ข่าว
Making AI operational in constrained public sector environments
The AI boom has hit across industries, and public sector organizations are facing pressure to...
Make It Hard to Hear, Easy to Learn: Long-Form Bengali ASR and Speaker Diarization via Extreme Augmentation and Perfect Alignment
arXiv:2602.23070v1 Announce Type: cross Abstract: Although Automatic Speech Recognition (ASR) in Bengali has seen significant...
MacroBench: A Novel Testbed for Web Automation Scripts via Large Language Models
arXiv:2510.04363v2 Announce Type: replace-cross Abstract: We introduce MacroBench, a code-first benchmark that evaluates whether LLMs...
MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations
arXiv:2512.13154v1 Announce Type: cross Abstract: Conversational agents often encounter ambiguous user requests, requiring an effective...
M$^3$FinMeeting: A Multilingual, Multi-Sector, and Multi-Task Financial Meeting Understanding Evaluation Dataset
arXiv:2506.02510v1 Announce Type: new Abstract: Recent breakthroughs in large language models (LLMs) have led to...
LPFQA: A Long-Tail Professional Forum-based Benchmark for LLM Evaluation
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
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
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
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
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
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
arXiv:2507.18263v1 Announce Type: new Abstract: Direct speech translation (ST) has garnered increasing attention nowadays, yet...
