Related papers: Single-Thread JPEG Decoder Benchmarks Mis-Evaluate…

With the rapid advances of powerful multimodal models such as GPT-4o, Nano Banana, and Seedream 4.0 in Image Editing, the performance gap between closed-source and open-source models is widening, primarily due to the scarcity of…

We introduce VisualQuest, a novel dataset designed to rigorously evaluate multimodal large language models (MLLMs) on abstract visual reasoning tasks that require the integration of symbolic, cultural, and linguistic knowledge. Unlike…

Identifying and addressing performance anti-patterns in machine learning (ML) models is critical for efficient training and inference, but it typically demands deep expertise spanning system infrastructure, ML models and kernel development.…

In this paper, we propose an efficient and generalizable framework based on deep convolutional neural network (CNN) for multi-source remote sensing data joint classification. While recent methods are mostly based on multi-stream…

Modern SoC datapaths include deeply pipelined, domain-specific accelerators, but their RTL implementation and verification are still mostly done by hand. While large language models (LLMs) exhibit advanced code-generation abilities for…

With Nvidia's release of the Grace Superchip, all three big semiconductor companies in HPC (AMD, Intel, Nvidia) are currently competing in the race for the best CPU. In this work we analyze the performance of these state-of-the-art CPUs and…

Multimodal retrieval still leans on embedding-based models like CLIP for fast vector search over pre-computed image embeddings. Yet, unlike text retrieval, where joint-encoder rerankers are standard, comparable vision-language rerankers are…

We explore different approaches to integrating a simple convolutional neural network (CNN) with the Lucene search engine in a multi-stage ranking architecture. Our models are trained using the PyTorch deep learning toolkit, which is…

Code generation benchmarks such as HumanEval are widely adopted to evaluate LLMs' capabilities. However, after consolidating the latest 24 benchmarks, we noticed three significant imbalances. First, imbalanced programming language. 95.8% of…

Multimodal Large Language Models (MLLMs) are increasingly applied in real-world scenarios where user-provided images are often imperfect, requiring active image manipulations such as cropping, editing, or enhancement to uncover salient…

In an unpaired setting, lacking sufficient content constraints for image-to-image translation (I2I) tasks, GAN-based approaches are usually prone to model collapse. Current solutions can be divided into two categories, reconstruction-based…

Verifying computational processes in decentralized networks poses a fundamental challenge, particularly for Graphics Processing Unit (GPU) computations. Our investigation reveals significant limitations in existing approaches: exact…

WebGPU's security-focused design imposes per-operation validation that compounds across the many small dispatches in neural network inference, yet the true cost of this overhead is poorly characterized. We present a systematic…

Exams are a fundamental test of expert-level intelligence and require integrated understanding, reasoning, and generation. Existing exam-style benchmarks mainly focus on understanding and reasoning tasks, and current generation benchmarks…

The joint source-channel coding (JSCC) framework leverages deep learning to learn from data the best codes for source and channel coding. When the output signal, rather than being binary, is directly mapped onto the IQ domain…

The advent of modern cloud services along with the huge volume of data produced on a daily basis, have set the demand for fast and efficient data processing. This demand is common among numerous application domains, such as deep learning,…

JPEG is a popular image compression method widely used by individuals, data center, cloud storage and network filesystems. However, most recent progress on image compression mainly focuses on uncompressed images while ignoring trillions of…

Currently, there is a high demand for neural network-based image compression codecs. These codecs employ non-linear transforms to create compact bit representations and facilitate faster coding speeds on devices compared to the hand-crafted…

Fast, reliable decoders are pivotal components for enabling fault-tolerant quantum computation (FTQC). Neural network decoders like AlphaQubit have demonstrated potential, achieving higher accuracy than traditional human-designed decoding…

Visual text compression (VTC) promises efficient long-context processing by rendering text into an image and re-encoding it with a vision-language model, often producing $3$--$20\times$ fewer decoder tokens than subword tokenization. Yet…