AI News Archive: July 21, 2026 — Part 18
Sourced from 500+ daily AI sources, scored by relevance.
- Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning
Machine unlearning for vision-language models (VLMs) remains underexplored. Unlike language models, VLMs combine a language backbone with visual components, which makes unlearning more complex. There is a surprising phenomenon when moving from single-modality unlearning to VLM unlearning: a target f...
- Selection Shapes the Boundary: A Preregistered Replication of Monotonicity and Label Agreement in Unselected NLI Populations
Prior work on human label variation (HLV) in natural language inference (NLI) has often relied on re-annotation resources that select items by disagreement level. An earlier study (arXiv:2607.15870) found that hypotheses containing non-upward monotonicity operators showed lower label agreement in Ch...
- Translation as Augmentation: Effect of Translated Data on Assessment of Difficulty
Reliable Text Difficulty Assessment is a prerequisite for valid text simplification workflows and personalized learning applications. However, the development of robust assessment models is severely hindered by a critical bottleneck: the scarcity of expert-annotated corpora containing fine-grained d...
- Constrained CTC Decoding for Efficient Diacritic Restoration
In this work, we address diacritic restoration for Arabic speech transcripts. Most speech data are undiacritized, limiting the ability of modeling fine-grained phonological distinctions. The speech modality has recently been explored as a way to complement text-based diacritic restoration efforts. W...
- Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing
Modern ASR models trained on heterogeneously annotated data treat transcription style (verbatim vs. intended) as an uncontrolled latent variable, causing measurable decoding instability, evaluation confounding (up to 60% of reported WER attributable to style mismatch), and unreliable word-level timi...
- RAGAL: A Frugal, Fully Local Retrieval-Augmented Assistant for Technical Support at a Government Agency
Public institutions hold large volumes of sensitive documents and support tickets that cannot leave the premises, ruling out cloud-hosted language models entirely. We report on RAGAL, a retrieval-augmented assistant for the technical-support team of AFIR, the Romanian Agency for Financing Rural Inve...
- Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth Analysis Using a Neuropsychology-Inspired Benchmark
Translating brain signals into text could restore communication for people with severe paralysis, yet practically usable systems to date rely on invasive electrocorticography (ECoG). Electroencephalography (EEG) offers a non-invasive alternative, and EEG-to-text (EEG2Text) has been widely explored. ...
- Dual Attention Residuals
Recent work extends Transformer residual pathways along two complementary axes: historical retrieval selects information from earlier depths, whereas multi-stream methods maintain multiple residual trajectories. These capabilities have largely been studied in isolation, and assigning an independent ...
- Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio
A single embedding space that covers text, images, video, and audio lets one index serve every query a user can pose. Embedding models built on vision-language backbones now lead text/image/video retrieval benchmarks but lack audio entirely, while audio-text retrieval is led by specialist systems th...
- PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID
Multi-vector dense retrieval models, such as ColBERT, achieve strong retrieval effectiveness by modelling fine-grained token-level interactions between queries and documents. Methods such as PLAID use centroid-based quantisation of each token's vector to reduce the index size and speed up retrieval ...
- LatentMT: Machine Translation with Latent Reasoning
Latent-reasoning looped language models (LoopLMs) offer a different scaling path for machine translation (MT): instead of increasing parameter count or emitting explicit chain-of-thought tokens, they spend additional recurrent computation inside hidden states. We introduce LatentMT, the first system...
- AutoIndex: Learning Representation Programs for Retrieval
We present AutoIndex, a framework for learning representation programs: executable transformations that map raw documents into the representations exposed to a retrieval system. Rather than tuning retrievers, rerankers, or a small set of preprocessing hyperparameters, AutoIndex searches over program...
- Lev8
Find, research, and reach the right people
- CartAI
The AI agent that handles checkout.
- ditto.site
Clone any website into clean code. Free & open source
- Skim
Free, open-source AI email client for Windows
- Bolna Agent Studio
Build Voice AI Agent in 10 Minutes
- Manifest
Turn any webpage into an action manifest for AI agents
- Topolines
Generate Topologic contours
- OpenChatCut
Open-source AI agent video editor with a real timeline
- Routebase
Catch API drift before your customers do
- DualStream
Simultaneous desktop and mobile streaming, the easy way.
- tterm
A terminal, a real browser, and Claude Code under one roof
- PieceKeeper
Track your music repertoire and practice
- Tidy
Your Mac tidies itself: screenshots, installers, Downloads
- Universal Dictation on Stream
Private Voice Ring for dictation across iOS & Mac
- Diffsmith
Comment on your AI agent's code & collaborate on changes
- ProtoFlow
AI-powered PCB design tool for engineers and hardware teams
- GetMint
Turn AI search into a growth channel
- Hitoo
Speak all languages in your own voice, in real time
- ScaliQ
AI agents that run LinkedIn outreach just like you
- Mantlecore
Managed cloud for open-source AI agents
- Evertree
Preserve your family's stories with AI-guided conversations
- Sited
Is your brand visible to AI?
- LeadGuide
Sales Copilot built for authentic relationships, not spam.
- MyPeople
Put a boss on your Claude Code and Codex agents
- AdRiseLab
Your AI performance marketer for Meta ads
- Magical Chess
Free smart chess board — runs on the phone in your pocket.
- Flomo Health AI
AI Health Coach, Daily Tracking, Perssonalized Meal Plans
- Dreemart AI - Turn Your Dream Into Art
Turn Your Dreams Into Stunning Works of Art With AI
- Softalon
Instagram & WhatsApp AI Booking Assistant for Salons
- handmux—Your coding agent, on your phone
Drive your coding agent from anywhere, zero install
- AI Usage Tracker
One local dashboard for Claude and Codex spend
- Loqara
AI chat and voice agents that turn conversations into sales
- Mela
The agent that hires creative freelancers
- Korean Food Recipes
AI that turns any Korean cooking YouTube link into a recipe.
- Fortress
The stealth browser engine for scrapers and AI agents
- Skryber
Turn long videos into viral shorts with AI — in minutes
- OpenIngress
Can AI agents use your UI?
- Phaide AI
Stop building static dashboards. Start discovering.