Related papers: SAGE Celer 2.6 Technical Card

At the confluence of 6G, deep learning (DL), and natural language processing (NLP), DL-enabled text semantic communication (SemCom) has emerged as a 6G enabler since it minimizes bandwidth consumption, transmission delay, and power usage.…

Decoding speech-related information from non-invasive MEG is a key step toward scalable brain-computer interfaces. We present compact Conformer-based decoders on the LibriBrain 2025 PNPL benchmark for two core tasks: Speech Detection and…

Realizing personalized intelligence faces a core dilemma: sending user history to centralized large language models raises privacy concerns, while on-device small language models lack the reasoning capacity required for high-quality…

The escalating demand to migrate legacy software across different Instruction Set Architectures (ISAs) has driven the development of assembly-to-assembly translators to map between their respective assembly languages. However, the…

Modern transformer-based deep neural networks present unique technical challenges for effective acceleration in real-world applications. Apart from the vast amount of linear operations needed due to their sizes, modern transformer models…

Deep search agents, which aim to answer complex questions requiring reasoning across multiple documents, can significantly speed up the information-seeking process. Collecting human annotations for this application is prohibitively…

We propose RaDeR, a set of reasoning-based dense retrieval models trained with data derived from mathematical problem solving using large language models (LLMs). Our method leverages retrieval-augmented reasoning trajectories of an LLM and…

Domain specific accelerators present new challenges and opportunities for code generation onto novel instruction sets, communication fabrics, and memory architectures. In this paper we introduce an intermediate representation (IR) which…

Modern Large Language Models achieve impressive reasoning capabilities with long Chain of Thoughts, but they incur substantial computational cost during inference, and this motivates techniques to improve the performance-cost ratio. Among…

Generating clinical reports that summarize abnormal patterns, diagnostic findings, and clinical interpretations from long-term EEG recordings remains labor-intensive. We present CELM, the first clinical EEG-to-Language foundation model…

We introduce SigLIP 2, a family of new multilingual vision-language encoders that build on the success of the original SigLIP. In this second iteration, we extend the original image-text training objective with several prior, independently…

In today's rapidly evolving field of electronic design automation (EDA), the complexity of hardware designs is increasing, necessitating more sophisticated automation solutions. High-level synthesis (HLS), as a pivotal solution, automates…

Large language models excel at complex tasks by breaking down problems into structured reasoning steps. However, reasoning traces often extend beyond reaching a correct answer, causing wasted computation, reduced readability, and…

In this report, we present the third technical report on the development of slow-thinking models as part of the STILL project. As the technical pathway becomes clearer, scaling RL training has become a central technique for implementing…

Background: Short-read aligners have recently gained a lot of speed by exploiting the massive parallelism of GPU. An uprising alternative to GPU is Intel MIC; supercomputers like Tianhe-2, currently top of TOP500, is built with 48,000 MIC…

Speculative decoding (SD) is a widely used approach for accelerating decode-heavy LLM inference workloads. While online inference workloads are highly dynamic, existing SD systems are rigid and take a coarse-grained approach to SD…

We present Seedream 3.0, a high-performance Chinese-English bilingual image generation foundation model. We develop several technical improvements to address existing challenges in Seedream 2.0, including alignment with complicated prompts,…

Scaling language models improves performance but comes with significant computational costs. This paper proposes UL2R, a method that substantially improves existing language models and their scaling curves with a relatively tiny amount of…

Retrieval-augmented generation (RAG) is a framework enabling large language models (LLMs) to enhance their accuracy and reduce hallucinations by integrating external knowledge bases. In this paper, we introduce a hybrid RAG system enhanced…

In this work, we propose a realistic semantic network called seq2seq-SC, designed to be compatible with 5G NR and capable of working with generalized text datasets using a pre-trained language model. The goal is to achieve unprecedented…