ニュース
Beyond GPT architecture: Why Google’s Diffusion approach could reshape LLM deployment
Gemini Diffusion is also useful for tasks such as refactoring code, adding new features to...
Best AI Apps for Managing Your Day (Without the Stress)
Let’s face it — managing our everyday lives can feel like a in no way-ending to-do listing...
BentoML Released llm-optimizer: An Open-Source AI Tool for Benchmarking and Optimizing LLM Inference
BentoML has recently released llm-optimizer, an open-source framework designed to streamline the benchmarking and performance...
Benchmarking the Pedagogical Knowledge of Large Language Models
arXiv:2506.18710v3 Announce Type: replace Abstract: Benchmarks like Massive Multitask Language Understanding (MMLU) have played a...
Benchmarking Chinese Commonsense Reasoning with a Multi-hop Reasoning Perspective
arXiv:2510.08800v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated advanced reasoning capabilities...
Batch-Max: Higher LLM Throughput using Larger Batch Sizes and KV Cache Compression
arXiv:2412.05693v3 Announce Type: replace Abstract: Several works have developed eviction policies to remove key-value (KV)...
Base Models Beat Aligned Models at Randomness and Creativity
arXiv:2505.00047v2 Announce Type: replace Abstract: Alignment has quickly become a default ingredient in LLM development...
Aya Vision: Advancing the Frontier of Multilingual Multimodality
arXiv:2505.08751v1 Announce Type: new Abstract: Building multimodal language models is fundamentally challenging: it requires aligning...
Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition
arXiv:2509.07555v1 Announce Type: new Abstract: In a rapidly evolving world where information updates swiftly, knowledge...
AutoSpec: An Agentic Framework for Automatically Drafting Patent Specification
arXiv:2509.19640v1 Announce Type: new Abstract: Patents play a critical role in driving technological innovation by...
AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists
arXiv:2506.08140v1 Announce Type: cross Abstract: Despite long-standing efforts in accelerating scientific discovery with AI, building...
AutoRev: Multi-Modal Graph Retrieval for Automated Peer-Review Generation
arXiv:2505.14376v2 Announce Type: replace Abstract: Enhancing the quality and efficiency of academic publishing is critical...
