AI News Archive: May 7, 2026 — Part 18
Sourced from 500+ daily AI sources, scored by relevance.
- VoiStory
AI bedtime stories in your voice
- Lovanian
Create your AI companion. Chat on Telegram. Receive selfies.
- Coach Aira
AI English Speaking Coach For Daily Practice
- Wolzen
Create beautiful wallpapers with generative visuals
- llmranks.io
Find out what AI actually says about your brand.
- Dreaming in Claude Managed Agents
Dreaming, outcomes, and multiagent orchestration
- TikoNote: Study with AI
Explain it to learn it
- Madio
3Blue1Brown-style math animations from text prompts
- AIDLC
AI-driven SDLC pipeline for VS Code — from req to deploy
- AI Captions
Add captions to any video
- AI Product Manager Agent
AI that does your product management for you
- AiTom Assist
The ultimate AI career assistant for modern job seekers.
- parserio.com
Advanced VFX Editorial Automation & Ai interoperability
- Operator-Guided Invariance Learning for Continuous Reinforcement Learning
Reinforcement learning (RL) with continuous time and state/action spaces is often data-intensive and brittle under nuisance variability and shift, motivating methods that exploit value-preserving structures to stabilize and improve learning. Most existing approaches focus on special cases, such as p...
- Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
AI systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to perform behaviour that is more useful for certain goals? We introduce a benchmark for measuring model propensity for ins...
- 3D MRI Image Pretraining via Controllable 2D Slice Navigation Task
Self-supervised pretraining has become the mainstream approach for learning MRI representations from unlabeled scans. However, most existing objectives still treat each scan primarily as static aggregations of slices, patches or volumes. We ask whether there exists an intrinsic form of self-supervis...
- Litespark Inference on Consumer CPUs: Custom SIMD Kernels for Ternary Neural Networks
Large language models (LLMs) have transformed artificial intelligence, but their computational requirements remain prohibitive for most users. Standard inference demands expensive datacenter GPUs or cloud API access, leaving over one billion personal computers underutilized for AI workloads. Ternary...
- Patch-Effect Graph Kernels for LLM Interpretability
Mechanistic interpretability aims to reverse-engineer transformer computations by identifying causal circuits through activation patching. However, scaling these interventions across diverse prompts and task families produces high-dimensional, unstructured datasets that are difficult to compare syst...
- Beyond Task Success: Measuring Workflow Fidelity in LLM-Based Agentic Payment Systems
LLM-based multi-agent systems are increasingly deployed for payment workflows, yet prevailing metrics, Task Success Rate (TSR) and Agent Handoff F1-Score (HF1), capture only final outcomes or unordered routing decisions. We introduce the Agentic Success Rate (ASR), a trajectory-fidelity metric that ...
- PrefixGuard: From LLM-Agent Traces to Online Failure-Warning Monitors
Large language model (LLM) agents now execute long, tool-using tasks where final outcome checks can arrive too late for intervention. Online warning requires lightweight prefix monitors over heterogeneous traces, but hand-authored event schemas are brittle and deployment-time LLM judging is costly. ...
- ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation
For artistic applications, video generation requires fine-grained control over both performance and cinematography, i.e., the actor's motion and the camera trajectory. We present ActCam, a zero-shot method for video generation that jointly transfers character motion from a driving video into a new s...
- UniPool: A Globally Shared Expert Pool for Mixture-of-Experts
Modern Mixture-of-Experts (MoE) architectures allocate expert capacity through a rigid per-layer rule: each transformer layer owns a separate expert set. This convention couples depth scaling with linear expert-parameter growth and assumes that every layer needs isolated expert capacity. However, re...
- BAMI: Training-Free Bias Mitigation in GUI Grounding
GUI grounding is a critical capability for enabling GUI agents to execute tasks such as clicking and dragging. However, in complex scenarios like the ScreenSpot-Pro benchmark, existing models often suffer from suboptimal performance. Utilizing the proposed \textbf{Masked Prediction Distribution (MPD...
- AI Co-Mathematician: Accelerating Mathematicians with Agentic AI
We introduce the AI co-mathematician, a workbench for mathematicians to interactively leverage AI agents to pursue open-ended research. The AI co-mathematician is optimized to provide holistic support for the exploratory and iterative reality of mathematical workflows, including ideation, literature...
- Superintelligent Retrieval Agent: The Next Frontier of Information Retrieval
Retrieval-augmented agents are increasingly the interface to large organizational knowledge bases, yet most still treat retrieval as a black box: they issue exploratory queries, inspect returned snippets, and iteratively reformulate until useful evidence emerges. This approach resembles how a newcom...
- When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds
Sign-based optimization algorithms, such as SignSGD and Muon, have garnered significant attention for their remarkable performance in training large foundation models. Despite this empirical success, we still lack a theoretical understanding of when and why these sign-based methods outperform vanill...
- Patch2Vuln: Agentic Reconstruction of Vulnerabilities from Linux Distribution Binary Patches
Security updates create a short but important window in which defenders and attackers can compare vulnerable and patched software. Yet in many operational settings, the most accessible artifacts are binary packages rather than source patches or advisory text. This paper asks whether a language-model...
- Ex Ante Evaluation of AI-Induced Idea Diversity Collapse
Creative AI systems are typically evaluated at the level of individual utility, yet creative outputs are consumed in populations: an idea loses value when many others produce similar ones. This creates an evaluation blind spot, as AI can improve individual outputs while increasing population-level c...
- Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
In recent years, open-source efforts like Senorita-2M have propelled video editing toward natural language instruction. However, current publicly available datasets predominantly focus on local editing or style transfer, which largely preserve the original scene structure and are easier to scale. In...
- Market-Alignment Risk in Pricing Agents: Trace Diagnostics and Trace-Prior RL under Hidden Competitor State
Outcome metrics can certify the wrong behavior. We study this failure in a two-hotel revenue-management simulator where Hotel A trains an agent against a fixed rule-based revenue-management competitor, Hotel B. A standard learning agent can obtain near-reference revenue per available room (RevPAR) w...
- From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features
Sparse autoencoders (SAEs) have become central to mechanistic interpretability, decomposing transformer activations into monosemantic features. Yet existing analyses characterise features almost exclusively through top-activating token lists or decoder weight vectors, leaving the higher-order co-occ...
- ReasonSTL: Bridging Natural Language and Signal Temporal Logic via Tool-Augmented Process-Rewarded Learning
Signal Temporal Logic (STL) is an expressive formal language for specifying spatio-temporal requirements over real-valued, real-time signals. It has been widely used for the verification and synthesis of autonomous systems and cyber-physical systems. In practice, however, users often express their r...
- Probabilistic Dating of Historical Manuscripts via Evidential Deep Regression on Visual Script Features
We introduce a probabilistic approach for dating historical manuscript pages from visual features alone. Instead of aggregating centuries into classes as is standard in the previous literature, we pose dating as an evidential deep regression problem over a continuous year axis, allowing our neural n...
- Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching
We present a novel theoretical framework, Q-MMR, for off-policy evaluation in finite-horizon MDPs. Q-MMR learns a set of scalar weights, one for each data point, such that the reweighted rewards approximate the expected return under the target policy. The weights are learned inductively in a top-dow...
- EMO: Pretraining Mixture of Experts for Emergent Modularity
Large language models are typically deployed as monolithic systems, requiring the full model even when applications need only a narrow subset of capabilities, e.g., code, math, or domain-specific knowledge. Mixture-of-Experts (MoEs) seemingly offer a potential alternative by activating only a subset...
- Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients
Reinforcement learning with verifiable rewards (RLVR), due to the deterministic verification, becomes a dominant paradigm for enhancing the reasoning ability of large language models (LLMs). The community witnesses the rapid change from the Proximal Policy Optimization (PPO) to Group Relative Policy...
- Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents
Large language models (LLMs) power deep research agents that synthesize information from hundreds of web sources into cited reports, yet these citations cannot be reliably verified. Current approaches either trust models to self-cite accurately, risking bias, or employ retrieval-augmented generation...
- Algospeak, Hiding in the Open: The Trade-off Between Legible Meaning and Detection Avoidance
As large language models (LLMs) increasingly mediate both content generation and moderation, linguistic evasion strategies known as Algospeak have intensified the coevolution between evaders and detectors. This research formalizes the underlying dynamics grounded in a joint action model: when Algosp...
- Automated Clinical Report Generation for Remote Cognitive Remediation: Comparing Knowledge-Engineered Templates and LLMs in Low-Resource Settings
The growing demand for cognitive remediation therapy, combined with limited speech therapist availability, has accelerated the adoption of remote rehabilitation tools. These systems generate large volumes of interaction data that are difficult for clinicians to review efficiently. This paper investi...
- Long Context Pre-Training with Lighthouse Attention
Training causal transformers at extreme sequence lengths is bottlenecked by the quadratic time and memory of scaled dot-product attention (SDPA). In this work, we propose Lighthouse Attention, a training-only symmetrical selection-based hierarchical attention algorithm that wraps around ordinary SDP...
- Efficient Pre-Training with Token Superposition
Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in order to achieve high data throughput. In this work, we present Token-Superposition Training (TST), a simple drop-in method that significantly improves the...
- STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
Large Language Model (LLM) agents are increasingly expected to maintain coherent, long-term personalized memory, yet current benchmarks primarily measure static fact retrieval, overlooking the ability to revise stored beliefs when new evidence emerges. We identify a critical and underexplored failur...
- Cubit: Token Mixer with Kernel Ridge Regression
Since its introduction in 2017, the Transformer has become one of the most widely adopted architectures in modern deep learning. Despite extensive efforts to improve positional encoding, attention mechanisms, and feed-forward networks, the core token-mixing mechanism in Transformers remains attentio...
- Towards Emotion Consistency Analysis of Large Language Models in Emotional Conversational Contexts
In this work, we conduct an analysis to examine the consistency of Large Language Models (LLMs) with respect to their own generated responses in an emotionally-driven conversational context. Specifically, the text generated by LLM is framed as a query to the same model, and its responses are subsequ...
- bazarr.ai
Search deals anytime with Baz
- COVID-19 Infodemic. Understanding content features in detecting fake news using a machine learning approach
The use of content features, particularly textual and linguistic for fake news detection is under-researched, despite empirical evidence showing the features could contribute to differentiating real and fake news. To this end, this study investigates a selection of content features such as word bigr...
- From 124 Million Tokens to 1,021 Neologisms: A Large-Scale Pipeline for Automatic Neologism Detection
We present a scalable, modular pipeline for automatic neologism detection that combines rule-based filtering with LLM classification. The pipeline is grounded in two complementary word-formation frameworks, grammatical and extra-grammatical morphology, which jointly define the scope of what counts a...
- GATHER: Convergence-Centric Hyper-Entity Retrieval for Zero-Shot Cell-Type Annotation
Zero-shot single-cell cell-type annotation aims to determine a cell's type from a given set of expressed genes without any training. Existing knowledge-graph-based RAG approaches retrieve evidence by expanding from source entities and relying on iterative LLM reasoning. However, in this setting each...
- Is Escalation Worth It? A Decision-Theoretic Characterization of LLM Cascades
Model cascades, in which a cheap LLM defers to an expensive one on low-confidence queries, are widely used to navigate the cost-quality tradeoff at deployment. Existing approaches largely treat the deferral threshold as an empirical hyperparameter, with limited guidance on the geometry of the result...
- Don't Lose Focus: Activation Steering via Key-Orthogonal Projections
Activation steering controls LLM behaviour towards target behaviour by intervening in internal representations, yet it often degrades reasoning and retrieval performance. We argue that a primary cause of this trade-off is attention rerouting: steering vectors alter query-key matching, shifting atten...