nlp
30 articles about nlp in AI news
VMLOps Publishes NLP Engineer System Design Interview Guide
VMLOps has published 'The NLP Engineer's System Design Interview Guide,' a detailed resource covering architecture, scaling, and trade-offs for real-world NLP systems. It provides a structured framework for both interviewers and candidates.
Talkie: Vintage LLM Trained on 260B Pre-1931 English Tokens
Talkie is a new 'vintage language model' trained on 260 billion tokens of historical English text from before 1931, developed by a team including Alec Radford, co-author of the original GPT paper. It offers a unique linguistic artifact for NLP research.
LIDS Framework Revolutionizes LLM Summary Evaluation with Statistical Rigor
Researchers introduce LIDS, a novel method combining BERT embeddings, SVD decomposition, and statistical inference to evaluate LLM-generated summaries with unprecedented accuracy and interpretability. The framework provides layered theme analysis with controlled false discovery rates, addressing a critical gap in NLP assessment.
JD.com Deploys AI Across Qixi Gifting
JD.com is leveraging AI to transform Qixi gifting, shifting focus from product discovery to immersive brand storytelling. This move, reported by Business Insider, signals a major evolution in how Chinese e-commerce platforms drive festival sales through personalized narrative experiences.
Relay-OPD: On-Policy Distillation Fixes Prefix Failure in LLMs
Relay-OPD introduces on-policy distillation where a teacher briefly takes over student LLM generation to fix prefix failure, reducing error compounding without full teacher compute.
Dior Launches Multi-City Pop-Ups Across China, 12 Locations
Dior opened 12 pop-ups across China with Tuileries theme. Campaign targets luxury rebound after 2025 slump.
Most digital shoppers still aren't sold on AI shopping, eMarketer reports
eMarketer reports that most digital shoppers remain unconvinced by AI shopping tools, posing a trust and adoption challenge for retailers investing in the technology.
Moonshot AI's Kimi K3: 2.8T params, 1M token window, $3/M input
Moonshot AI released Kimi K3, a 2.8T-parameter mixture-of-experts model with 1M token context window and $3/M input pricing, claiming autonomous chip design and research capabilities.
Instacart Acquires Computer Vision Firm Arpalus for Real-Time Grocery
Instacart acquired computer vision firm Arpalus to add real-time shelf intelligence for grocery retailers. The technology automates inventory monitoring, product placement, and pricing verification.
ServiceNow's SynthDocBench Teases Apart VLM Long-Context Failure Modes
ServiceNow releases SynthDocBench, a controlled synthetic benchmark for long-context visual document understanding that varies length, layout, modality, and reasoning to diagnose VLM failures.
AI now at top of agenda for more luxury houses: Bain report
Bain & Company reports that AI is now a top priority for an increasing number of luxury houses, signaling a major strategic shift. This matters as luxury brands move to integrate AI for personalization, operations, and customer experience.
Kering Deploys AI-Powered Sustainable Sourcing Assistant on Google Cloud
Kering launched a Sustainable Sourcing Assistant on Google Cloud's Vertex AI. The tool helps luxury brands like Gucci and Saint Laurent evaluate materials for environmental and social impact, advancing sustainability in procurement.
Canada Deploys Grace Blackwell via $220M Bell-Cohere Deal
Canada's $220M Bell-Cohere deal puts Grace Blackwell on domestic soil for sovereign AI, reducing reliance on US cloud providers.
AI could unlock €320 billion for European retail, new analysis finds
A new fashionunited.uk analysis estimates AI could unlock up to €320 billion for European retail. The figure underscores AI's potential in automation, personalization, and supply chain optimization across the sector.
Google Open-Sources DiffusionGemma, 26B Model Hits 1K Tokens/Sec on H100
Google open-sourced DiffusionGemma, a 26B-parameter diffusion text model hitting 1,000 tokens/sec on H100 — 4x faster than autoregressive models, but with lower quality.
Instacart's Semantic IDs: Product Understanding at Scale
Instacart's engineering team details a semantic ID system for product understanding at scale, using embeddings to create meaningful identifiers that enhance search and recommendations. This approach captures nuanced product relationships, improving relevance for grocery e-commerce.
Alibaba + Nanjing Univ Claim 9.36X Faster Million-Token Prefill vs FlashAttention-2
Alibaba + Nanjing Univ claim 9.36X faster million-token prefill vs FlashAttention-2, targeting the key bottleneck in long-context LLM inference.
ModelBest Drops BitCPM-CANN: First 1.58-bit LLM on Ascend 910B
ModelBest released BitCPM-CANN, the first 1.58-bit ternary LLM on Ascend 910B NPUs, using 6× less VRAM than BF16 with minimal capability loss.
MLLM Raters Show Central Tendency Bias in Clinical Scoring
Study finds GPT-5 and other MLLMs show central tendency bias in clinical scoring, compressing predictions toward scale midpoint despite prompt modifications.
Simple Graph Heuristic Beats Generative Recommenders on 10 of 14 Benchmarks
A no-training graph heuristic beats generative recommenders on 10 of 14 benchmarks, exposing shortcut-solvable datasets. Relative NDCG@10 gains hit 44% on Amazon CDs.
New CASIA Benchmark Exposes Fragmented Face Swapping Evaluation
CASIA researchers released a face swapping survey and benchmark on April 27, 2026, aiming to standardize evaluation across fragmented GAN and diffusion model methods.
Meta Tuna-2: Encoder-Free Multimodal Model Beats VAE-Based Rivals
Meta released Tuna-2, an encoder-free multimodal model that understands and generates images from raw pixels. It beats encoder-based models on fine-grained perception benchmarks, challenging the dominant VAE/vision encoder paradigm.
R³AG: A New Routing Framework That Matches Queries to Retriever
R³AG is a novel routing framework that dynamically selects the optimal retriever for each query in RAG systems, considering not just relevance but also how well the retrieved document helps the generator produce correct answers. It uses contrastive learning to model query-specific preferences, consistently outperforming existing methods on knowledge-intensive tasks.
New MoE Framework Tames User Interest Shifts in Long-Sequence Recommendations
Researchers propose MoS, a model-agnostic MoE approach that handles long user sequences by detecting session hopping – where user interests shift across sessions. The theme-aware routing mechanism filters irrelevant sessions, while multi-scale fusion captures global and local patterns. Results show SOTA on benchmarks with fewer FLOPs than alternatives.
ERA Framework Improves RAG Honesty by Modeling Knowledge Conflicts as
ERA replaces scalar confidence scores with explicit evidence distributions to distinguish between uncertainty and ambiguity in RAG systems, improving abstention behavior and calibration.
ESGLens: A New RAG Framework for Automated ESG Report Analysis and Score
ESGLens combines RAG with prompt engineering to extract structured ESG data, answer questions, and predict scores. Evaluated on ~300 reports, it achieved a Pearson correlation of 0.48 against LSEG scores. The paper highlights promise but also significant limitations.
AI Turned Thrift Into a Profitable Fashion Machine
The article details how AI technologies are being deployed in the thrift and resale fashion industry to automate critical operations like pricing, authentication, and inventory management, turning a traditionally labor-intensive sector into a scalable, data-driven profit engine.
RoTE: A New Plug-and-Play Module to Sharpen Time-Aware Sequential
A new research paper introduces RoTE, a multi-level temporal embedding module for sequential recommenders. It explicitly models the time spans between user interactions, a factor often overlooked, leading to significant performance gains on standard benchmarks.
ETH Zurich & Anthropic AI Links Anonymous Accounts via Writing Style
Researchers built an AI that identifies authors from anonymous accounts by analyzing writing style. It achieved over 80% accuracy, raising significant privacy concerns for online anonymity.
Binghamton University Tests Robotic Guide Dog with Natural Language Interface
Researchers at Binghamton University have developed a robotic guide dog prototype that communicates with users using natural language. The system, built on a Unitree Go2 platform, was demonstrated navigating a user through a test environment.