AI News Archive: May 18, 2026 — Part 14
Sourced from 500+ daily AI sources, scored by relevance.
- EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agents, as it enables them to store, update, and retrieve information over time. This ability remains under-evaluated, largely because existing benchmarks...
- SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
Long-horizon LLM agents leave traces that could become reusable experience, but raw trajectories are noisy and hard to govern. We treat Agent Skills as an experience schema that couples executable scripts, with non-executable guidance on procedures. Yet open skill ecosystems contain redundant, uneve...
- Presupposition and Reasoning in Conditionals: A Theory-Based Study of Humans and LLMs
Presupposition projection in conditionals is central to theories of meaning and pragmatics, yet it remains largely unevaluated in large language models. We address this gap through a parallel behavioral study comparing human judgments and LLM predictions on a normed dataset of conditional sentences ...
- Infini-News: Efficiently Queryable Access to 1.3 Billion Processed Common Crawl News Articles
Large-scale news corpora support a wide range of research in Computational Social Science and NLP, yet access remains constrained: commercial archives impose prohibitive costs and licensing restrictions, while open alternatives like Common Crawl's CC-News require terabyte-scale storage and computati...
- SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning
Search-augmented reasoning agents interleave internal reasoning with calls to an external retriever, and their performance relies on the quality of each issued query. However, under outcome-reward reinforcement learning, every search decision in a rollout shares the same trajectory-level reward, lea...
- From Volume to Value: Preference-Aligned Memory Construction for On-Device RAG
With the rapid emergence of personal AI agents based on Large Language Models (LLMs), implementing them on-device has become essential for privacy and responsiveness. To handle the inherently personal and context-dependent nature of real-world requests, such agents must ground their generation in de...
- Agentspan
Open-source runtime for durable AI agents
- Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains
Reinforcement learning with verifiable rewards (RLVR) has demonstrated promising potential to enhance the reasoning capabilities of large language models (LLMs) in domains such as mathematics and coding. However, its applications on knowledge-intensive domains have not been effectively explored due ...
- CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook
Multimodal representation alignment is pivotal for large language models and robotics. Traditional methods are often hindered by cross-modal information discrepancies and data scarcity, leading to suboptimal alignment spaces that overlook modality-unique features. We propose CodeBind, a framework th...
- Multilingual jailbreaking of LLMs using low-resource languages
Large Language Models (LLMs) remain vulnerable to jailbreak attempts that circumvent safety guardrails. We investigate whether multi-turn conversations using low-resource African languages (Afrikaans, Kiswahili, isiXhosa, and isiZulu) can bypass safety mechanisms across commercial LLMs. We translate...
- SomaliWeb v1: A Quality-Filtered Somali Web Corpus with a Matched Tokenizer and a Public Language-Identification Benchmark
Somali is a Cushitic language of the Horn of Africa with ~25 million speakers, yet no documented dedicated Somali pretraining corpus with a companion tokenizer and language-identification benchmark has been publicly released. Existing Somali text appears either inside multilingual distributions (HPL...
- Context Memorization for Efficient Long Context Generation
Modern large language model (LLM) applications increasingly rely on long conditioning prefixes to control model behavior at inference time. While prefix-augmented inference is effective, it incurs two structural limitations: i) the prefix's influence fades as generation proceeds, and ii) attention c...
- Free ai text detector
AI Text Detection Studio is a free bulk online tool
- AureonAi
24/7 AI Receptionist & Automation for Small Business
- HADEMANASTIA llms.txt
llms.txt for a sonic protocol, not a SaaS
- RedRok
AI-Powered Attack Surface Management
- AethirexAI
Pre-market news sentiment for stock traders powered by AI
- Agentlas
Describe a worker, get an AI agent that does it
- DocVoice — Talk to Your Documents
Speak Smarter. Sound Better.
- GlowCut AI
Generate image and video by ai using shopify product url
- Salus Scan
Free & anonymous AI symptom checker.
- Block Blast Solver
Block Blast Solver Free & Instant Solutions Online AI Tool
- hermitAI
A solitary, fully-local AI. No cloud, no API keys.
- WhiteboardMaker
Turn images into whiteboard videos
- Shake Cursor
Shake your mouse to summon local Codex.
- ledger
AI powered professional invoicing for productive businesses.
- Planiaro
Travel / Travel Planning / AI Itinerary Generator
- AI Motion Control
AI motion-controlled video generation
- ElseID — Social network via MCP
No app. It lives inside the AI clients you already have.
- Ai vision
Free
- Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video
Retrieving the 3D kinematics of articulated objects from monocular video is a fundamental challenge in computer vision. Existing methods rely on complex video setups or cues such as long-term point tracking or wide-baseline matching, but are frequently brittle under severe occlusions, rapid camera e...
- Leveraging Latent Visual Reasoning in Silence
Latent visual reasoning involves visual evidence more directly in multimodal reasoning by inserting continuous latent tokens before textual generation. However, the necessity of these latent tokens at inference remains ambiguous. We show that replacing latent tokens with random noise or removing the...
- SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents
Long-horizon multimodal agents in open-world games must stay goal-directed across many low-level interactions under tight token and latency budgets. Existing approaches often trade off costly per-step reasoning against reactive execution that can drift, repeat failures, and recover poorly. Our key i...
- LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift
Modeling hyperspectral imagery (HSI) across different sensors presents a fundamental challenge due to variations in wavelength coverage, band sampling, and channel dimensionality. As a result, models trained under a fixed spectral configuration often fail to generalize to other sensors. Existing Vis...
- Benchmarking transferability of SSL pretraining to same and different modality segmentation tasks
Methods: Nine SSL methods spanning four pretext-task families were pretrained from scratch using the same 10{,}412 3D CT scans (1.89~M 2D axial slices) covering varied disease sites. The pretrained Swin Transformer encoder from each method was integrated into a SwinUNETR-style segmentation network (...
- Speech-Guided Multimodal Learning for Vocal Tract Segmentation in Real-Time MRI
Segmenting vocal tract articulators in real-time MRI (rtMRI) is a challenging dynamic image segmentation problem characterized by low contrast, rapid motion, and limited spatial resolution. However, while rtMRI acquisitions may provide synchronized acoustic signals, existing methods discard this inf...
- PERL: Parameter Efficient Reasoning in CLIP Latent Space
Contrastively trained vision-language models such as CLIP provide strong zero-shot transfer by aligning images and text in a shared embedding space. However, adapting these models to downstream tasks without degrading their open-vocabulary generalization remains challenging. Existing parameter-effic...
- A Dataset for the Recognition of Historical and Handwritten Music Scores in Western Notation
A large amount of musical heritage has been digitised by memory institutions: libraries, museums, and archives. Nevertheless, the field of Optical Music Recognition (OMR) has struggled with making this music machine-readable, despite advances in deep learning, mostly because no datasets for training...
- TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval
E-commerce image search often takes a cropped image as the query, while each candidate is represented by full item images and structured text. This image-to-multimodal retrieval setting presents two asymmetries: a modality disparity -- a visual query must match image--text items, and a granularity d...
- Seeing Together:Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) have made substantial progress in egocentric video understanding, but their ability to reason cooperatively from multiple embodied viewpoints remains largely unexplored. We study this problem through multi-robot cooperative dynamic spatial reasoning, where a ...
- Geometry-Aware Uncertainty Coresets for Robust Visual In-Context Learning in Histopathology
Vision-language models (VLMs) can couple visual perception with open-ended clinical reasoning, making them attractive for computational histopathology. However, fine-tuning billions of parameters on scarce, expert-annotated pathology data is prohibitive, while in-context learning (ICL), which condit...
- Vision Foundation Models as Generalist Tokenizers for Image Generation
In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (VFM). To build this tokenizer, we utilize a frozen VFM as the encoder and introduce two key innovations: (1) a region-adaptive quantization framewor...
- Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate
Multiview 3D evaluation assumes that the images being scored are observations of one static 3D scene. This assumption can fail in NVS and sparse-view reconstruction: inputs or generated outputs may contain artifacts, outlier frames, repeated views, or noise, yet still receive high 3D consistency sco...
- WavFlow: Audio Generation in Waveform Space
Modern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this work, we challenge this paradigm with WavFlow, a framework that generates high-fidelity audio directly in raw waveform space without intermediate repres...
- Aurora: Unified Video Editing with a Tool-Using Agent
Recent video editing models have converged on a unified conditioning design: a single diffusion transformer jointly consumes text, source video, and reference images, and one set of weights covers replacement, removal, style transfer, and reference-driven insertion. The design is flexible, but it as...
- The Claude Code Daily
Claude Code news. Curated Daily.
- LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
We present LongLive-2.0, an NVFP4-based parallel infrastructure throughout the full training and inference workflow of long video generation, addressing speed and memory bottlenecks. For training, we introduce sequence-parallel autoregressive (AR) training, instantiated as Balanced SP, which co-desi...
- Spectral Progressive Diffusion for Efficient Image and Video Generation
Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later timesteps. This structure offers a natural opportunity for ...
- PIXLRelight: Controllable Relighting via Intrinsic Conditioning
We present PIXLRelight, a feed-forward approach for physically controllable single-image relighting. Existing methods either provide limited lighting control (e.g. through text or environment maps), accumulate errors when chaining inverse and forward rendering, or require costly per-image optimizati...
- EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric Videos
Egocentric memory is widely used in embodied intelligence, but it may be insufficient for comprehensive spatial-temporal reasoning. Inspired by human recall from both field and observer perspectives, we introduce EgoExoMem, the first benchmark for cross-view memory reasoning over synchronized egocen...