Focus: A Streaming Concentration Architecture for Efficient Vision-Language Models

Chiyue Wei; Cong Guo; Junyao Zhang; Haoxuan Shan; Yifan Xu; Ziyue Zhang; Yudong Liu; Qinsi Wang; Changchun Zhou; Hai "Helen" Li; Yiran Chen

arXiv · 2512.14661

Focus: A Streaming Concentration Architecture for Efficient Vision-Language Models

Chiyue Wei·Cong Guo·Junyao Zhang·Haoxuan Shan·Yifan Xu·Ziyue Zhang·Yudong Liu·Qinsi Wang·Changchun Zhou·Hai "Helen" Li·Yiran Chen

View original source ↗Read source document ↗Export metadata ↓

Abstract

Vision-Language Models (VLMs) have demonstrated strong performance on tasks such as video captioning and visual question answering. However, their growing scale and video-level inputs lead to significant computational and memory overhead, posing challenges for real-time deployment on hardware accelerators. While prior work attempts to reduce redundancy via token pruning or merging, these methods typically operate at coarse granularity and incur high runtime overhead due to global token-level operations. In this study, we propose Focus, a Streaming Concentration Architecture that efficiently accelerates VLM inference through progressive, fine-grained redundancy elimination. Focus introduces a multilevel concentration paradigm that hierarchically compresses vision-language inputs at three levels: (1) semantic-guided token pruning based on textual prompts, (2) spatial-temporal block-level concentration using localized comparisons, and (3) vector-level redundancy removal via motion-aware matching. All concentration steps are tightly co-designed with the architecture to support streaming-friendly, on-chip execution. Focus leverages GEMM tiling, convolution-style layout, and cross-modal attention to minimize off-chip access while enabling high throughput. Implemented as a modular unit within a systolic-array accelerator, Focus achieves a 2.4x speedup and 3.3x reduction in energy, significantly outperforming state-of-the-art accelerators in both performance and energy efficiency. Full-stack implementation of Focus is open-sourced at https://github.com/dubcyfor3/Focus.

Explore related subjects

cs.AR

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Chiyue Wei, Cong Guo, Junyao Zhang, Haoxuan Shan, Yifan Xu, Ziyue Zhang, Yudong Liu, Qinsi Wang, Changchun Zhou, Hai "Helen" Li, Yiran Chen. 2025-12-16. Focus: A Streaming Concentration Architecture for Efficient Vision-Language Models. https://arxiv.org/abs/2512.14661

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

HLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation

Application-specific FPGA accelerators offer substantial performance and energy-efficiency gains across many application domains, but developing them is costly, often requiring months of specialized effort. Even with high-level synthesis (HLS), designers still need extensive hardware expertise to build high-performance accelerators. Although large language models (LLMs) have demonstrated strong software-generation capabilities, even frontier models lack the hardware intuition and procedural knowledge needed to reliably translate baseline C/C++ programs into high-performance HLS designs: they struggle to identify effective architectures, follow the optimization processes used by HLS experts, and apply hardware transformations consistently across diverse kernels. We present HLSmith, an expert-guided framework for translating C/C++ programs into optimized HLS accelerators. HLSmith combines three components: an HLS optimization expertise library that encodes guarded transformation recipes, their applicability and prerequisite conditions, and unsafe cases to avoid; a staged, feedback-driven orchestration flow modeled on expert HLS development practice that guides agents through synthesis, bottleneck analysis, and optimization; and a tool-grounded model-adaptation pipeline that converts optimization trajectories from commercial frontier models into training data for fine-tuning open-weight LLMs. We evaluate HLSmith on PolyBench against ChatHLS, a leading prior agent-orchestration framework for HLS accelerator development. HLSmith achieves a geometric mean speedup of 4.24x over ChatHLS while producing functionally correct designs, in both software and RTL simulation, for every benchmark, compared with ChatHLS's 57% valid-design rate. It further reaches speedups of up to 252x and 138x with commercial frontier models and open-weight models, respectively.

cs.AR↗

arXiv2026

Accelerating the Mitigation of LLM Inference Nondeterminism Across GPU Architectures

Large language model (LLM) outputs are expected to be reproducible under greedy decoding, yet in practice the same model, prompt, and software stack produce different outputs on different GPUs. The root cause is floating-point non-associativity combined with hardware-dependent kernel selection. Inference frameworks select different matrix-multiplication kernels on each architecture, with different parallel reduction orders and unspecified tensor-core arithmetic, and the resulting rounding differences can flip output tokens. Existing solutions have imperfect cross-architecture reproducibility and incur a significant performance penalty. We present a solution employing a set of fixed-configuration fused-upcast GEMM kernels that load 16-bit weights from memory, upcast them to FP32 in registers, and accumulate with IEEE-754 arithmetic in a reduction order that is a pure function of the problem shape and is therefore independent of the device, its SM count, or kernel scheduling. By fixing the floating-point reduction order as a function of problem shape alone, every GPU runs the same operation sequence, so cross-architecture reproducibility of the linear layers reduces to correct IEEE-754 arithmetic rather than to rounding differences staying below a tie-flip threshold. We confirm our solution's linear-layer outputs are bitwise identical across NVIDIA Ampere, Ada, and Hopper GPUs, while running $1.17$ to $3.1\times$ faster end-to-end than the state-of-the-art solution and cutting weight-memory traffic in half.

cs.AR↗

arXiv2026

Decoupling Logical Masks from GPU Execution for Dynamic Block-Sparse Attention

Attention computation makes inference expensive in video diffusion transformers (vDiTs), which generate videos through iterative denoising. Block-sparse attention (BSA) reduces this cost by computing only blocks selected by a logical mask, which specifies attention interactions to compute. However, coupling logical block geometry to execution choices limits adaptation to varying masks and graphics processing units (GPUs), while runtime kernel specialization can incur preparation overhead that outweighs execution time savings. We present Tessera, a specialized runtime for dynamic BSA that decouples logical masks from GPU execution while preserving specified attention interactions. Its physical mapping layer retains, combines, or subdivides logical attention blocks into physical tiles suited to different attention mask shapes and GPU architectures. Its task organization layer groups and schedules tiles within GPU tasks to reuse data, expose parallelism, and overlap data movement with computation. Finally, profile-guided regime selection enables low- overhead execution plan selection through a lookup table constructed from offline profiling. We implement Tessera with specialized CUDA kernels supporting four NVIDIA GPU generations. Evaluated on 2,315 real attention masks and industrial video diffusion models, Tessera achieves up to 6.79x BSA request speedup over baseline systems in the evaluated video diffusion models.

cs.AR↗