AI News Archive: May 7, 2026 — Part 19
Sourced from 500+ daily AI sources, scored by relevance.
- MANTRA: Synthesizing SMT-Validated Compliance Benchmarks for Tool-Using LLM Agents
Tool-using large language model (LLM) agents are increasingly deployed in settings where their reliable behavior is governed by strict procedural manuals. Ensuring that such agents comply with the rules from these manuals is challenging, as they are typically written for humans in natural language w...
- Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity
Safety benchmarks are routinely treated as evidence about how a language model will behave once deployed, but this inference is fragile if behavior depends on whether a prompt looks like an evaluation. We define evaluation-context divergence as an observable within-item change in behavior induced by...
- Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs
Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes. Highly structured methods rely on fixed roles, pipelines, or task decompositions assigned a priori. In contrast, fully unstructured teams enable adaptability and explorati...
- Who and What? Using Linguistic Features and Annotator Characteristics to Analyze Annotation Variation
Human label variation has been established as a central phenomenon in NLP: the perspectives different annotators have on the same item need to be embraced. Data collection practices thus shifted towards increasing the annotator numbers and releasing disaggregated datasets, harmful language being mos...
- Log-Likelihood, Simpson's Paradox, and the Detection of Machine-Generated Text
The ability to reliably distinguish human-written text from that generated by large language models is of profound societal importance. The dominant approach to this problem exploits the likelihood hypothesis: that machine-generated text should appear more probable to a detector language model than ...
- LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG
Single-step retrieval-augmented generation (RAG) provides an efficient way to incorporate external information for simple question answering tasks but struggles with complex questions. Agentic RAG extends this paradigm by replacing single-step retrieval with a multi-step process, in which the large ...
- Quantifying the Statistical Effect of Rubric Modifications on Human-Autorater Agreement
Autoraters, also referred to as LLM-as-judges, are increasingly used for evaluation and automated content moderation. However, there is limited statistical analysis of how modifications in a rubric presented to both humans and autoraters affect their score agreement. Rubrics that ask for an overall ...
- Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning
Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not teach new strategies; it redistributes probability mass over solutions the base model already contains. In this work, we ask: if RL merely steers the m...
- UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification
As large language models (LLMs) continue to advance rapidly, they are becoming increasingly capable while simultaneously demanding ever-longer context lengths. To improve the inference efficiency of long-context processing, several novel low-complexity hybrid architectures have recently been propose...
- TIDE: Every Layer Knows the Token Beneath the Context
We revisit a universally accepted but under-examined design choice in every modern LLM: a token index is looked up once at the input embedding layer and then permanently discarded. This single-injection assumption induces two structural failures: (i) the Rare Token Problem, where a Zipf-type distrib...
- Above Security
AI agents for insider risk detection and response
- Parser agreement and disagreement in L2 Korean UD: Implications for human-in-the-loop annotation
We propose a simplified human-in-the-loop workflow for second language (L2) Korean morphosyntactic annotation by leveraging agreement between two domain-adapted parsers. We first evaluate whether parser agreement can serve as a proxy for annotation correctness by comparing it with independent human ...
- PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization
Many operations on sensory data -- comparison, memory, retrieval, and reasoning -- are naturally expressed over discrete symbolic structures. In language this interface is given by tokens; in audio, it must be learned. Existing audio tokenizers rely on quantization, clustering, or codec reconstructi...
- The Frequency Confound in Language-Model Surprisal and Metaphor Novelty
Language-model (LM) surprisal is widely used as a proxy for contextual predictability and has been reported to correlate with metaphor novelty judgments. However, surprisal is tightly intertwined with lexical frequency. We explore this interaction on metaphor novelty ratings using two different word...
- Invariant Features in Language Models: Geometric Characterization and Model Attribution
Language models exhibit strong robustness to paraphrasing, suggesting that semantic information may be encoded through stable internal representations, yet the structure and origin of such invariance remain unclear. We propose a local geometric framework in which semantically equivalent inputs occup...
- MiA-Signature: Approximating Global Activation for Long-Context Understanding
A growing body of work in cognitive science suggests that reportable conscious access is associated with \emph{global ignition} over distributed memory systems, while such activation is only partially accessible as individuals cannot directly access or enumerate all activated contents. This tension ...
- E = T*H/(O+B): A Dimensionless Control Parameter for Mixture-of-Experts Ecology
We introduce E = T*H/(O+B), a dimensionless control parameter that predicts whether Mixture-of-Experts (MoE) models will develop a healthy expert ecology or collapse into dead experts. E combines four hyperparameters -- routing temperature T, routing entropy weight H, oracle weight O, and balance we...
- WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling
Integrating speech understanding and generation is a pivotal step toward building unified speech models. However, the different representations required for these two tasks currently pose significant compatibility challenges. Typically, semantics-oriented features are learned from self-supervised le...
- SEQUOR: A Multi-Turn Benchmark for Realistic Constraint Following
In a conversation, a helpful assistant must reliably follow user directives, even as they refine, modify, or contradict earlier requests. Yet most instruction-following benchmarks focus on single-turn or short multi-turn scenarios, leaving open how well models handle long-horizon instruction-followi...
- Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning
Tool-integrated reasoning (TIR) offers a direct way to extend thinking models beyond the limits of text-only reasoning. Paradoxically, we observe that tool-enabled evaluation can degrade reasoning performance even when the strong thinking models make almost no actual tool calls. In this paper, we in...
- MultiLinguahah : A New Unsupervised Multilingual Acoustic Laughter Segmentation Method
Laughter is a social non-vocalization that is universal across cultures and languages, and is crucial for human communication, including social bonding and communication signaling. However, detecting laughter in audio is a challenging task, and segmenting is even more difficult. Currently, Machine L...
- Linear Semantic Segmentation for Low-Resource Spoken Dialects
Semantic segmentation is a core component of discourse analysis, yet existing models are primarily developed and evaluated on high-resource written text, limiting their effectiveness on low-resource spoken varieties. In particular, dialectal Arabic exhibits informal syntax, code-switching, and weakl...
- YEZE at SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization via Heterogeneous Ensembling
This paper presents our system for SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization, which identifies polarized social media content in 22 languages through three subtasks: binary detection, target classification, and manifestation identification. We prop...
- Contrastive Identification and Generation in the Limit
In the classical identification in the limit model of Gold [1967], a stream of positive examples is presented round by round, and the learner must eventually recover the target hypothesis. Recently, Kleinberg and Mullainathan [2024] introduced generation in the limit, where the learner instead must ...
- SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders
Sparse Autoencoders (SAEs) have become an important tool in mechanistic interpretability, helping to analyze internal representations in both Large Language Models (LLMs) and Vision Transformers (ViTs). By decomposing polysemantic activations into sparse sets of monosemantic features, SAEs aim to tr...
- MedHorizon: Towards Long-context Medical Video Understanding in the Wild
Medical multimodal large language models (MLLMs) have advanced image understanding and short-video analysis, but real clinical review often requires full-procedure video understanding. Unlike general long videos, medical procedures contain highly redundant anatomical views, while decisive evidence i...
- Bluespine
AI claims review for employer health plans
- MARBLE: Multi-Aspect Reward Balance for Diffusion RL
Reinforcement learning fine-tuning has become the dominant approach for aligning diffusion models with human preferences. However, assessing images is intrinsically a multi-dimensional task, and multiple evaluation criteria need to be optimized simultaneously. Existing practice deal with multiple re...
- Hyperbolic Concept Bottleneck Models
Concept Bottleneck Models (CBMs) have become a popular approach to enable interpretability in neural networks by constraining classifier inputs to a set of human-understandable concepts. While effective, current models embed concepts in flat Euclidean space, treating them as independent, orthogonal ...
- From Review to Design: Ethical Multimodal Driver Monitoring Systems for Risk Mitigation, Incident Response, and Accountability in Automated Vehicles
As vehicles transition toward higher levels of automation, Driver Monitoring Systems (DMS) have become essential for ensuring human oversight, safety, and regulatory compliance in a vehicle. These systems rely on multimodal sensing and AI-driven inference to assess driver attention, cognitive state,...
- Empirical Evidence for Simply Connected Decision Regions in Image Classifiers
Understanding the topology of decision regions is central to explaining the inner workings of deep neural networks. Prior empirical work has provided evidence that these regions are path connected. We study a stronger topological question: whether closed loops inside a decision region can be contrac...
- Earth-o1: A Grid-free Observation-native Atmospheric World Model
Despite the unprecedented volume of multimodal data provided by modern Earth observation systems, our ability to model atmospheric dynamics remains constrained. Traditional modeling frameworks force heterogeneous measurements into predefined spatial grids, inherently limiting the full exploitation o...
- TinyBayes: Closed-Form Bayesian Inference via Jacobi Prior for Real-Time Image Classification on Edge Devices
Cocoa (Theobroma cacao) is a critical cash crop for millions of smallholder farmers in West Africa, where Cocoa Swollen Shoot Virus Disease (CSSVD) and anthracnose cause devastating yield losses. Automated disease detection from leaf images is essential for early intervention, yet deploying such sys...
- When Labels Have Structure: Improving Image Classification with Hierarchy-Aware Cross-Entropy
Standard cross-entropy is the default classification loss across virtually all of machine learning, yet it treats all misclassifications equally, ignoring the semantic distances that a class hierarchy encodes. We propose Hierarchy-Aware Cross-Entropy (HACE), a drop-in replacement for standard cross-...
- ZScribbleSeg: A comprehensive segmentation framework with modeling of efficient annotation and maximization of scribble supervision
Curating fully annotated datasets for medical image segmentation is labour-intensive and expertise-demanding. To alleviate this problem, prior studies have explored scribble annotations for weakly supervised segmentation. Existing solutions mainly compute losses on annotated areas and generate pseud...
- Bridging visual saliency and large language models for explainable deep learning in medical imaging
The opaque nature of deep learning models remains a significant barrier to their clinical adoption in medical imaging. This paper presents a multimodal explainability framework that bridges the gap between convolutional neural network (CNN) predictions and clinically actionable insights for brain tu...
- Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios
Recent large vision-language models have achieved strong performance on short- and medium-length video understanding, yet they remain inadequate for ultra-long or even infinite video reasoning, where models must preserve coherent memory over extended durations and infer causal dependencies across te...
- Beyond Forgetting in Continual Medical Image Segmentation: A Comprehensive Benchmark Study
Continual learning (CL) is essential for deploying medical image segmentation models in clinical environments where imaging domains, anatomical targets, and diagnostic tasks evolve over time. However, continual segmentation still faces three main challenges. First, the scenarios for this task remain...
- Relit-LiVE: Relight Video by Jointly Learning Environment Video
Recent advances have shown that large-scale video diffusion models can be repurposed as neural renderers by first decomposing videos into intrinsic scene representations and then performing forward rendering under novel illumination. While promising, this paradigm fundamentally relies on accurate in...
- DPM++: Dynamic Masked Metric Learning for Occluded Person Re-identification
Although person re-identification has made impressive progress, occlusion caused by obstacles remains an unsettled issue in real applications. The difficulty lies in the mismatch between incomplete occluded samples and holistic identity representations. Severe occlusion removes discriminative body c...
- Agentic AIs Are the Missing Paradigm for Out-of-Distribution Generalization in Foundation Models
Foundation models (FMs) are increasingly deployed in open-world settings where distribution shift is the rule rather than the exception. The out-of-distribution (OOD) phenomena they face -- knowledge boundaries, capability ceilings, compositional shifts, and open-ended task variation -- differ in ki...
- DCR: Counterfactual Attractor Guidance for Rare Compositional Generation
Diffusion models generate realistic visual content, yet often fail to produce rare but plausible compositions. When prompted with combinations that are valid but underrepresented in training data, such as a snowy beach or a rainbow at night, the generation process frequently collapses toward more co...
- ClearMesh
A Git-like platform for datasets, models, and binary folders
- FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction
Video diffusion models perform well in short-video synthesis, but their training-free extension to long videos often suffers from content drift, temporal inconsistency, and over-smoothed dynamics. Existing methods improve temporal consistency by combining a global branch with a local branch, but the...
- GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs
We address the challenge of knowledge composition in Vision-Language Models (VLMs), where accumulating expertise across multiple domains or tasks typically leads to catastrophic forgetting. We introduce GeoStack (Geometric Stacking), a modular framework that allows independently trained domain exper...
- J2 Insights
Automated market briefings with a live data portal
- TalorData SERP API
Real-time SERP data API for SEO, AI, and automation
- Autonomous Vehicle Safety Test Framework
Automated MISRAC compliance validation for AVs Nvidia
- Milkiyat.com
Data-driven PropTech bridging Pakistan's trust gap.
- AI Rules Pack for modern FE Development
Stop teaching AI your code conventions every session