Noticias
Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models
arXiv:2503.22879v3 Announce Type: replace-cross Abstract: State Space Models (SSMs) are emerging as a compelling alternative...
QFFT, Question-Free Fine-Tuning for Adaptive Reasoning
arXiv:2506.12860v1 Announce Type: new Abstract: Recent advancements in Long Chain-of-Thought (CoT) reasoning models have improved...
QE4PE: Word-level Quality Estimation for Human Post-Editing
arXiv:2503.03044v2 Announce Type: replace Abstract: Word-level quality estimation (QE) methods aim to detect erroneous spans...
PyLate: Flexible Training and Retrieval for Late Interaction Models
arXiv:2508.03555v1 Announce Type: cross Abstract: Neural ranking has become a cornerstone of modern information retrieval...
Puzzle Corner Archives
July/August 25Guest edited by Edward Faulkner ’03 May/June 25Guest edited by Frank Rubin ’62 March/April...
Putnam-AXIOM: A Functional and Static Benchmark
arXiv:2508.08292v1 Announce Type: new Abstract: Current mathematical reasoning benchmarks for large language models (LLMs) are...
Putin says organ transplants could grant immortality. Not quite.
This week I’m writing from Manchester, where I’ve been attending a conference on aging. Wednesday was...
ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs
arXiv:2502.00258v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated exceptional performance in natural...
ProtoReasoning: Prototypes as the Foundation for Generalizable Reasoning in LLMs
arXiv:2506.15211v1 Announce Type: new Abstract: Recent advances in Large Reasoning Models (LRMs) trained with Long...
Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents
arXiv:2502.18509v2 Announce Type: replace-cross Abstract: Conversational agents are increasingly woven into individuals’ personal lives, yet...
Pronunciation-Lexicon Free Training for Phoneme-based Crosslingual ASR via Joint Stochastic Approximation
arXiv:2507.06249v1 Announce Type: cross Abstract: Recently, pre-trained models with phonetic supervision have demonstrated their advantages...
PromptCanvas: Composable Prompting Workspaces Using Dynamic Widgets for Exploration and Iteration in Creative Writing
arXiv:2506.03741v1 Announce Type: cross Abstract: We introduce PromptCanvas, a concept that transforms prompting into a...
