Pular para o conteúdo

News

O que saiu sobre eficiência

Coletado de feeds RSS de laboratórios de IA, do arXiv e de divulgação científica, filtrado pelos termos do projeto.

News

O que saiu esta semana

Atualizado por robô de RSS a cada 6 horas. Só entram itens ligados a embeddings, busca vetorial, quantização e eficiência.

arXiv cs.IR · 12/10/2026Beyond the Final Embedding: Retrieving Memories from Token-Level Evidence arXiv cs.IR · 12/10/2026PRIME: Pre-Retrieval Index Modeling Enhancement for Structured Document Retrieval-Real arXiv cs.IR · 12/10/2026NEAR: Neighborhood-Aware Residuals for Memory Retrieval arXiv cs.IR · 12/10/2026GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports arXiv cs.IR · 12/10/2026RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics arXiv cs.IR · 12/10/2026CRM: Retrieval Model with Controllable Condition arXiv cs.IR · 12/10/2026Differentiable Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation arXiv cs.LG · 12/10/2026Algebraic Integer Quantization for Machine Learning Applications arXiv cs.LG · 12/10/2026STAPLE: Static Sparse Upcycling of Pretrained Checkpoints via Embedding Modules arXiv cs.LG · 12/10/2026CAST: Credit Alignment for Cross-Tokenizer On-Policy Distillation arXiv cs.LG · 12/10/2026MHR-Router: Multimodal Heterogeneous Retrieval-Enhanced Adaptive Routing for VLM Inference arXiv cs.LG · 12/10/2026DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs arXiv cs.LG · 12/10/2026TTS-Q: Perception-Guided Post-Training Quantization of Text-to-Speech Diffusion Transformers arXiv cs.LG · 12/10/2026CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches arXiv cs.LG · 12/10/2026The Predictability Bias of Joint-Embedding Predictive Learning in Medical Imaging arXiv cs.LG · 12/10/2026Taking Tokenization off the Host for Agentic LLM Serving arXiv cs.LG · 12/10/2026RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation arXiv cs.LG · 12/10/2026Shortcut Learning in Geospatial Foundation Model Embeddings for Cross-Disaster Damage Assessment arXiv cs.LG · 12/10/2026Mixture of Many Zero-Compute Experts: A High-Rate Quantization Theory Perspective arXiv cs.CL · 12/10/2026KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse arXiv cs.CL · 12/10/2026Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge Graph arXiv cs.CL · 12/10/2026Benchmarking Embedding Geometries and Clustering Algorithms for Unsupervised Patent Claim Classification arXiv cs.CL · 12/10/2026O\'ido: Open-Vocabulary Speech Recognition on a $5 Microcontroller without a Neural Accelerator arXiv cs.CL · 12/10/2026Retrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical Prognosis arXiv cs.CL · 12/10/2026Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking arXiv cs.CL · 12/10/2026TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models Google DeepMind · 06/10/2026EmbeddingGemma 2: an open, lightweight multimodal embedding model Hugging Face · 21/09/2026tokenizers v1: encode, decode and scaling, measured Google Research · 15/09/2026Bypassing inference bottlenecks: Accelerating complex AI search with Retrieve-for-Train

Feeds monitorados

arXiv cs.IRrss.arxiv.org/rss/cs.IR

arXiv cs.LGrss.arxiv.org/rss/cs.LG

arXiv cs.CLrss.arxiv.org/rss/cs.CL

OpenAIopenai.com/news/rss.xml

Google Researchresearch.google/blog/rss/

Google DeepMinddeepmind.google/blog/rss.xml

Microsoft Researchwww.microsoft.com/en-us/research/feed/

Hugging Facehuggingface.co/blog/feed.xml

Qwenqwenlm.github.io/blog/index.xml

Quanta Magazinewww.quantamagazine.org/feed/

Anthropicsem RSS: coletor de página

CERNsem RSS confirmado: coletor de página