LPFQA: A Long-Tail Professional Forum-based Benchmark for LLM Evaluation
1月 9, 2026admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2511.06346v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) perform well on standard reasoning and...
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
11月 10, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2510.03222v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has propelled Large Language...
Loss Landscape Degeneracy and Stagewise Development in Transformers
8月 4, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2402.02364v3 Announce Type: replace-cross Abstract: Deep learning involves navigating a high-dimensional loss landscape over the...
Los Angeles is finally going underground
4月 22, 2026admin NUAI,Committee,ニュース,Uncategorized(0)Los Angeles deserves its reputation as the quintessential car city—the rhythms of its 2,200 square...
LookAhead Tuning: Safer Language Models via Partial Answer Previews
12月 22, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2503.19041v4 Announce Type: replace Abstract: Fine-tuning enables large language models (LLMs) to adapt to specific...
LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating
7月 16, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2412.18424v3 Announce Type: replace-cross Abstract: Large vision language models (LVLMs) have improved the document understanding...
Locate-and-Focus: Enhancing Terminology Translation in Speech Language Models
7月 25, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2507.18263v1 Announce Type: new Abstract: Direct speech translation (ST) has garnered increasing attention nowadays, yet...
Localmax dynamics for attention in transformers and its asymptotic behavior
9月 22, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2509.15958v1 Announce Type: new Abstract: We introduce a new discrete-time attention model, termed the localmax...
Localized LoRA: A Structured Low-Rank Approximation for Efficient Fine-Tuning
9月 25, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2506.00236v2 Announce Type: replace-cross Abstract: Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, offer compact and...
