AI News Archive: July 16, 2026 — Part 23
Sourced from 500+ daily AI sources, scored by relevance.
- Latent Trajectory Discrimination for AI-Generated Text Detection
Most existing approaches to AI-Generated Text Detection (AIGTD) treat documents as static objects and base their decisions on aggregate statistics or globally compressed embeddings. However, this perspective overlooks the inherently dynamic nature of autoregressive generation, where content evolves ...
- Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control
World Action Models (WAMs) enable semantically- and physically-informed control but are brittle under distribution shift. In this work, we use mechanistic interpretability to study how robustness-relevant perturbations are represented in WAM activation space. Comparing activations across successful ...
- A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems
Recent foundation models (FMs) for zero-shot reconstruction of dynamical systems (DS) achieve strong out-of-domain generalization but provide little insight into the mechanisms that underlie their forecasts. Such an understanding could help to strip down overladen FM architectures to their bare esse...
- Benchmarking Face Recognition without Real Faces
Synthetic face datasets have become effective enough to train face recognition models with accuracy rivaling that of models trained on real photographs. This progress sidesteps the ethical and legal burdens of collecting real biometric data, yet evaluation has not kept pace. Even studies that train ...
- FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with Transformers
Real-time video generation demands fast decoding as much as fast denoising, yet current latent video diffusion models rely on 3D convolutional decoders that are slow and memory-intensive at high resolutions or for long video. We introduce FlashDecoder, a fast, memory-efficient pure-Transformer video...
- Proof-or-Stop: Don't Trust the Agent, Trust the Evidence -- Loop Engineering for Verifiable Evidence-Gated Lifecycle Control
Autonomous coding agents increasingly execute multi-step software work, but lifecycle states such as reviewed, tested, DONE, and ready-to-merge remain claims unless supported by current evidence. We present Proof-or-Stop Lifecycle Control, a method that permits lifecycle transitions only when fresh,...
- Does generative AI supersede supervised XMLC? A Benchmark Study on Automated Subject Indexing with German Scientific Literature
With a large controlled vocabulary as the label set, the task of automated subject indexing in a library can be understood as a multi-label classification task. If the set of subject terms is large, the problem fits the Extreme Multi-Label Classification (XMLC) objective. In this study, we apply a s...
- Asymmetric Peak-Aware Loss for Peak-Critical Time Series Forecasting
In many operational time-series forecasting applications, such as crowd demand forecasting, the risk related to under-prediction is substantially higher than that of over-prediction. Accurate prediction of rare demand spikes plays a critical role in downstream tasks. Yet most time-series forecasters...
- RW-Voice-EQ Bench: A Real World Benchmark for Evaluating Voice AI Systems
Current voice AI benchmarks typically evaluate isolated capabilities such as speech intelligibility, word error rate, or text-based dialogue quality, but they rarely test whether systems harness the acoustic information that distinguishes spoken language from its textual representation. To this end,...
- Nitrosend
Email for AI agents. They sign up, send and reply.
- Interventional Causal Circuits for Safe Robot Action Testing and Failure Recovery
Safe physical AI for robot actions are required not only likely to succeed but tested to be safe before execution. In practice, however, formal testing of motion parameters is computationally expensive, and the cost scales poorly with the dimensionality of the action space. When a proposed action is...
- Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning
Current evaluation of epistemic uncertainty relies on tasks such as out-ofdistribution detection and active learning. However, the Bayes-optimal decision strategies for these tasks do not coincide with the scores commonly used to quantify epistemic uncertainty. Building on the epistemic reject-optio...
- CrimeNER Demo: Named-Entity Recognition in the Crime Domain
We present CrimeNER Demo, an AI-powered platform that enables us to extract general crime-related information from documents and classify them into entity types with two levels of granularity. We provide pretrained NER models on the CrimeNER database, and we give the possibility to users to provide ...
- Transcoders for Investigating Deception in Language Models
Transcoders have recently emerged as a promising approach for mechanistic interpretability (MI), enabling circuit-level analysis of model behaviour. In this paper, we investigate the use of transcoders to analyse deceptive behaviour in language models, a behaviour that poses a safety and security ri...
- On-Policy Delta Distillation
On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervision from a teacher model. Although on-policy distillation has been studied and applied across various settings, its fundam...
- Grokipedia vs Wikipedia: An LLM-Based Audit of Political Neutrality along Ideologies
Online encyclopedias shape political opinion and, through it, democratic discourse. In late 2025, Grokipedia was released, an encyclopedia written entirely by the LLM Grok. One motivation behind the project was to provide an unbiased alternative to Wikipedia, which has faced accusations of "left-win...
- Rubrics on Trial: Evolving Rubrics from a Single Query via Synthetic Pairwise Evidence
Rubrics provide structured, fine-grained signals for training and evaluating large language models (LLMs). Yet reliable query-specific rubrics are difficult to construct. Existing approaches often derive supervision from human-written rubrics, preference data, or sampled responses. Direct query-to-r...
- Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation
Reasoning language models (RLMs) have demonstrated impressive performance in domains such as mathematics and coding. These domains permit reliable verification of model outputs, which is important for enabling the reinforcement learning that drives RLM performance gains. However, training RLMs on do...
- The Energy Society: A Simulation Environment for Studying Agent Cooperation under Survival Pressure
LLM-based agents are increasingly deployed in multi-agent environments whose incentives can shape their behavior. We introduce The Energy Society, a minimal survival economy for studying how competitive and cooperative incentives affect emergent behavior when inference cost is directly tied to survi...
- SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based reinforcement learning (RL) provides a practical optimization paradigm, but its sparse trajectory-level rewards offer limite...
- Dialogue Summarization with Emotion Dynamics Using Topic- and Participant-Centric Decomposition
Existing text summarization research has focused much on monologic information (e.g., newspaper articles, reports) without accounting for the interaction between speakers or authors. In contrast, dialogues are a rich communication channel where multiple participants conduct back and forth exchanges ...
- CoTu at EXACT 2026: Neuro-Symbolic Reasoning for Transparent Educational QA
Transparent educational question answering asks for answers that are not only correct but explainable, and doing so with small models rules out the reasoning power of the largest proprietary systems. The EXACT 2026 competition poses this problem concretely: open-weight language models of at most 8B ...
- The Misclassification of Autistic Writing as AI-Generated
Recent findings suggest that detection models for artificial intelligence (AI) cannot accurately identify AI-generated text and may exhibit bias against certain minority groups. In the present study, anecdotal claims that autistic writers more often have their work flagged as AI-generated are examin...
- Gold-Guided Programmatic Distillation for Financial Reasoning over Hybrid Tables and Text
Financial question answering over hybrid tabular and textual data may require multi-source reasoning and precise numerical computation. While large language models (LLMs) can generate intermediate reasoning steps, natural-language rationales remain prone to arithmetic errors, making them an unreliab...
- Harnessing LLMs for Reliable Academic Supervision: A Comparative Study
Large language models routinely produce fluent answers to single-shot prompts, yet deploying them as reliable components of a domain decision system is substantially harder. Closing this gap is the work of harness engineering: the deliberate composition of deterministic scaffolding (symbolic filters...
- Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment
Efficient multimodal document question answering with explicit visual grounding, locating the precise document region that supports each answer remains an open challenge. Current approaches bifurcate into Supervised Fine-Tuning (SFT), which requires large annotated datasets and reaches optimization ...
- D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding
Speculative decoding accelerates large language model (LLM) inference without compromising output quality. Recent parallel drafting methods further improve single-request performance by decoupling draft length from drafting latency, enabling longer drafts and higher mean accepted tokens (MAT). Howev...
- Routing Ceilings Are Domain-Independent: Structural Prior Injection in Code Security Vulnerability Detection
Large language models (LLMs) exhibit a well-documented gap between latent capability and consistent activation: the router hypothesis posits that models possess the knowledge to solve a task but lack reliable internal routing to activate it. Prior work in formal mathematical reasoning (SAIR, Cázares...
- Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization
Reinforcement learning with verifiable rewards (RLVR) commonly uses entropy for advantage shaping. However, entropy cannot distinguish useful uncertainty from detrimental confusion, limiting its effectiveness as a correctness signal. We propose Contrastive Policy Optimization (CPO), which uses token...
- Investigating first-language bias in LLM-based automated essay scoring: A cross-prompt evaluation of an open-weight AI-model on TOEFL essays
This study examines the cross-prompt generalization and first-language (L1) scoring effects of a LoRA-adapted open-weight large language model (Gemma-3-27B-it) applied to automated essay scoring. Using the identical model and inference configuration reported in "AiAWE: An Open-Source LLM Automated W...
- Memory-Driven Self-Disclosure and Relational Turning Points: A Longitudinal Multimodal Study of Human-AI Interaction
As conversational AI systems are designed for repeated use, a central question is how a series of interactions becomes a relationship. We present a longitudinal multimodal study of a memory-augmented conversational agent (24 participants x 10 sessions), in which participants rated five relational co...
- How Well Does AI-Generated Feedback Work? Intrinsic and Extrinsic Evaluation across more than 20,000 EFL Essay Drafts
This study examines feedback in English as a Foreign Language (EFL) writing contexts, focusing on written corrective feedback (WCF). Large language models (LLMs) can provide WCF at scale, but aligning them with pedagogical best practices remains an ongoing challenge. WCF meeting criteria like factua...
- MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA
Large language models (LLMs) have demonstrated strong reasoning performance, but their tendency to hallucinate limits their reliability in knowledge-intensive tasks requiring up-to-date and grounded information. Combining knowledge graphs (KGs) with LLMs facilitates the use of explicit symbolic know...
- Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models
A standard recipe for distilling the reasoning ability of large language models (LLMs) is to sample chains of thought from the model, keep those that reach the correct final answer, and fine-tune on the survivors. When sampling fails, a common fix shows the generator the gold answer and asks it to w...
- Controlled Reformulation Testing for Logical Consistency in Large Language Models
Large language models (LLMs) frequently contradict themselves when the surface form of a logically equivalent question changes. We present a benchmark of 350 question families (1,750 total questions) for Controlled Reformulation Testing (CRTBench) to evaluate logical invariance. In this benchmark, w...
- RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning
Multi-step retrosynthesis planning seeks to decompose a target molecule into commercially available building blocks through a sequence of feasible reactions. The vast combinatorial search space makes this task challenging even for expert chemists. Traditional methods combine tree search with offline...
- LLM Evaluators are Biased across Languages
LLM evaluators (trained reward models and prompted LLM-as-a-Judge) are routinely validated via pairwise accuracy. In a multilingual setting, this operates under the premise that high pairwise accuracy implies reliable, language-neutral scoring. We show that this assumption does not hold. We conduct ...
- Linear representations of grammaticality in neural language models
Whether neural language models (NLMs) possess the ability to distinguish strings on the basis of their grammaticality remains a debated topic in the computational linguistics literature. Existing evidence has largely relied on probability-based measures, testing whether models assign higher probabil...
- Does Multi-Agent Debate Improve AI Feedback on Research Papers?
Probably not, at least for meta-analyses in economics. In a pre-registered, identity-masked, within-paper experiment, the authors of 44 meta-analyses ranked three AI reports on their own paper by usefulness for improving it: a single pass by a frontier model against two multi-agent debate tools we b...
- Penny: Transition Network Analysis of Learner-Chatbot Interactions in Scaffolded EFL Writing
Generative AI chatbots promise to transform English as a Foreign Language (EFL) writing by providing immediate, personalised feedback. However, their pedagogical value depends on how learners engage with them - a process often treated as a "black box." This study uses Transition Network Analysis to ...
- CityLLM: A framework for natural-language querying of semantic 3D city models
Semantic 3D city models provide rich geometric and semantic information, but remain challenging for non-experts and interdisciplinary researchers to access and query due to their complex structures and specialized data formats. To address this issue, we present CityLLM, a framework for natural-langu...
- Nuvio
Connect your X bio to your MRR and GA4 for auto updates
- xHC: Expanded Hyper-Connections
Hyper-Connections (HC) expand the residual stream of Transformers into $N$ parallel streams, providing a form of memory scaling beyond model width and depth. Manifold-Constrained HC (mHC) stabilizes this formulation at scale. The large gains from $N{=}1$ to $N{=}4$ suggest residual-stream expansion ...
- WrAFT: a Modularized Automated Writing Evaluation System for Argumentative Essays
This study presents WrAFT, a Writing Assessment and Feedback Tool, that delivers both accurate and reliable scores and effective comprehensive feedback to argumentative essays. WrAFT adopts a modular design by dividing automated writing evaluation (AWE) tasks into scoring, surface-level feedback, an...
- DAPGNet: Dynamic Adaptive Physics-Guided Graph Diffusion Network for Hyperspectral Image Classification
Hyperspectral image (HSI) classification requires reliable pixel-relation modeling under spectral variability, mixed pixels, and heterogeneous boundaries. Existing graph-based HSI classifiers usually construct graph topology from spatial proximity, superpixel connectivity, or learned feature affinit...
- AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning
Multimodal models such as CLIP learn a shared embedding space for cross-modal retrieval, but continual adaptation to sequentially arriving data can disrupt the cross-modal alignment acquired from earlier phases. Conventional continual-learning methods return a single checkpoint, which commits every ...
- Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding
Multimodal Large Language Models (MLLMs) have demonstrated substantial promise in spatial understanding. Existing works typically incorporate prior knowledge extracted from a pre-trained foundation model to further enhance the spatial awareness of MLLMs. In this paper, we first reveal that when inte...
- RoGS: Adaptive Meshgrid Gaussian for Large-Scale Road Surface Mapping
Road surface mapping plays a crucial role in autonomous driving, supporting high-definition map generation, lane-level perception, and automatic road annotation. Recent mesh-based road surface reconstruction methods have shown promising results, but they still suffer from limited reconstruction qual...
- Weakly-Supervised RGB-D Salient Object Detection via SAM-driven Pseudo Annotation and State Space Interaction-based Diffusion
Weakly-supervised RGB-D Salient Object Detection (SOD) is explored to reduce the heavy burden of pixel-level annotations. But scribble annotations lack the structure and details of objects, resulting in inaccurate saliency maps. In this paper, we propose a novel scribble-supervised RGB-D SOD method,...
- On Success and Simplicity: A Second Look at Transferable Vision-Language Attack Pipeline
Vision-Language Pre-training Models (VLPMs) are known to be vulnerable to adversarial attacks. Recent transferable attacks on VLPMs have followed a common pipeline with complicated loss functions or multi-stage text/image attacks. However, in this paper, we demonstrate that such a sophisticated atta...