AI News Today

<!-- SC_OFF --><div class="md"><p>Hi everyone,</p> <p>I'm working on extracting the hierarchical structure of long PDF documents (legal/regulatory text, lots of numbered sections) and would like to gather some feedback on my approach before committing to it.</p> <p><strong>What I've done so far:</strong> I render each PDF page to an image and run it through <a href="https://huggingface.co/baidu/Unlimited-OCR">Baidu's DeepSeek-OCR model</a>. It returns each detected block with a bounding box <cod

NVIDIA has released Cosmos 3 Edge, a 4-billion-parameter open world model built to run on-device. It helps robots and vision AI agents understand surroundings, reason in real time, and generate robot actions locally. The Cosmos 3 family included Cosmos 3 Nano (16B) and Cosmos 3 Super (64B) shipped on May 31, 2026 at GTC Taipei. […] The post NVIDIA Releases Cosmos 3 Edge: A 4B-Parameter Open World Model That Reasons and Generates Robot Actions On-Device appeared first on MarkTechPost .

<!-- SC_OFF --><div class="md"><p><strong>TL;DR:</strong> I’m reproducing the trait-persistence result from <a href="https://arxiv.org/abs/2606.24014">arXiv:2606.24014</a> on one RTX 3090. Before I can test persistence I need to <em>install</em> a trait via RL — and my GRPO run moves the trait only <strong>+2.4 points</strong> (95% CI [+0.2, +4.8]) when I need ~+15. Training is mechanically healthy and I’ve ruled out the obvious culprits. Looking for advice from people who’ve done small-scale RL

arXiv:2607.16196v1 Announce Type: new Abstract: Soft, sensorized companions offer a physically safe and emotionally intuitive interface for socially assistive technologies, yet their deformability and multichannel tactile sensing complicate the robust interpretation of human affect. This study presents a complete open-source MATLAB-based framework for the development and validation of compact deep learning models for affective touch recognition in soft interactive companions. As a primary contri

arXiv:2607.16197v1 Announce Type: new Abstract: As artificial intelligence systems are deployed in open-ended, high-stakes settings, a critical dimension remains unmeasured: how perceived risk is translated into action. We test whether large language models (LLMs) exhibit systematic and consistent risk attitudes under uncertainty. We introduce a cross-domain framework that decouples contextual risk belief from categorical decision, and apply it to six representative LLMs and 100 human participan

arXiv:2607.16198v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have emerged as the leading paradigm for link prediction, enabling the inference of missing connections and the anticipation of potential future links. However, existing reviews lack systematic exploration specifically targeting underlying GNN architectures and diverse graph structures. To address this critical gap, this paper provides a comprehensive review of GNN-based link prediction from a novel and dedicated GNN pe

arXiv:2607.16199v1 Announce Type: new Abstract: Multi-agent LLM systems increasingly rely on a Planner to decompose goals into sub-task sequences that downstream Executor and Critic agents execute and audit. We identify the planning phase as a critical attack surface: a single injection into the Planner's context achieves cascade amplification, corrupting all downstream sub-tasks simultaneously. We introduce PlanFlip, a framework comprising four planning-phase prompt injection attacks -- GoalSub

arXiv:2607.16200v1 Announce Type: new Abstract: AI agent systems that couple large language models (LLMs) with external tools and APIs are inherently non-deterministic: LLM sampling variance, external API state, CDN infrastructure headers, and execution-environment noise collectively prevent any prior agent run from being faithfully re-executed. Existing observability platforms capture execution logs but cannot reproduce a run in isolation. We present agrepl, a developer-first CLI framework for

arXiv:2607.16201v1 Announce Type: new Abstract: Ontology engineering remains a critical bottleneck in knowledge-intensive AI systems. Existing automated approaches either depend on predefined schemas, operate within narrow domains, or produce unstructured outputs unsuitable for downstream pipelines. We introduce Generative Ontology Induction (GOI), a domain-agnostic framework that induces a generative blueprint - entities, dimensions, properties, relationships, and constraints - from a corpus of

arXiv:2607.16202v1 Announce Type: new Abstract: AI democratization is not primarily a question of matching frontier-scale generality; it is a question of whether capable models can be selected, audited, and specialized under hardware and governance constraints that ordinary institutions can actually satisfy. This paper studies that problem through a controlled evaluation of nine open-weight language models between 135M and 3B parameters on a 1,085-example, 16-topic multiple-choice benchmark desi

arXiv:2607.16204v1 Announce Type: new Abstract: Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments. Hand-curated environments with fixed task and reward difficulties become ineffective signals as model performance improves, and sparse rewards over long horizons induce mode collapse on specific workflows or tool structures. World models that simulate environment states have matched pure rollout performance, making them promising for sca

arXiv:2607.16205v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has emerged as a standard approach for enhancing reasoning in large language models, which typically optimizes the policy by contrasting multiple self generated rollouts. However, we identify a critical support limited bottleneck in this paradigm: on challenging reasoning tasks, the target model's samples often exhibit semantic redundancy, converging into the same erroneous "reasoning basins" that offe

arXiv:2607.16206v1 Announce Type: new Abstract: This paper introduces PPO-HSC (Proximal Policy Optimization with High-order Sampling Coverage), an exploratory reinforcement learning framework designed to address the "Invisible Shackles" of mode collapse in Large Language Model (LLM) fine-tuning. While standard Reinforcement Learning from Verifiable Rewards (RLVR) effectively reinforces high-reward trajectories, it often leads models to over-optimize known solutions, sacrificing curiosity and the

arXiv:2607.16207v1 Announce Type: new Abstract: Membership inference attacks (MIAs) test whether a candidate example appeared in a model's training data. We study MIAs for fine-tuned discrete diffusion language models (dLLMs), where membership means inclusion in the target model's fine-tuning set. Unlike autoregressive language models, dLLMs allow an attacker to choose arbitrary mask sets and obtain token distributions for all masked positions in parallel. The prior dLLM attack, SAMA, follows a

arXiv:2607.16210v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly applied in complex, safety-critical domains, yet the lack of rigorous behavioral guarantees for neural network-based policies remains a major barrier to deployment. Recent advances in policy expressiveness and scale have intensified this challenge, leading to a rapidly growing but conceptually fragmented body of work on RL policy verification. This survey provides a unifying perspective on RL verification

arXiv:2607.16211v1 Announce Type: new Abstract: LLM agents augmented with persistent memory can recall past interactions, but existing systems suffer from two limitations: flat, unstructured storage loses relational context needed for multi-hop and temporal reasoning, and reliance on expensive LLM-based classification makes them impractical for latency-sensitive deployment. Without mechanisms to validate new information against stored knowledge, these systems silently accumulate contradictions.

arXiv:2607.16212v1 Announce Type: new Abstract: Large language models hallucinate numbers and units when summarizing scientific text, a failure mode that can silently invert a scientific claim. We recast the detection of such errors as typed verification: we introduce a five-class typed-quantity error taxonomy and a 1500-item benchmark, rewritten from PMC and arXiv sources and labeled by two independent LLM annotators with adjudication (Krippendorff's alpha = 0.882). A ModernBERT encoder fine-tu

arXiv:2607.16213v1 Announce Type: new Abstract: Large Language Models (LLMs) generate text autoregressively, relying on a key-value (KV) cache whose memory footprint grows linearly with context length, creating a major bottleneck. Recent compression methods mitigate this cost via token merging; however, these approaches often rely on indiscriminate aggregation, which degrades representations and introduces attention sag, a mismatch where merged tokens receive the same softmax mass as individual

arXiv:2607.16215v1 Announce Type: new Abstract: Existing guardrail systems for large language model agents operate as binary classifiers that block unsafe content, leaving organizations to discard failing outputs and retry from scratch. We introduce RAIL Guard, a closed-loop responsible AI pipeline that evaluates LLM outputs across eight measurable dimensions and iteratively remediates failing outputs through an evaluate-rewrite-reevaluate loop. We evaluate the pipeline across three experiments

arXiv:2607.16313v1 Announce Type: new Abstract: Traditional controllers are designed for specific systems and do not transfer across different system orders and dynamics. We present a Generalist Controller, a learning-based controller capable of controlling systems of varying orders and dynamics. The approach introduces a novel dynamic state-space representation using attention mechanisms with masking, enabling a single neural network, trained in one shot, to handle systems with different dimens

arXiv:2607.16339v1 Announce Type: new Abstract: Diffusion-based Large Language Models(DLLMs) enable parallel generation via Semi-Autoregressive (SAR) decoding in text generation. However, current methods suffer from severe operator-level redundancy: they recompute the entire sequence during denoising steps, ignoring that the prefix and masked suffix remain invariant within a block. We propose LaCache, a training-free acceleration framework that alleviates this redundancy through lossless caching

arXiv:2607.16421v1 Announce Type: new Abstract: It has long been recognized that humans have the ability to switch between fast, reactive decision-making and slower, deliberative planning. In this paper, we study the question of how to learn this ability, known as meta-reasoning, in artificial agents. We model reactive decision-making as a policy that directly maps state observations to actions. Such policies can be trained with reinforcement learning (RL) or imitation learning, but may generali

arXiv:2607.16523v1 Announce Type: new Abstract: One of the main strengths of Constraint Programming is the ability to reduce the search space via propagation. However, propagation is a double-edged sword, with more pruning power coming at the price of larger computation time. For each problem constraint, the best propagator depends on the specific instance and may change at search time. In the literature, Machine Learning (ML) techniques and activity-based heuristics have been applied respective

arXiv:2307.00919v2 Announce Type: replace Abstract: Over the past decade deep learning has revolutionized the field of computer vision, with convolutional neural network models proving to be very effective for image classification benchmarks. However, a fundamental theoretical questions remain answered: why can they solve discrete image classification tasks that involve feature extraction? We address this question in this paper by introducing a novel mathematical model for image classification,

arXiv:2511.20332v3 Announce Type: replace Abstract: This article trained a network for perceiving three-dimensional motion information of binocular vision target, which can provide real-time three-dimensional coordinate, velocity, and acceleration, and has a basic spatiotemporal perception capability. Understood the ability of neural networks to fit nonlinear problems from the perspective of PID. Considered a single-layer neural network as using a second-order difference equation and a nonlinear

arXiv:2607.16194v1 Announce Type: new Abstract: In modern financial markets, decision-makers increasingly rely on quantitative methods to navigate complex trade-offs among multiple, often conflicting objectives. This paper addresses constrained multi-objective optimization (MOO) with an application to portfolio optimization for minimizing risk and maximizing return. To address existing gaps, we propose a novel reinforcement learning (RL)-guided non-dominated sorting genetic algorithm II (NSGA-II

arXiv:2607.16227v1 Announce Type: new Abstract: LLMs are increasingly deployed in security-critical systems across healthcare, finance, education, and decision support, yet their inability to forget creates serious cybersecurity, privacy, and safety risks. Sensitive personal information, copyrighted material, hazardous domain knowledge, and memorized training data remain encoded across billions of parameters long after deployment, leaving models vulnerable to extraction, jailbreak attacks, membe

arXiv:2607.16228v1 Announce Type: new Abstract: Most tensor-kernel correctness tests go through a fixed-shape all close-style check with hand-picked absolute and relative tolerances. The thresholds are copied across the corpus and rarely revisited. We mine the element-wise error distribution of every test case from accumulated cloud GPU runs across the 26-entry gpuemu corpus and 2 dtypes (8,076 result rows). We then ask one empirical question: what absolute tolerance would the kernel itself, obs

arXiv:2607.16231v1 Announce Type: new Abstract: Modern neural networks can fit corrupted training labels, making noisy-label learning a useful setting for studying memorization-driven overfitting. Most regularization methods modify the objective, architecture, or data distribution; here we instead study a geometric intervention on the optimizer update itself. We evaluate OrthoGrad, which removes the component of each weight gradient parallel to the current weight vector, in noisy-label image cla

arXiv:2607.16239v1 Announce Type: new Abstract: AI judges offer a scalable, low-cost alternative to human evaluation, but their outputs can be biased relative to human preferences and highly item-dependent, varying across judges, tasks, and domains. When uncalibrated AI evaluations are used for model ranking, item scoring, or population-level quality reporting, these biases can directly distort downstream decisions. We propose BACON, a four-stage pipeline that combines budgeted human calibration

arXiv:2607.16247v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have empowered embodied agents to execute complex household tasks, they struggle to proactively handle dynamically emerging hazards during closed-loop interactions. Existing safety approaches often rely on runtime guardrails to block unsafe actions or induce excessive caution, which severely stalls task progress instead of actively resolving the underlying risks. To break this safety-progress trade-off, we introd

arXiv:2607.16251v1 Announce Type: new Abstract: Spatio-Temporal Foundation Models (STFMs) aim to learn generalizable representations of complex dynamical systems across space and time. However, existing approaches suffer from distributional bias in real-world pre-training data, structural bottlenecks of autoregressive or diffusion-based paradigms, and objectives that overemphasize point-wise reconstruction in noisy observation space.We propose \textbf{NeoST}, the first spatio-temporal foundation

arXiv:2607.16259v1 Announce Type: new Abstract: Pretrained models are typically ranked on multi-task leaderboards to assess their effectiveness across diverse tasks. Rank confidence intervals were recently introduced as a method to quantify the uncertainty in these rankings by aggregating pairwise hypothesis tests. In this work, we analyze the sources of uncertainty in the knowledge evaluation benchmark MMLU and show how hypothesis tests can be modified to account for their effects. We demonstra

arXiv:2607.16268v1 Announce Type: new Abstract: Adaptive optimizers such as Adam and AdamW apply the same update rule regardless of whether training is in a chaotic early phase or near convergence. We introduce PsiLogic, an optimizer that augments Adam with a dynamic Active Cancellation Term gated by a dual exponential moving average (EMA) of scale-normalized gradient norms. The resulting chaos detector strengthens damping when gradient statistics are unstable and fades to zero as training stabi

arXiv:2607.16384v1 Announce Type: new Abstract: For stochastic gradient descent (SGD) with a constant stepsize $\alpha$, the invariant law of the iterates, centered at a minimizer, describes the behavior of the algorithm over long time horizons. In the strongly convex case, this invariant law has the familiar $\sqrt{\alpha}$ scaling and a Gaussian limit as $\alpha\downarrow 0$. We show that this behavior changes fundamentally for convex objectives $H$ with flat minima and (sub)quadratic tails. M

arXiv:2607.16449v1 Announce Type: new Abstract: Accurate path loss prediction is a critical component of wireless network planning. Current path loss prediction methods typically struggle to balance the trade-off between accuracy and computational efficiency. This paper proposes the Efficient Attention Radio Map Estimation Network (EA-RMENet) which is an image data-driven, deep learning (DL) model designed for radio map estimation (RME). EA-RMENet uses a U-Net framework with an EfficientNetB5 en

arXiv:2607.16455v1 Announce Type: new Abstract: The increasing use of first-person-view drones in modern conflicts has created a demand for compact and reliable detection systems capable of operating in complex electromagnetic environments. These drones continuously transmit video signals through onboard video transmitters, generating radio-frequency emissions that can be exploited for early detection. This study investigates the use of lightweight convolutional neural networks for automated det

arXiv:2607.16493v1 Announce Type: new Abstract: Multi-task deep learning models that jointly perform fault classification and remaining useful life (RUL) regression are increasingly used in predictive maintenance, yet reported performance can be strongly affected by how sliding-window sequences are split into training and test sets. We investigate this issue using AMTLNet, an attention-enhanced multi-task architecture, on three public benchmarks: NASA C-MAPSS, NASA IMS, and the UCI Hydraulic Sys

arXiv:2607.16524v1 Announce Type: new Abstract: Cooperative multi-agent RL systems routinely use team-averaged rewards, a feedback-attribution choice that gives each agent the team outcome regardless of its individual contribution. We ask whether this leaves a measurable signature, geometric or behavioral, on learned representations. We propose EffRank/$n$ (effective rank normalized by agent count) and $D_\text{act}$ (mean pairwise KL divergence between agents' action distributions) as low-overh

arXiv:2607.16528v1 Announce Type: new Abstract: We study hierarchical domain generalization as a problem of extrapolation from finite observed regions to an entire instance space, replacing i.i.d. sampling with arbitrary domain hierarchies. We show that the central obstruction is not only the complexity of the hypothesis class, but the train/test domain partition through which evidence is revealed. In particular, no matter how small the class or how large the training size, some partition makes