone. We show that aggressive operator fusion in a mobile NPU compiler can create monolithic superlayers whose concentrated execution produces large peak-current bursts. These bursts shift the DVFS-onset voltage upward and reduce the low-voltage operating margin. We further evaluate a practical black-box mitigation: a measurement-guided, pre-compilation graph rewrite that inserts barriers at selected peak-to-average power ratio hot spots to prevent harmful superlayer merging in the vendor NPU compiler. On Snapdragon 8 Gen 3 with MobileNetV4 at 768 x 768 resolution on ImageNet-1k, this method reduces peak current from 3.12 A to 1.94 A with 3.76% latency overhead, preserves stable latency deeper into the low-voltage regime, and shifts the inferred DVFS margin by approximately 173 mV.
On-device LLM inference faces a trilemma of response latency, limited hardware resources and user privacy. Full cloud inference delivers strong computing power but exposes user prompts and dialogue data, while standalone on-device inference is unfeasible for most consumer and embedded edge devices. This paper presents a privacy-centric edge-cloud collaborative LLM inference framework built on endpoint-authenticated KV cache. Local endpoints handle input preprocessing, embedding computation, adaptive feature optimization, KV cache authentication, speculative decoding and low-dimensional model head calculation, while the cloud conducts authenticated decoder inference, KV cache management, token verification and high-dimensional vocabulary projection. Endpoints fuse partial outputs, apply language-adaptive masking and sample target tokens. All transmitted data and truncated logits are quantized and AES-GCM encrypted for privacy, with core lightweight modules, draft parameters and cache access policies kept local to avoid leakage. The framework supports heterogeneous devices including CPU-only, GPU-equipped and embedded devices via optimized streaming, batching and quantized ONNX deployment. Evaluations demonstrate that the framework reduces per-token latency by up to 46.1\% and downlink payloads by up to 67.4\% over baseline split inference, retaining comparable performance to full cloud inference.
Diffusion models have become the central backbone for modern image, video, and audio generation, but their efficient service remains a challenge. Unlike autoregressive decoding, diffusion inference repeatedly updates high-dimensional spatial or temporal latents over many denoising steps. This all-region execution pattern makes generation latency high and limits serving throughput. Existing multi-GPU parallelization methods can reduce per-step computation, but often introduce substantial activation exchange overhead, causing communication to offset or even outweigh the benefits of parallel execution. This paper presents FlashDiff, a diffusion serving system that improves inference efficiency through adaptive regional execution and scheduling. FlashDiff is based on the observation that diffusion refinement is not uniform across latent regions or denoising steps: different regions often stabilize at different rates, while neighboring steps exhibit strong temporal correlation. FlashDiff leverages these properties to selectively execute only regions that require further refinement and to reallocate the resulting compute slack across concurrent serving requests. FlashDiff consists of three mechanisms. First, it decomposes the latent representation into coherent execution regions using early-stage attention signals, preserving semantic structure while exposing fine-grained parallelism. Second, it uses a lightweight runtime controller to estimate region activity and bypass low-impact updates when further refinement is unlikely to affect output quality. Third, it applies an affinity-aware online scheduler that co-locates dependent regions, balances residual load across GPUs, and reuses reclaimed compute capacity to improve serving efficiency. Across real-world image, video, and audio workloads, FlashDiff reduces end-to-end serving latency by 30-97% and improves throughput by 1.2-2.2x.
Mikhail Kiselev, Aleksandr Marukhin, Ivan Snegirev +3cs.HC cs.AI cs.CV
UltraArUco is a lightweight multilingual library and framework for low latency, realtime marker-based tracking in mobile augmented reality. Unlike standard OpenCV-based implementations, UltraArUco introduces an optimized multilingual wrapper that reduces per-frame latency in six times, while maintaining high accuracy. Distributed Wi-Fi architecture provides portability, connects a mobile device (camera input) with a PC-based visual application, enabling responsive interactions. The framework is validated through an interactive piano simulation, where static ArUco markers on keys enable occlusion based note triggering, and hand-mounted markers provide spatial gesture recognition. UltraArUco's system requirements make it highly suitable for resource-constrained mobile AR applications, demonstrating a viable AR music application without specialized equipment.
Kalle Kujanpää, Ning Liu, Shahnawaz Alam +4cs.CL cs.LG cs.SE
Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace this inference-time coding loop with an agentic tool-making pipeline that compiles repeated SOP steps into validated, versioned tools before deployment. The tool-maker grounds synthesis in the live environment as it collects execution traces, observes backend schemas and values, generates candidate tools, and repairs them against labeled cases. At runtime, the production agent calls these tools directly and falls back to code generation only when needed. We deploy the approach in a Fulfillment Center alarm-triage system, where an agent diagnoses alarms against a 44-node SOP over heterogeneous metric backends. In production, tool calls reduce p50 latency by 42%. On 1,500 historical alarms, they reduce end-to-end error rate by up to 53% by suppressing run-to-run variance in repeated steps. Because tools return compact structured verdicts, they also enable a simpler direct-call architecture, reducing p50 latency by a further 62% in a controlled ablation. Versioned tools also improve auditability and expose specification gaps and upstream data drift. Our results show that self-evolving agents can make industrial LLM systems faster, more reliable, and easier to operate.
Tingkai Liu, Muralidhar Andoorveedu, Sanjoy Das +2cs.DC cs.LG
The evolution of compute infrastructure has transformed multi-GPU systems into tightly integrated shared-memory structures. However, current software still mostly treats these coherent interconnects simply as high-speed networks. Simultaneously, the demand for serving Large Language Models under latency constraints has shifted GPU workload optimization from being throughput-driven to latency-bound, necessitating latency-oriented scaling methods beyond Tensor Parallelism (TP). Thus, we introduce CTA-pipelining, an execution paradigm designed to exploit shared-memory multi-GPU systems. As a latency-oriented spatial scaling technique, CTA-pipelining leverages dependencies at the Cooperative Thread Array level, enabling concurrent execution of dependent kernels across GPUs. We demonstrate its capability using CUTLASS, cuBLAS, and NCCL libraries on 8-GPU H200 and B200 systems. Results show on 2-layer GEMM, representing the MLP operation, CTA-pipelining reduces latency by up to 31.8% compared to micro-batching, and 29.6% compared to TP. It can also be combined with TP as an orthogonal scaling dimension to further push the latency boundary.
Real-time decoding is a major bottleneck in scaling quantum error correction (QEC) from noisy intermediate-scale quantum (NISQ) devices to fault-tolerant quantum computing. We present an adaptive confidence-gated decoding framework for the rotated surface code that treats decoding as a two-stage inference problem. A lightweight feed-forward neural network performs fast-path decoding for the majority of syndrome measurements, while only low-confidence predictions are escalated to a minimum-weight perfect matching (MWPM) refinement stage. We benchmark the framework on rotated surface codes with distances $d \in \{3,5,7,9,11\}$ under circuit-level depolarising noise using the Stim stabiliser simulator. The evaluation characterises logical accuracy, confidence-controlled accuracy-latency trade-offs, decoding throughput, per-shot latency, and decoding-graph resource scaling. Routing only 3.3%-6.2% of syndromes to the refinement stage improves logical accuracy from 99.21% for the neural-only baseline to 99.81% at a confidence threshold of 0.95 while incurring only a bounded increase in average decoding cost. Neural-decoder throughput saturates near $4.6 \times 10^{5}$ samples s$^{-1}$ at batch size 512 on commodity CPU hardware, indicating that the neural fast path is not the dominant throughput bottleneck beyond code distance $d=7$. We release the complete benchmarking pipeline, trained models, raw benchmark data, and source code, and explicitly distinguish the experimentally validated contributions from the broader hardware-aware QEC co-design roadmap, including hardware-constrained code discovery, GPU-accelerated inference, and multi-noise optimisation, which remain directions for future work.
Language agents run a loop - observe, reason, act - but the memory they reason over sits outside it: a store queried at most once per turn. We study the regime where memory moves inside the loop, read and written on every step. The obstacle has always been latency: networked stores answer in tens to hundreds of milliseconds, and in-loop retrieval can inflate end-to-end latency by up to 83x when retrieval is expensive. Prior work manages that cost rather than questioning it: serving-layer scheduling hides it, "memory-first" designs ration retrieval to once per turn. We argue latency is a property of where the store lives, not the in-loop pattern: an in-process store answers in ~100us, three orders of magnitude below the network regime, and at that speed the per-step tax collapses. By the extended-mind thesis's parity principle, a store fast enough to be constantly and directly available becomes extended working memory, not a tool the agent merely consults. The premise is causal: holding a fixed per-turn memory-latency budget and varying only the store's answer speed, redundant actions rise monotonically with latency - 0.0 of 12 at in-process speed, 7.2 of 12 at a 110ms cloud round trip (gpt-5-nano, gpt-5-mini; exact permutation p=0.0079). We demonstrate the regime end-to-end: across four GPT-5-class models under a bounded window, recall improves from 0/5 to 3.6-4.8/5 with in-loop memory, store ops at p50 80-165us - though an instructed restate-every-reply baseline also solves it perfectly, at a token cost that grows with the working set. The store never lost a fact in any run (244 of 244 writes kept); every miss traces to the agent's read policy, not the store. Our measurements also relocate the bottleneck: the dominant per-step cost is embedding (~200-400ms over the network); pairing the in-process store with a small local embedder returns the complete operation to a measured ~40us.
LLM agents are becoming a common interface for research, coding, and question answering, yet their Thought-Action-Observation loop is often serial: the model reasons, emits a tool call, then idles the GPU until the result returns. This wait consumes 16-37% of wall time in our workloads and 35-61% in prior reports. Speculative tool execution can hide this wait, but existing systems need auxiliary predictors, historical traces, or static workflow graphs, leaving a gap for training-free, day-one deployment. We observe that the model can be its own predictor: a probe forked at the start of generation predicts Qwen3-32B's upcoming tool name with 74.6-99.6% accuracy across five benchmarks. We present SPORK (Self-sPeculative fORKing), a training-free controller that dispatches the speculated tool call early, overlapping its execution with the remaining chain-of-thought decode. A cost model captures when speculation breaks even, and each component improves one of its terms: a prefix-cache fork cuts probe cost, a confidence gate filters mispredictions, and partial-token accept turns rejected probes into speculative-decoding drafts. On acceptance, the tool result is ready when reasoning ends; on rejection, SPORK falls back to serial execution with no correctness penalty. On real-tool benchmarks, SPORK cuts Qwen3-32B's GAIA P95 by 18% (131.9 to 108.1 s); the mechanism holds across model sizes from 4B to 32B and across dense and mixture-of-experts models, with task accuracy within 1 pp of baseline or better wherever measured. SPORK deploys as a thin controller over standard completion APIs (no retraining, no auxiliary models, no offline traces) and is orthogonal to token-level speculative decoding. SPORK is open source at https://github.com/baihuajun24/spork.
Disaggregated LLM serving runs prefill and decode on separate GPU pools to keep the two phases from interfering. In practice, this creates a new asymmetry: under bursty, heavy-tailed workloads prefill nodes saturate while decode nodes have compute underutilized, and on a production-style A100 cluster with 2 prefill and 2 decode nodes (2P2D), we find that prefill execution accounts for only 2-23% of P95 Time-to-First-Token (TTFT). Queuing and inter-node GPU-GPU KV-cache transfer account for the rest. We present a proactive prefill-deflecting scheduler that lets decode nodes serve prefill phase of requests as chunked-prefill steps interleaved with their in-flight decode batches. For each queued request, we estimate the TTFT it would see on the prefill node, and on every decode node, search for the largest chunk schedule that keeps in-flight decodes within their Time-Between-Tokens (TBT) SLO and deflect when the decode path helps tail latency. Because the prefill phase of deflected requests runs in place on the decode node, the inter-node KV transfer is eliminated. Implemented on vLLM and evaluated on production-style traces with DeepSeek-V2-Lite, our approach reduces P95 TTFT by upto 81% and raises SLO attainment by upto 79% over state-of-the-art disaggregated schedulers, at sub-millisecond per-request routing cost.
João Henrique Inacio de Souza, Mattia Merluzzi, Mateus P. Mota +2cs.IT cs.AI
Communication systems designed for reliable data reconstruction, rather than task-oriented communication, typically rely on separate source and channel coding and incur high latency under limited spectrum availability and fading channels. To address this, we propose a transmission framework with opportunistic spectrum access, in which the transmitter sends discrete latent representations learned via a vector-quantized variational autoencoder (VQ-VAE) over idle licensed channels using standard digital modulation. The AI-powered receiver is still able to reconstruct task-related information from the heavily compressed data. We develop a cross-layer latency model that accounts for compression, block errors, retransmissions, and stochastic channel access. Results on latency-accuracy trade-offs show that the proposed scheme achieves at least 79- and 3.3-fold latency reductions with only 5.7% and 2.4% drops in classification accuracy compared to benchmarks using conventional source and channel coding. The framework enables low-latency communication and reliable task execution even under limited spectrum availability and challenging channel conditions.
Vo Phi Son, Van-Dinh Nguyen, Ngoc Hung Nguyen +2cs.LG
Load imbalance across edge and cloud layers degrades latency performance in hierarchical edge-cloud computing (HECC) systems under dynamic task arrivals and heterogeneous resources, leading to severe queuing delays and inefficient resource utilization. To address this challenge, we study a joint service placement, computational delegation, and power control (JSCP) problem to minimize the average end-to-end (e2e) latency. The resulting JSCP problem is a mixed-integer nonconvex and NP-hard optimization problem due to the strong coupling between discrete and continuous variables. To enable tractable optimization and stable system adaptation, we exploit the inherent difference in decision dynamics and decompose the problem into long-term system configuration and short-term resource allocation subproblems. Based on this formulation, we propose a two-timescale multi-layer deep reinforcement learning framework with a latent action space (2T-MDRL-LA) to jointly optimize service placement, user association, computational delegation, task offloading, and user transmit power. A latent action representation based on a variational autoencoder is introduced to efficiently compress the high-dimensional combinatorial action space. Simulation results demonstrate that the proposed framework effectively adapts to dynamic network conditions and achieves near-optimal performance compared to branch-and-bound solutions. It achieves up to a 20.8% reduction in average e2e latency and a 13% improvement in resource utilization over the scheme without the computational delegation, while converging approximately 50% faster than conventional proximal policy optimization.