large language model
PulseAugur coverage of large language model — every cluster mentioning large language model across labs, papers, and developer communities, ranked by signal.
- instance of CatalyzeX 90%
- used by multi-agent system 80%
- authored by alphaXiv 70%
- used by alphaXiv 70%
- used by Gotit.pub 70%
- used by ScienceCast 70%
- used by speech recognition 70%
- uses multi-agent system 70%
- affiliated with multi-agent system 60%
- used by DagsHub 60%
- instance of multi-agent system 60%
- competes with speech recognition 50%
26 day(s) with sentiment data
-
Prompt engineering evolves from clever tricks to reliable AI systems
The era of relying on clever prompt engineering for large language models is fading, replaced by a more robust discipline of building dependable AI systems. While basic prompting is now accessible due to improved models…
-
New system HiLSVA blends human and AI for scientific visualization
Researchers have developed HiLSVA, a novel human-in-the-loop agentic system designed to enhance scientific visualization (SciVis) workflows. Unlike previous autonomous systems, HiLSVA emphasizes collaboration between hu…
-
RAG Chunking Methods: A Guide to Improving LLM Accuracy
Chunking is a critical preprocessing step for Retrieval-Augmented Generation (RAG) systems, which aim to improve the factual accuracy of Large Language Models (LLMs) by providing them with external knowledge. The effect…
-
New framework merges LLMs and physics for realistic motion synthesis
Researchers have developed a new framework called In-Context Model Predictive Generation (ICMPG) to improve the synthesis of human motion from textual descriptions. This approach combines the semantic understanding of l…
-
LLM framework AIGP boosts e-commerce pricing performance
Researchers have developed AIGP, a new framework that uses Large Language Models (LLMs) for e-commerce pricing. This system aims to overcome the limitations of traditional dynamic pricing models by incorporating domain …
-
PersistentKV optimizes LLM serving on commodity GPUs with new scheduling techniques
A new paper introduces PersistentKV, a system designed to optimize the serving of large language models (LLMs) with long contexts on commodity GPUs. PersistentKV employs page-aware decode scheduling and a native block-t…
-
Speech LLMs enhanced by translation-based encoder pre-training
A new research paper proposes using speech translation to bridge the gap between speech encoders and large language models (LLMs) in Speech LLMs. The paper argues that current architectures have a structural misalignmen…
-
DriveStack-VLA enhances driving models with spatial intelligence and self-critique
Researchers have introduced DriveStack-VLA, a novel framework designed to enhance the spatial intelligence of vision-language-action driving models. This system leverages a large vision-language model backbone and incor…
-
LLM agents simulate social perception uncertainty in classrooms
Researchers have developed a novel framework using Large Language Model (LLM) agents to simulate uncertainty in social perception within classroom settings. These agents construct individualized subjective graphs to man…
-
LLM-MINE framework extracts Alzheimer's phenotypes from clinical notes
Researchers have developed LLM-MINE, a framework utilizing large language models to extract phenotypes related to Alzheimer's Disease and Related Dementias (ADRD) from clinical notes. This method aims to improve early d…
-
LLM-ACES framework uses large language models to discover dynamical systems
Researchers have developed LLM-ACES, a novel framework that uses large language models to guide the discovery of dynamical systems by searching for Ordinary Differential Equations (ODEs). This closed-loop system optimiz…
-
LLMs discover quantum error-correcting codes via structured evolution
Researchers have developed a novel framework called structured concept evolution (SCE) that leverages large language models (LLMs) to discover quantum low-density parity-check (qLDPC) codes. This method pairs an LLM wit…
-
ByteDance's Doubao 2.1 Pro model shows advanced AI coding capabilities
ByteDance's new Doubao 2.1 Pro model has reportedly surpassed Anthropic's benchmark models in AI coding capabilities, with some metrics matching high-end international versions. This advancement is seen as a significant…
-
New VieSpeaker Dataset Enhances Vietnamese Speaker Recognition Without Visual Cues · 3 sources tracked
Researchers have introduced VieSpeaker, a new large-scale dataset for Vietnamese speaker recognition that does not rely on visual cues. This dataset was constructed using a novel pipeline that leverages textual metadata…
-
DREAM paper proposes autoregressive modeling for dense retrieval training
Researchers have developed DREAM (Dense Retrieval Embeddings via Autoregressive Modeling), a novel method for training dense retrieval systems. Unlike traditional methods that rely on costly labeled data, DREAM leverage…
-
Event Tensor abstraction unifies dynamic megakernel compilation for LLMs
Researchers have introduced Event Tensor, a novel compiler abstraction designed to unify the compilation of dynamic megakernels for modern GPU workloads. This abstraction addresses limitations in current megakernel tech…
-
New framework INSPIRE improves e-commerce sponsored product retrieval
Researchers have developed INSPIRE, a novel framework for intent-aware neural sponsored product retrieval in e-commerce, specifically targeting the food and beverage categories. This system aims to improve the alignment…
-
New framework proposed for complex, goal-oriented dialogue systems
Researchers have introduced the Goal-Oriented Dialogue Runtime (GODR), a conceptual design pattern for managing complex, multi-domain conversations. GODR treats user objectives, task frames, and lifecycle states as firs…
-
Research: Intrinsic Self-Correction in LLMs is Task-Dependent
A new research paper explores the effectiveness of intrinsic self-correction (SC) in large language models, moving beyond general assessments to a task-sensitive analysis. The study investigates how SC functions through…
-
LLM-aided A* search optimizes pathfinding in complex networks
Researchers have developed a novel approach to optimize pathfinding in complex network graphs by integrating Large Language Models (LLMs) with the A* search algorithm. This LLM-aided A* method generates intermediate way…