每日文章

Light field (LF) image denoising is challenging due to the high-dimensional structure of LF data. While noise is independent across sub-aperture images, scene content exhibits strong cross-view correlations. We introduce VSANet, a view-aware sparse attention network for LF denoising. Specifically, we propose a view-aware sparse attention (VSA) block that represents the 4D LF feature map as a unified spatial-angular token space and performs cross-view aggregation via locality-sensitive hashing-based sparse attention. This enables global feature interactions with linear complexity, effectively exploiting LF correlations across views and spatial locations. In addition, we design a feature refinement (FR) block to emphasize informative features in spatial, angular, and epipolar subspaces. The VSA and FR blocks are integrated within a sequential attention refinement module, forming the core of VSANet. Experiments demonstrate VSANet outperforms stateof-the-art LF denoising methods.

The integration of visual evidence has significantly enhanced the capabilities of large multimodal models. However, this integration predominantly relies on generating discrete outputs (etc., code or box coordinates) to invoke external tools, a process that introduces rigid dependencies and substantial latency. To overcome these limitations, we propose {EVA} (LatEnt Visual StAtes), a novel framework that natively generates continuous latent visual representations. These internal representations manifest as an adaptive sequence of Latent_slot tokens, serving as intermediate visual thoughts during the reasoning process. These Latent_slot tokens are then trained end-to-end with the discrete text tokens. This co-optimization, notably, causes extreme policy deviation in the 'transition window' following the Latent_slot tokens. We develop D-GSPO (Decouple-GSPO) to target this root cause by decoupling the optimization of latent and discrete components. To support SFT, we construct EVA-230K, a high-quality text-image interleaved CoT dataset encompassing a diverse range of real-world scenes, documents, charts and OCR tasks. Extensive experiments across multiple benchmarks confirm that EVA achieves significant performance gains while enhancing inference efficiency.

Quadratic unconstrained binary optimization (QUBO)-based quantum computed tomography (CT) casts reconstruction as a binary quadratic problem for quantum annealing and hybrid quantum--classical solvers. For grayscale CT, however, image encoding is constrained by the binary-variable budget: fixed global bit-plane encodings increase QUBO size and coupling complexity as gray-level precision improves, whereas low-bit encodings introduce quantization error. We propose a QUBO-based grayscale CT reconstruction framework that combines dynamic interval encoding with prior-balanced optimization. Each refinement round encodes active pixels only within local gray-level intervals around the current estimate, and a boundary-hit-guided update rule adaptively switches between search expansion and local refinement. To improve optimization stability, the method balances projection-domain data consistency and an edge-preserving quadratic prior before forming the final QUBO. Sparse-view and limited-angle fan-beam CT experiments show that the proposed method recovers structures and gray-level distributions more faithfully than the evaluated analytic, iterative, variational, and representation-based baselines. Expressivity analysis and ablation studies further indicate that the improvement mainly arises from effective gray-level representation through dynamic local encoding and more stable data-fidelity--prior coupling. Experiments on the D-Wave hybrid binary quadratic model (BQM) solver further demonstrate that the formulation is executable on a hardware-backed hybrid quantum--classical backend.

Memory stranding wastes 25-35% of installed DRAM in production cloud clusters. Memory pooling over CXL and RDMA offers a remedy, but neither technology alone suffices: CXL provides low-latency, load/store-transparent access limited to a pod, while RDMA provides cluster-wide reach at higher latency with software overhead. A hierarchical architecture combining both tiers is the practical path forward, yet remains unexplored for MicroVM-based serverless computing, where snapshot restore latency is the dominant cold-start bottleneck. We present Aquifer, the first system to serve MicroVM snapshots from a hierarchical CXL+RDMA memory pool. A characterization of snapshot images reveals that the vast majority of pages are either zero or cold, enabling a hotness-based snapshot format that eliminates zero pages and places only the hot working set in the CXL pool while storing cold pages in the RDMA pool. Sharing these snapshots across hosts on CXL 2.0 multi-headed devices, which lack hardware cache coherence, requires Aquifer's ownership-based coherence protocol to ensure correctness. Finally, Aquifer uses a copy-based page serving mechanism pre-installs hot pages from CXL memory before MicroVM resume and demand-pages cold pages asynchronously from RDMA. On emulated CXL+RDMA hardware, Aquifer achieves a 2.2x geometric-mean speedup in end-to-end invocation time over Firecracker and 1.1x over the next best alternative.

Adapting a streaming speech recognition model to a new language requires choosing between two plausible warm starts: a multilingual (ML) encoder or an English-only (EN) encoder. The common intuition is that the multilingual encoder should help most at low data, but it is unclear how long that advantage persists, whether tight streaming latency amplifies it, and whether it survives deployment quantization. We answer these questions with a controlled sweep of a 0.6 B-parameter cache-aware FastConformer transducer across eight European languages, up to five target-language data scales (100 h to 2500 h), three streaming tiers plus offline decoding, and up to four public test sets. The main result is that multilingual initialization is a data-limited advantage, not a latency-limited one. On FLEURS at 160 ms, the mean EN-ML word error rate (WER) gap falls from +4.21 percentage points (pp) at 100 h to +0.20 pp at 2500 h; a power-law fit summarizes this decay, with each doubling of target-language data roughly halving the remaining advantage. Across the three streaming tiers, the across-language mean EN-ML gap is approximately stable at each scale from 100 to 1000 h, and is near zero by 2500 h. Finally, 4-bit weight-only encoder quantization at the matched 560 ms streaming tier reduces the encoder footprint by about 3x, with an average FLEURS WER increase of about 0.5 pp. The resulting guideline is simple: use multilingual initialization in low-data regimes, treat the choice as effectively irrelevant at large data, and make latency and quantization decisions independently.

Emerging LLM services increasingly host many sparse MoE models, yet most models receive sparse requests and remain cold. This creates a GPU memory problem: model weights are stable and model-determined, while KV-cache is transient and demand-determined. Because cold models rarely reach peak KV-cache demand at the same time, reserving worst-case KV capacity per model wastes memory; a shared KV-cache pool can instead provision aggregate active demand. However, KV-cache sharing is not sufficient when weights and KV-cache remain in a monolithic GPU memory pool. Static weights compete with dynamic KV-cache, and KV-head-limited attention under cold, low-concurrency traffic exposes only a fraction of replicated KV capacity, leading to low GPU memory utilization and weak long-context support. We present CrossPool, a serving engine for cold MoE models that separates FFN weights and KV-cache into two GPU memory pools: a weights pool that consolidates FFN weights across cold models, and a KV-cache pool that dynamically serves active requests while keeping attention local to KV-cache. CrossPool combines a KV-cache planner and virtualizer, a layer-wise pipeline scheduler that hides hidden-state transfers, and persistent kernels with control lowering to reduce CPU-GPU control overhead. With efficient GPU memory pooling, CrossPool underpins bursty long-context requests and outperforms the state-of-the-art kvcached-based multi-LLM serving system, reducing P99 TBT by up to \(10.4\times\).

Existing low-bit KV-cache quantizers often treat each cached key as a flat vector. Under RoPE, however, a key's contribution to a future attention logit decomposes into a position-dependent sum over two-dimensional frequency blocks. This makes key-cache quantization a block-wise bit-allocation problem: high-energy RoPE blocks are more sensitive to quantization error and should receive more bits. We introduce Block-GTQ, a RoPE-aware bit allocator for key-cache quantization built on TurboQuant-MSE(TQ-MSE). For each layer and KV head, Block-GTQ computes a label-free energy score for each RoPE block and greedily allocates integer bit widths by marginal gain. Under matched K/V bit budgets, Block-GTQ better preserves RoPE query-key logits on a ten-model diagnostic panel, cutting per-layer MAE by 32-80% at 2 and 3 b/dim K-only quantization and winning all 367/367 layer comparisons against uniform TQ-MSE. These fidelity gains translate to stronger downstream long-context retrieval, understanding, and reasoning. At K2V2 on Llama-3.1-8B-Instruct, Block-GTQ raises the six-task NIAH average from 70.6 to 97.4, and the LongBench-EN average from 36.87 to 53.31. On AIME 2024/2025 with DeepSeek-R1-Distill-Qwen-7B, without an fp16 recent-key buffer, Block-GTQ at K3V2 scores 51.7/37.5, close to fp16's 54.2/37.9, whereas uniform TQ-MSE collapses to 0.0/0.0. We further implement a packed-cache serving path. On a single H800 GPU with Qwen2.5-3B-Instruct, packed K3V3 achieves 3.24x KV-cache compression with fp16-comparable quality, runs 1.34x faster than fp16 FlashAttention2 at 128K context, reduces peak memory from 56.31 GB to 19.85 GB, and remains feasible at 256K and 512K where fp16 OOMs. Code is available at https://github.com/JIA-Lab-research/blockgtq.

Efficient genomic k-mer indexing depends on approximate membership query (AMQ) structures that must deliver high throughput, low false-positive rates (FPR), and modest memory footprints. The Super Bloom filter (SBF) is attractive for this scenario because minimizer-guided sharding and the Findere scheme exploit the redundancy of overlapping k-mers. However, those same features cause high per-k-mer compute cost, severe register pressure, and irregular memory accesses, which hinder an effective GPU implementation. We present cuSBF, an open-source, header-only CUDA library that implements SBF for sequence-native workloads. cuSBF's design merges sectorized shards, cooperative shared-memory tiling, warp-level shard sharing, and segmented warp reductions, turning super-k-mer locality into scalable GPU parallelism. Across real genomic workloads on RTX PRO 6000 Blackwell and GH200 systems, cuSBF achieves the highest throughput among all evaluated sequence-capable baselines. On the RTX PRO 6000, it surpasses the cuCollections blocked Bloom filter baseline by up to 9.1x for insertion and 7.7x for query, while reaching up to 92x and 234x speedups over the multi-threaded CPU Super Bloom reference implementation. It also outperforms GPU-based dynamic AMQs (Cuckoo, Two-Choice, Quotient filters) by 1.5-3400x depending on workload characteristics. A parameter sweep identifies (s = 28, m = 16, H = 4) as Pareto-optimal for k = 31, yielding significantly lower FPR than cuCollections at matched memory budgets. Crucially, cuSBF's architecture-aware design sustains 85% streaming multiprocessor utilization even for out-of-cache filters - proving that sequence locality, not raw bandwidth, is the key to GPU-accelerated genomic indexing.

Progress in deep learning is, at scale, more a matter of systems engineering than of modelling: the behaviour of a model in training (its throughput, its memory footprint, and the numerical fidelity of the result) is determined less by the architecture itself than by how that architecture is expressed on the hardware. To achieve absolute control over this hardware expression while abstracting away systems complexity to make modelling seamless and eliminating the need for repetitive orchestration logic, BluTrain was architected from first principles as a robust, lightweight, and architecture-general training framework in standard C++ and the core CUDA programming model. Every layer is implemented natively: a typed tensor module with reverse-mode autograd, a linear-algebra library, a caching allocator, a multi-mode distributed-execution module, and an MLIR-based deep-learning compiler. In formal evaluations training a 124M-parameter GPT-2 baseline in FP32 on an 8-GPU 6000 Ada system, BluTrain outperforms industry-standard baselines in both throughput (sustaining an average of 407K tokens/s versus PyTorch's 395K tokens/s) and memory efficiency (achieving up to a 22% footprint reduction), while strictly preserving numerical fidelity and converging to a marginally lower final validation loss. With every layer explicitly open to native tuning, the performance ceiling is the framework's own to raise.

Interactive music and live performance relies on real-time human expression, but modern generative music AI remains largely absent from this domain due to its prohibitive inference latency and offline rendering paradigm. To provide pioneer musicians with a novel medium for interactive composition, we should fundamentally change these static models into dynamic, playable instruments. In this paper, we propose a framework that bridges this gap. To achieve the low latency required for live interaction without sacrificing structural coherence, we formulate distillation within a streaming autoregressive latent space. Our approach gets rid of the need for expensive paired audio-latent datasets by utilizing prompt-only inputs to synthesize teacher-guided, chunk-wise trajectories on the fly. Because live instruments require high acoustic fidelity, we introduce music-aware consistency objectives, which combine latent, spectral, and temporal-difference losses, to preserve crucial qualities like timbre, transients, and rhythmic stability during accelerated single-step streaming generation. Implemented via parameter-efficient adaptation, our distillation reduces generation steps to achieve a low real-time factor. Crucially, by operating as a continuous autoregressive stream, the system can seamlessly assimilate dynamic human inputs on the fly, allowing users to instantly steer the musical trajectory without interrupting the audio flow. Ultimately, this work recontextualizes generative text-to-music models not as passive prompt-and-wait systems, but as responsive instruments, opening new frontiers for live human-AI musical co-creation.

Non-autoregressive generation offers a powerful paradigm for iterative refinement, allowing models to recursively critique, erase and regenerate arbitrary subsets of tokens. However, existing non-autoregressive models fail to realize this potential. Masked Diffusion Models (MDMs) suffer from factorization error, causing sample quality to collapse when generating multiple tokens simultaneously. Flow Map Language Models (FMLMs) circumvent this bottleneck via joint sequence transport for excellent few-step generation, but sacrifice the inference-time flexibility of MDMs. We introduce FMLM+, a framework that bridges this gap by equipping FMLM with masking-style noise schedules. While generating the full sequence in a single step, FMLM+ simultaneously scores the global consistency of each token a posteriori. We leverage this to introduce Posterior Refinement, a novel inference-time refinement strategy that enables the model to adaptively self-correct its outputs, matching the performance of discrete baselines with 32x fewer NFEs. Across diverse benchmarks, we demonstrate that FMLM+ with Posterior Refinement improves the speed--quality tradeoff over both MDM and FMLM families, providing a scalable foundation for high-fidelity language modeling.

Generative models, particularly diffusion and score-based approaches, have recently achieved strong performance in speech enhancement, but their iterative sampling process limits real-time deployment. Flow Matching offers an efficient alternative by transporting noisy speech toward clean speech through an ordinary differential equation with few function evaluations. In this work, we propose a skip-free encoder-decoder backbone for flow-matching speech enhancement, guided by Latent Representation Alignment (LRA). Instead of relying on U-Net skip connections, which may transfer noise-correlated low-level features to the decoder, the proposed model aligns its bottleneck and decoder representations with clean latent features extracted from a frozen Descript Audio Codec encoder-decoder without quantization. This codec-aligned supervision promotes compact clean-speech representations while preserving efficient few-step inference. Experiments on WSJ0-CHiME3 and VoiceBank-DEMAND show improved PESQ and perceptual quality, especially on VoiceBank-DEMAND, using only five function evaluations.

Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware. Existing KV cache eviction methods typically apply heuristic token scoring over all heads in GQA-based LLMs. These methods ignore the different functionalities of attention heads, leading to the eviction of critical tokens and thus degrading the performance of LLMs. To address this issue, we propose CompressKV, a resource-efficient KV-cache compression framework for GQA-based LLMs. Instead of aggregating attention scores from all heads, CompressKV identifies Semantic Retrieval Heads (SRHs) that capture both the initial and final tokens of a prompt and semantically important mid-context evidence, and uses them to select tokens whose KV pairs should be retained. Furthermore, CompressKV allocates cache budgets across layers according to offline estimates of layer-wise eviction error. Experiments on LongBench and Needle-in-a-Haystack show that CompressKV consistently outperforms existing KV-cache eviction methods across memory budgets. Notably, it preserves over 97\% of full-cache performance using only 3\% of the KV cache on LongBench question-answering tasks and achieves 90\% accuracy with just 0.7\% KV storage on Needle-in-a-Haystack. These results demonstrate an improved resource--performance trade-off for long-context LLM inference. Our code is publicly available at: https://github.com/TUDa-HWAI/CompressKV

Reducing visual token redundancy is critical for accelerating Multimodal Large Language Models (MLLMs) without degrading cross-modal reasoning performance. Existing token pruning methods typically rely on single-layer signals, such as attention scores or token similarities, which overlook the cross-layer transformation of visual representations and may exhibit positional bias in multimodal token sequences. To address this limitation, we propose a training-free token pruning framework based on Cross-Layer Spectral Evolution (CLSE). Instead of measuring token importance from single-layer feature magnitudes, CLSE quantifies how token representations evolve across Transformer layers in the frequency domain. This evolution reflects the transition from high-frequency structural details to low-frequency semantic abstractions. We observe that tokens with stronger spectral redistribution across layers are more likely to be semantically active and should therefore be preserved. By modeling cross-layer token dynamics, CLSE provides a stable importance criterion that mitigates positional bias. Extensive experiments on both image and video benchmarks demonstrate that CLSE achieves a superior trade-off between efficiency and accuracy under aggressive token reduction. Across multiple MLLMs, CLSE reduces FLOPs, KV cache memory, and latency while maintaining competitive or improved performance.

Mobile apps frequently suffer from performance issues such as frame drops, overheating, and excessive power consumption. While developers optimize algorithms and debug code, a critical bottleneck often goes unnoticed: native libraries compiled with low optimization levels (O0/O1 instead of O2/O3). Because these libraries execute without functional errors, the resulting performance degradation remains hidden in production apps, affecting millions of users. We present \textsc{OptDetect}, a source-free framework that detects compiler optimization problems directly from app binaries without requiring source code or build metadata. \textsc{OptDetect} handles mixed optimization levels within a single binary through a pipeline of binary disassembly, chunk-level classification, and weighted score aggregation, achieving 93.0\% accuracy on controlled datasets and 81.9\% on real-world datasets. Applying \textsc{OptDetect} to 21,972 native libraries from 830 top-ranked Google Play apps, we find that 30.5\% of libraries use low optimization levels, affecting 91.7\% of apps. Through case studies on 12 production apps (6 commercial, 6 open-source), we demonstrate that fixing detected issues reduces CPU instructions by 10-63\% (median: 20.5\%) for commercial apps and 15-58\% (median: 32\%) for open-source apps, with performance complaints decreasing by a median of 42\% and ratings increasing by a median of 0.14 points. Further investigation reveals a previously overlooked root cause: widely-used third-party libraries are themselves distributed at low optimization levels, with 49.7\% of 1,073 libraries in a major repository exhibiting this problem. These findings highlight the need for automated detection tools and industry-wide optimization standards.

Mainstream Fast-Slow dual system vision-language-action models decouple a high-frequency action expert from a low-frequency vision-language model for efficiency, yet they face a fundamental frequency dilemma: large update gaps cause semantic drift from stale context, while small gaps erode the intended computational savings. Moreover, because the action expert receives only the VLM's final-layer representation at a single fixed frequency, rich intermediate features are discarded, limiting both information coupling and manipulation precision. Inspired by multi-timescale neural processing in the human brain, we introduce UniFS, a unified fast-to-slow architecture that resolves these challenges through three key designs. First, we stratify the VLM layers into groups with progressively decreasing update frequencies, enabling shallow layers to capture fast-changing dynamics while deeper layers cache stable semantic context. Second, a latent vector inversion mechanism re-routes the interaction order between multi-scale VLM features and the action expert, aligning fast-varying representations with fine-grained action decoding and slow-varying ones with coarse planning. Third, a multi-level supervision strategy enforces a coarse-to-fine learning hierarchy across temporal scales. Together, these designs enable richer cross-frequency information transfer within a single backbone, while the low-frequency pathways additionally preserve temporal context across steps. Experiments on LIBERO show that UniFS achieves state-of-the-art performance (98.3\% average success rate, a 2.5\% gain over VLA-Adapter baseline) while reducing average inference latency from 36.5~ms to 17.8~ms (2.1\(\times\) speedup). Real-robot experiments on a Franka platform further validate its practical applicability. Code is opensourced at https://github.com/linsun449/UniFS.

Hash-based data structures such as Bloom filters are widely used in network systems for tasks including caching, anomaly detection, and machine learning pipelines. They typically provide binary indications of whether an element belongs to a set of interest, e.g., the contents of a cache. When uncertainty arises due to hash collisions, a positive indication is returned to avoid false negatives. We argue that the certainty associated with such indications can itself be useful information. This work focuses on Counting Bloom Filters (CBFs), a Bloom-filter variant that maintains counters rather than bits. Besides supporting insertions and deletions, these counters provide additional information that can be used to estimate the certainty of positive membership indications. We show how this certainty signal can be exploited in architectures that combine Bloom Filters with machine learning (ML) models.

Long contexts have become standard in pretrained LLMs, yet they remain expensive to run: prefill compute grows quadratically with sequence length, and every decode step re-reads a key-value cache that grows linearly with it. Sparse attention cuts these costs by attending only to a relevant subset of past tokens, but selecting that subset is itself expensive. We present SpotAttention, a lightweight selector that attaches to a frozen pretrained transformer and learns by KL distillation to estimate its attention distribution. The selector picks the top-K keys each query attends to, and because its estimate is a calibrated distribution, a dual top-p rule reads the per-query, per-layer budget directly from it. Across Qwen3 (dense, 4B-32B) and Qwen3.5 (hybrid linear/full attention, 4B-9B), SpotAttention matches dense accuracy at contexts up to 128K tokens, eight times the training length. Decode at L=128K runs 3.9x faster than FlashAttention and 1.8x faster than Twilight, the strongest training-free baseline. Quantizing the selector's K-cache to INT4 or FP4 microscale shrinks it 3.5x at no accuracy cost.

Pre-trained Vision Foundation Models (VFMs) have become central to modern computer vision due to their powerful semantic representations and strong generalization ability. However, their patchified or pooled outputs are inherently low-resolution, limiting their effectiveness in tasks requiring fine-grained, pixel-level reasoning. Existing feature upsampling approaches either degrade semantic fidelity or rely on VFM-specific retraining and heavy architectures, hindering efficiency and scalability. To address these challenges, we propose RaysUp, an ultra-lightweight, task-agnostic, and VFM-agnostic feature upsampling framework that reconstructs high-resolution feature maps at arbitrary resolutions. Unlike conventional 2D interpolation or attention-based schemes, RaysUp lifts feature reconstruction into a geometry-aware ray domain. Specifically, we introduce a Spatially Decoupled Guidance Encoder for direction-aware guidance encoding, an Any-Resolution Cross-Attention mechanism for resolution-flexible reconstruction, and a novel Ray Positional Encoding (RayPE) that injects implicit 3D geometric priors via 6D Plucker ray coordinates. Finally, a Geometry-Aware Neighborhood Attention module further ensures content-adaptive bilateral aggregation while preserving geometric consistency. Extensive experiments across diverse dense prediction tasks demonstrate that RaysUp achieves state-of-the-art performance while using only 16% of the parameters of AnyUp and delivering approximately 7x faster inference. These results highlight a substantially improved accuracy-efficiency trade-off and establish RaysUp as a practical and scalable solution for universal feature upsampling. Code is available at https://github.com/MAP-RaysUp/RaysUp.

GPU Confidential Computing (GPU-CC) now preserves GPU-local performance: on NVIDIA B300, BF16 matmul runs at 0.998x of non-confidential performance. Yet LLM serving under Intel TDX plus GPU-CC still loses 13-27% of throughput, and KV-cache restore latency can more than double. This paper studies that gap on two Blackwell platforms, RTX Pro 6000 and B300 HGX, and identifies its dominant cause: the confidential VM-GPU bridge, not GPU compute. We find that GPU-CC turns host/device movement into a serialized, high-setup-cost channel. Secure copies do not gain CUDA-stream concurrency within a context, asynchronous transfers block at the runtime boundary, and small crossings pay a fixed toll. This violates the assumptions of modern inference runtimes, where DMA is expected to be cheap, concurrent, and asynchronous. In vLLM dense decode, the gap closes around 44x-slower small alloc-and-copy operations; targeted patches reject alternative explanations. A scheduling flag recovers 57% of the gap, while a worker-thread drain recovers up to 92% in qualified high-concurrency runs. The same bridge model explains a +131% KV-restore penalty and a 34x model-load slowdown. Blackwell also changes the confidential tenancy unit. We qualify confidential multi-GPU NVSwitch tenants on B300, including 510 GB/s NVLink P2P inside a CVM and concurrent isolated tenants, and identify the remaining fabric-attestation gap for production confidential AI platforms.