Notizie
Tomato, Tomahto, Tomate: Do Multilingual Language Models Understand Based on Subword-Level Semantic Concepts?
arXiv:2411.04530v2 Announce Type: replace Abstract: Human understanding of text depends on general semantic concepts of...
TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs
arXiv:2510.15545v1 Announce Type: new Abstract: Accelerating the inference of large language models (LLMs) has been...
TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability
arXiv:2507.19419v1 Announce Type: new Abstract: Understanding the relationship between training data and model behavior during...
Tokenization, Fusion and Decoupling: Bridging the Granularity Mismatch Between Large Language Models and Knowledge Graphs
arXiv:2602.22698v1 Announce Type: new Abstract: Leveraging Large Language Models (LLMs) for Knowledge Graph Completion (KGC)...
Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning
arXiv:2508.20697v1 Announce Type: cross Abstract: As large language models (LLMs) continue to grow in capability...
Together AI’s ATLAS adaptive speculator delivers 400% inference speedup by learning from workloads in real-time
Enterprises expanding AI deployments are hitting an invisible performance wall. The culprit? Static speculators that...
To Retrieve or To Think? An Agentic Approach for Context Evolution
arXiv:2601.08747v1 Announce Type: new Abstract: Current context augmentation methods, such as retrieval-augmented generation, are essential...
Time Magazine appears to accidentally publish embargoed story confirming new Anthropic model
Someone also appears to have published a full scrape of the Time article online on...
Tilde Research Introduces Aurora: A Leverage-Aware Optimizer That Fixes a Hidden Neuron Death Problem in Muon
Researchers at Tilde Research have released Aurora, a new optimizer for training neural networks that...
Tilde AI Releases TildeOpen LLM: An Open-Source Large Language Model with Over 30 Billion Parameters and Support Most European Languages
Latvian language-tech firm Tilde has released TildeOpen LLM, an open-source foundational large language model (LLM)...
TII Releases Falcon Perception: A 0.6B-Parameter Early-Fusion Transformer for Open-Vocabulary Grounding and Segmentation from Natural Language Prompts
In the current landscape of computer vision, the standard operating procedure involves a modular ‘Lego-brick’...
Three things you should know about permafrost
How much do you know about permafrost? Maybe, like me, you’ve been aware that this...
