RTL
PulseAugur coverage of RTL — every cluster mentioning RTL across labs, papers, and developer communities, ranked by signal.
- 2026-10-13 regulatory RTL is under investigation for potentially violating the EU AI Regulation by airing AI-altered content without disclosure. source
- 2026-09-12 product_launch German broadcaster RTL has integrated AI-generated audio content into its courtroom drama "Ulrich Wetzel das Strafgericht." source
4 day(s) with sentiment data
-
AI era demands precise specifications for system design and verification
In the emerging AI era, the quality of system specifications is paramount, as AI models directly translate natural language prompts into technical outputs like RTL and test benches. The effectiveness of these AI-driven …
-
LLM agents design RISC-V CPUs with FPGA evaluation, speeding up development
Researchers have developed a new environment for designing RISC-V CPUs using LLM agents and FPGA-in-the-loop evaluation. This approach significantly speeds up the design and decision-making process compared to tradition…
-
Dutch Minister Calls for Stricter AI Oversight in Higher Education
Dutch Minister Letschert is proposing stricter oversight of higher education programs, particularly concerning the final level of qualifications awarded. She is concerned that the increasing use of AI by students for es…
-
New framework automates chip design verification with AI
Researchers have developed a new agentic framework called Back-to-the-Future (BTTF) to address the manual nature of chip design verification. BTTF processes large simulation dumps into a SQLite database, enabling natura…
-
German broadcaster RTL faces EU AI Regulation probe for undisclosed AI-altered shows
RTL is facing scrutiny for re-using episodes of "Das Strafgericht" (The Criminal Court) by altering them with generative AI and presenting them as new content. This practice, which occurred without any disclosure to vie…
-
RTL integrates AI-generated audio into courtroom drama
German broadcaster RTL is incorporating AI-generated content into its courtroom drama "Ulrich Wetzel das Strafgericht." Specifically, parts of the show will feature AI-generated audio content. This marks a significant s…
-
New framework uses formal consensus to verify LLM-generated RTL designs
Researchers have developed a new framework called NoTB to assess the functional correctness of RTL designs generated by large language models (LLMs). This oracle-free approach leverages formal consensus by applying Sequ…
-
New HINT layer improves LLM-driven RTL code generation
Researchers have developed HINT, a new intermediate representation layer designed to improve the generation of Register-Transfer Level (RTL) code using Large Language Models (LLMs). HINT explicitly defines microarchitec…
-
HLSmith framework boosts C/C++ to HLS translation with expert guidance · 2 sources tracked
Researchers have developed HLSmith, a framework designed to improve the translation of C/C++ code into high-performance hardware accelerators using High-Level Synthesis (HLS). The system incorporates an expertise librar…
-
New RTLCurator method improves LLM training data for RTL code generation
Researchers have developed RTLCurator, a novel method for curating datasets used to train large language models for Register-Transfer Level (RTL) code generation. Existing datasets often suffer from a lack of correctnes…
-
New agentic framework GoGoTB automates IC verification using LLMs · 2 sources tracked
Researchers have developed GoGoTB, an agentic framework designed to automate functional verification in integrated circuit engineering. This new system utilizes large language models (LLMs) to address challenges like in…
-
AI models tricked by invisible characters into executing harmful commands
Researchers have discovered that large language models like GPT-4.1 mini and GPT-4o can be tricked into executing harmful instructions by subtly altering the input. By interleaving invisible characters or using homoglyp…
-
New Luxembourgish SQA system uses TTS, new expressive speech corpus released
Researchers have developed LuxSQA, a system for spoken question answering in Luxembourgish, a low-resource language. The system utilizes text-to-speech (TTS) technology to generate synthetic spoken questions, augmenting…
-
New expressive speech corpus released for Luxembourgish language
Researchers have introduced LuxEmo, a new 21-hour corpus of expressive speech for the Luxembourgish language, addressing the underrepresentation of low-resource languages in speech technology. The corpus, derived from R…
-
LLMs and formal methods combine for verifiable hardware design
Researchers have developed a new framework for generating hardware designs using large language models (LLMs) combined with formal methods. This approach aims to mitigate the risk of LLM-induced errors in chip design by…
-
AUTOGATE uses LLMs for automated RTL power optimization
Researchers have developed AUTOGATE, a novel framework for optimizing RTL (Register-Transfer Level) designs to reduce dynamic power consumption through automated clock gating. This system utilizes a co-design approach c…
-
New LLM tools enhance hardware design and data generation
Researchers are developing new methods to improve the use of large language models (LLMs) for hardware design, specifically for generating Register Transfer Level (RTL) code. One approach, LLM4RTL, uses a tool-assisted …
-
New LLM-driven system HierSVA aids hardware formal verification
Researchers have introduced HierSVA, a comprehensive system designed to enhance the formal verification of hardware designs using Large Language Models (LLMs). This system includes a pipeline for generating SystemVerilo…
-
New Framework Enhances LLM-Driven Hardware Design with Structured Testbenches
Researchers have developed STG, a Structured Testbench Generation framework designed to overcome limitations in LLM-driven hardware design. Unlike current methods that treat testbench generation as unconstrained code sy…
-
New framework steers LLMs to generate more accurate RTL code
Researchers have developed CASS-RTL, a novel framework designed to improve the accuracy of large language models (LLMs) in generating hardware description language (HDL) code, specifically Register-Transfer Level (RTL).…