Nachrichten
Vocabulary Customization for Efficient Domain-Specific LLM Deployment
arXiv:2509.26124v1 Announce Type: new Abstract: When using an LLM to process text outside the training...
VLQA: The First Comprehensive, Large, and High-Quality Vietnamese Dataset for Legal Question Answering
arXiv:2507.19995v1 Announce Type: new Abstract: The advent of large language models (LLMs) has led to...
vLLM vs TensorRT-LLM vs HF TGI vs LMDeploy, A Deep Technical Comparison for Production LLM Inference
Production LLM serving is now a systems problem, not a generate() loop. For real workloads...
VL-Cogito: Advancing Multimodal Reasoning with Progressive Curriculum Reinforcement Learning
Multimodal reasoning, where models integrate and interpret information from multiple sources such as text, images...
ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding
arXiv:2509.15235v4 Announce Type: replace-cross Abstract: Speculative decoding is a widely adopted technique for accelerating inference...
Visa launches ‘Intelligent Commerce’ platform, letting AI agents swipe your card—safely, it says
Visa launches Intelligent Commerce platform enabling AI assistants to make secure purchases with your credit...
Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics
arXiv:2405.19988v3 Announce Type: replace-cross Abstract: Natural language is often the easiest and most convenient modality...
VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents
arXiv:2506.21582v1 Announce Type: new Abstract: Text analytics has traditionally required specialized knowledge in Natural Language...
VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents
arXiv:2509.07553v3 Announce Type: replace Abstract: With the rapid progress of multimodal large language models, operating...
Verdict: A Library for Scaling Judge-Time Compute
arXiv:2502.18018v2 Announce Type: replace Abstract: The use of LLMs as automated judges (“LLM-as-a-judge”) is now...
Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators
arXiv:2602.22647v1 Announce Type: cross Abstract: Generative retrieval has emerged as a powerful paradigm for LLM-based...
