Noticias
Erasing Conceptual Knowledge from Language Models
arXiv:2410.02760v3 Announce Type: replace Abstract: In this work, we introduce Erasure of Language Memory (ELM)...
Epistemic Diversity and Knowledge Collapse in Large Language Models
arXiv:2510.04226v4 Announce Type: replace Abstract: Large language models (LLMs) tend to generate lexically, semantically, and...
EPFL Researchers Unveil FG2 at CVPR: A New AI Model That Slashes Localization Errors by 28% for Autonomous Vehicles in GPS-Denied Environments
Navigating the dense urban canyons of cities like San Francisco or New York can be...
EPFL Researchers Introduce MEMOIR: A Scalable Framework for Lifelong Model Editing in LLMs
The Challenge of Updating LLM Knowledge LLMs have shown outstanding performance for various tasks through...
Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations
arXiv:2509.05060v1 Announce Type: new Abstract: We introduce Entropy2Vec, a novel framework for deriving cross-lingual language...
Entropy-Guided Reasoning Compression
arXiv:2511.14258v1 Announce Type: new Abstract: Large reasoning models have demonstrated remarkable performance on complex reasoning...
Entrepreneurs in Nairobi make the case for going solar
__________________________THE PLACENairobi, Kenya Most of Kenya’s power grid runs on renewables. But with 25% of...
Enterprise alert: PostgreSQL just became the database you can’t ignore for AI applications
Analysts provide insight on what the latest acquisition of a PostgreSQL database vendor means for...
Enterprise AI Without GPU Burn: Salesforce’s xGen-small Optimizes for Context, Cost, and Privacy
Language processing in enterprise environments faces critical challenges as business workflows increasingly depend on synthesising...
Enigmata’s Multi-Stage and Mix-Training Reinforcement Learning Recipe Drives Breakthrough Performance in LLM Puzzle Reasoning
Large Reasoning Models (LRMs), trained from LLMs using reinforcement learning (RL), demonstrated great performance in...
Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS
arXiv:2507.05557v1 Announce Type: new Abstract: Test-time scaling has emerged as a promising paradigm in language...
Enhancing Robustness of Autoregressive Language Models against Orthographic Attacks via Pixel-based Approach
arXiv:2508.21206v1 Announce Type: new Abstract: Autoregressive language models are vulnerable to orthographic attacks, where input...
